Recommender systems help people make choices by suggesting items relevant to their needs and preferences. They trace their origins to the early 1990s. Bellcore hosted a Workshop on “High-Performance Information Filtering” in 1991, which led to a special issue of Communications of the ACM one year later. That special issue included a paper on a then-novel technique called collaborative filtering , which became a foundation of the field in the years that followed. As recommender systems enter their fourth decade, we look back at the field using a publication dataset of more than 2.5 million articles, including more than 50,000 core recommender systems articles. We use this dataset to explore the development of the field and its relationship to various adjacent research fields. We examine the research topics that have evolved within recommender systems over the years and the most influential research produced during this time. Our analysis reveals two largely separate communities of researchers, and we explore how these communities differ in terms of their output and impact. Finally, we discuss how we can identify recent emerging topics using measures of publication and citation momentum, and we present several emerging topics that appear destined to play a significant role in the immediate future of the field.

Users with large domain knowledge can be reluctant to use prediction models. This also applies to the sports domain, where running coaches rarely rely on marathon prediction tools for race-plan advice for their runners’ next marathon. This paper studies the effect of adding interactivity to such prediction models, to incorporate and acknowledge users’ domain knowledge. In think-aloud sessions and an online study, we tested an interactive machine learning tool that allowed coaches to indicate the importance of earlier races feeding into the model. Our results show that coaches deploy rich knowledge when working with the model on runners familiar to them, and their adaptations improved model accuracy. Those coaches who could interact with the model displayed more trust and acceptance in the resulting predictions.

Preparing for the marathon involves many weeks of dedicated training. Achieving the right balance between building strength and endurance and the need for rest and recovery is a must, if a runner is to arrive at the start-line injury-free and ready to achieve their desired finish-time. However, because most recreational runners rely on generic training plans, they can struggle to find this balance, which can impact their motivation, health, and performance. In this paper, we describe a novel case-based reasoning approach to fine-tuning a runner’s training by recommending training adjustments based on the patterns of similar runners at corresponding points in their marathon training. The approach is designed to target training adjustments that are based on similar runners but with varying race goals, to allow runners to adjust their training for slower or faster finish-times, as their training progresses and motivations change. We evaluate the recommendations produced using a large-scale real-world dataset according to several factors: (i) the plausibility of the recommended training adjustment, (ii) the effectiveness of the adjustment when it comes to achieving a particular performance goal, and (iii) the safety of the adjustment in terms of the degree of risk that it will lead to an injury or otherwise disrupt training. Our findings suggest that plausible, effective, and safe recommendations can be generated for runners when evaluated against a range of race goals.

Recent years have seen a rise in smartphone applications promoting health and well being. We argue that there is a large and unexplored ground within the field of recommender systems (RS) for applications that promote good personal health. During the COVID-19 pandemic, with gyms being closed, the demand for at-home fitness apps increased as users wished to maintain their physical and mental health. However, maintaining long-term user engagement with fitness applications has proved a difficult task. Personalisation of the app recommendations that change over time can be a key factor for maintaining high user engagement. In this work we propose a reinforcement learning (RL) based framework for recommending sequences of body-weight exercises to home users over a mobile application interface. The framework employs a user simulator, tuned to feedback a weighted sum of realistic workout rewards, and trains a neural network model to maximise the expected reward over generated exercise sequences. We evaluate our framework within the context of a large 15 week live user trial, showing that an RL based approach leads to a significant increase in user engagement compared to a baseline recommendation algorithm.

These days we have all become increasingly aware of the role that exercise plays in a healthy lifestyle. Activities such as cycling, triathlons, and running have become popular ways for people to keep fit and test their abilities. For recreational athletes there is no shortage of training advice or programmes to follow, yet most offer only one-size-fits-all, or minimally tailored guidance, which often leaves novices under-supported on their fitness journeys. In this work, we describe a case-based reasoning system to generate personalised training recommendations for marathon runners, based on their training histories and the training histories of similar runners with comparable race goals. The system harnesses the type of activity data that is routinely collected by smartwatches and apps like Strava. It uses prefactual explanations to suggest to runners how they may wish to adjust their training as their fitness goals evolve. We evaluate the approach using a large-scale dataset of more than 300,000 real-world runners and we show that it is feasible to generate tailored, personalised recommendations for up to 80% of these runners. Additionally, we show that the recommendations produced are realistic and reasonable for a runner to implement, as part of their training programme. These suggestions typically include a small number (3-5) of incremental training adaptations, such as a change in weekly distance, long-run distance, or mean training pace. We argue that by engaging runners in this type of dialog about their training progress and race goals, we can better support novice runners, as their training unfolds, which may help to keep runners motivated on their long journey to race day.

Financial forecasting has been an important and active area of machine learning research because of the challenges it presents and the potential rewards that even minor improvements in prediction accuracy or forecasting may entail. Traditionally, financial forecasting has heavily relied on quantitative indicators and metrics derived from structured financial statements. Earnings conference call data, including text and audio, is an important source of unstructured data that has been used for various prediction tasks using deep earning and related approaches. However, current deep learning-based methods are limited in the way that they deal with numeric data; numbers are typically treated as plain-text tokens without taking advantage of their underlying numeric structure. This paper describes a numeric-oriented hierarchical transformer model (NumHTML) to predict stock returns, and financial risk using multi-modal aligned earnings calls data by taking advantage of the different categories of numbers (monetary, temporal, percentages etc.) and their magnitude. We present the results of a comprehensive evaluation of NumHTML against several state-of-the-art baselines using a real-world publicly available dataset. The results indicate that NumHTML significantly outperforms the current state-of-the-art across a variety of evaluation metrics and that it has the potential to offer significant financial gains in a practical trading context.

A recommendation engine that relies solely on interactions between users and items will be limited in its ability to provide accurate, diverse and explanation-rich recommendations. Side information should be taken into account to improve performance. Methods like Factorisation Machines (FM) cast recommendation as a supervised learning problem, where each interaction is viewed as an independent instance with side information encapsulated. Previous studies in top-K recommendation have incorporated knowledge graphs (KG) into the recommender system to provide rich information about the relationships between users, items and entities. Nevertheless, these studies do not explicitly capture the preference of users for the side information. Furthermore, some studies explain the recommendation, but there is no unified method of measuring explanation quality.

Every year millions of people, from all walks of life, spend months training to run a traditional marathon. For some it is about becoming fit enough to complete the gruelling 26.2 mile (42.2 km) distance. For others, it is about improving their fitness, to achieve a new personal-best finish-time. In this paper, we argue that the complexities of training for a marathon, combined with the availability of real-time activity data, provide a unique and worthwhile opportunity for machine learning and for recommender systems techniques to support runners as they train, race, and recover. We present a number of case studies-a mix of original research plus some recent results-to highlight what can be achieved using the type of activity data that is routinely collected by the current generation of mobile fitness apps, smart watches, and wearable sensors.

Linyi Yang, Jiazheng Li, Padraig Cunningham, Yue Zhang, Barry Smyth, Ruihai Dong. Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers). 2021.

In this paper, we propose a novel communication-efficient algorithm for distributed matrix factorisation. Our goal is to find a good trade-off between the communication overhead and the overall model training time. In our setting, the training data is distributed across multiple servers that aim to learn a joint machine learning model. In contrast to standard distributed computation, due to privacy concerns, the participating servers are not allowed to share raw data, however, sharing of the non-personal model parameters is allowed. We investigate the draw-backs of traditional strongly coordinated distributed techniques and compare them to weakly coordinated gossip approaches. The advantage of strongly coordinated approaches is that the learning process closely mimics that of a centralised algorithm and hence this approach can keep the overall training time at a minimum. However, this is at the expense of a large communication footprint of the algorithm. On the other hand, the weakly coordinated gossip approach offers a communication efficient solution that can take a large amount of training time to reach a good accuracy. As a solution, we develop a hybrid approach combining the above two approaches. We apply the hybrid approach on a latent factor model solving a top-N recommendation problem and we show that the hybrid approach achieves good accuracy in relatively short training time with minimal communication overhead particularly on very sparse data.

Ancient oracle bone inscriptions (OBIs) are important Chinese cultural artefacts, which are difficult and time-consuming to decipher even by the most expert paleographers and, as a result, a large proportion of excavated OBIs remain unidentified. In practice, OBIs are deciphered by translating between different writing systems; Chinese writing systems have evolved over time and ancient OBIs can be deciphered by translating their inscriptions to a known inscription in an adjacent writing system, but this is a complex and time-consuming process. In this paper we propose a novel case-based system, to support this task, allowing a paleographer to present an unknown inscription (image) as a query, to receive a set of similar images from an adjacent writing system with associated scholarly information, and so help guide the deciphering of the query. One important contribution of this work involves the use of an auto-encoder to learn suitable image representations to capture the relationship between two adjacent writing systems. We demonstrate the effectiveness of this approach using a novel, purpose-built case base, and discuss its use in a paleographic setting.

In recent years, there has been an explosion of AI research on counterfactual explanations as a solution to the problem of eXplainable AI (XAI). These explanations seem to offer technical, psychological and legal benefits over other explanation techniques. We survey 100 distinct counterfactual explanation methods reported in the literature. This survey addresses the extent to which these methods have been adequately evaluated, both psychologically and computationally, and quantifies the shortfalls occurring. For instance, only 21% of these methods have been user tested. Five key deficits in the evaluation of these methods are detailed and a roadmap, with standardised benchmark evaluations, is proposed to resolve the issues arising; issues, that currently effectively block scientific progress in this field.

In the area of natural language processing, various financial datasets have informed recent research and analysis including financial news, financial reports, social media, and audio data from earnings calls. We introduce a new, large-scale multi-modal, text-audio paired, earnings-call dataset named MAEC, based on S&P 1500 companies. We describe the main features of MAEC, how it was collected and assembled, paying particular attention to the text-audio alignment process used. We present the approach used in this work as providing a suitable framework for processing similar forms of data in the future. The resulting dataset is more than six times larger than those currently available to the research community and we discuss its potential in terms of current and future research challenges and opportunities. All resources of this work are available at https://github.com/Earnings-Call-Dataset/

Corporate mergers and acquisitions (M&A) account for billions of dollars of investment globally every year, and offer an interesting and challenging domain for artificial intelligence.However, in these highly sensitive domains, it is crucial to not only have a highly robust and accurate model, but be able to generate useful explanations to garner a user's trust in the automated system.Regrettably, the recent research regarding eXplainable AI (XAI) in financial text classification has received little to no attention, and many current methods for generating textual-based explanations result in highly implausible explanations, which damage a user's trust in the system.To address these issues, this paper proposes a novel methodology for producing plausible counterfactual explanations, whilst exploring the regularization benefits of adversarial training on language models in the domain of FinTech.Exhaustive quantitative experiments demonstrate that not only does this approach improve the model accuracy when compared to the current stateof-the-art and human performance, but it also generates counterfactual explanations which are significantly more plausible based on human trials.

For elite and recreational runners alike, preparing for the marathon is a complex problem. In this work, we propose a recommender system that is capable of helping runners devise a strategy for the marathon. Using high-resolution performance data from runners' training and race performance we recommend both a realistic target time for the marathon and use collaborative filtering techniques to generate a pacing plan that allows runners to achieve that time. We demonstrate that our recommendations are capable of helping runners attain their goal time, while also helping them avoid premature fatigue and hitting the wall during the course of the race.

Federated learning (FL) is quickly becoming the de facto standard for the distributed training of deep recommendation models, using on-device user data and reducing server costs. In a typical FL process, a central server tasks end-users to train a shared recommendation model using their local data. The local models are trained over several rounds on the users' devices and the server combines them into a global model, which is sent to the devices for the purpose of providing recommendations. Standard FL approaches use randomly selected users for training at each round, and simply average their local models to compute the global model. The resulting federated recommendation models require significant client effort to train and many communication rounds before they converge to a satisfactory accuracy. Users are left with poor quality recommendations until the late stages of training. We present a novel technique, FedFast, to accelerate distributed learning which achieves good accuracy for all users very early in the training process. We achieve this by sampling from a diverse set of participating clients in each training round and applying an active aggregation method that propagates the updated model to the other clients. Consequently, with FedFast the users benefit from far lower communication costs and more accurate models that can be consumed anytime during the training process even at the very early stages. We demonstrate the efficacy of our approach across a variety of benchmark datasets and in comparison to state-of-the-art recommendation techniques.

Training for the marathon is a complex problem. In order to run an optimal time, runners must find the right workload for their current abilities and identify the correct balance between the hard work and rest throughout their training programmes. We propose a recommender system that will help guide runners through the weeks leading up to the marathon. Using a large sample of marathon training data (8730 runners), we generate user profiles that capture both a runner’s current fitness and training levels, and leverage this information to generate tailored recommendations for future weeks of training. We investigate patterns of successful runners to determine how best to schedule recommendations and training to allow for improvement in fitness levels alongside adequate rest.

Millions of people participate in marathon events every year, typically devoting at least 12-16 weeks to building their endurance and fitness so that they can safely complete these gruelling 42.2km races. Most runners follow a training plan that is tailored to their expected finish-time (e.g. sub-4 hours or 4-5 hours), and these plans will prescribe a complex mixture of training sessions to help them achieve these times. However, such plans cannot adapt to the individual needs (fitness levels, changing goals, personal preferences) of runners, providing only broad training guidance rather than more personalised support. The development of wearable sensors and mobile fitness applications facilitates the collection of a large amount of training data from runners. In this paper, we propose a recommender system that utilizes such training data to deliver more personalised training advice to runners, using ideas from case-based reasoning to reuse and adapt the training habits of similar runners. Explainability plays a significant role in this type of system, and we also describe how the predictions and recommendation advice can be presented to runners. An initial off-line evaluation is presented based on a large-scale, real-world dataset.

Nowadays we commonly have multiple sources of data associated with items. Users may provide numerical ratings, or implicit interactions, but may also provide textual reviews. Although many algorithms have been proposed to jointly learn a model over both interactions and textual data, there is room to improve the many factorization models that are proven to work well on interactions data, but are not designed to exploit textual information. Our focus in this work is to propose a simple, yet easily applicable and effective, method to incorporate review data into such factorization models. In particular, we propose to build the user and item embeddings within the topic space of a topic model learned from the review data. This has several advantages: we observe that initializing the user and item embeddings in topic space leads to faster convergence of the factorization algorithm to a model that out-performs models initialized randomly, or with other state-of-the-art initialization strategies. Moreover, constraining user and item factors to topic space allows for the learning of an interpretable model that users can visualise.

The volatility forecasting task refers to predicting the amount of variability in the price of a financial asset over a certain period. It is an important mechanism for evaluating the risk associated with an asset and, as such, is of significant theoretical and practical importance in financial analysis. While classical approaches have framed this task as a time-series prediction one – using historical pricing as a guide to future risk forecasting – recent advances in natural language processing have seen researchers turn to complementary sources of data, such as analyst reports, social media, and even the audio data from earnings calls. This paper proposes a novel hierarchical, transformer, multi-task architecture designed to harness the text and audio data from quarterly earnings conference calls to predict future price volatility in the short and long term. This includes a comprehensive comparison to a variety of baselines, which demonstrates very significant improvements in prediction accuracy, in the range 17% - 49% compared to the current state-of-the-art. In addition, we describe the results of an ablation study to evaluate the relative contributions of each component of our approach and the relative contributions of text and audio data with respect to prediction accuracy.

We propose endurance sports as a rich and novel domain for recommender systems and machine learning research. As sports like marathon running, triathlons, and mountain biking become more and more popular among recreational athletes, there exists a growing opportunity to develop solutions to a number of interesting prediction, classification, and recommendation challenges, to better support the complex training and competition needs of athletes. Such solutions have the potential to improve the health and well-being of large populations of users, by promoting and optimising exercise as part of a productive and healthy lifestyle.

We propose marathon running as a novel domain for recommender systems and machine learning. Using high-resolution marathon performance data from multiple marathon races (n = 7931), we build in-race recommendations for runners. We show that we can outperform the existing techniques which are currently employed for in-race finish-time prediction, and we demonstrate how such predictions may be used to make real time recommendations to runners. The recommendations are made at critical points in the race to provide personalised guidance so the runner can adjust their race strategy. Through the association of model features and the expert domain knowledge of marathon runners we generate explainable, adaptable pacing recommendations which can guide runners to their best possible finish time and help them avoid the potentially catastrophic effects of hitting the wall.

Conventional approaches to matrix factorisation (MF) typically rely on a centralised collection of user data for building a MF model. This approach introduces an increased risk when it comes to user privacy. In this short paper we propose an alternative, user-centric, privacy enhanced, decentralised approach to MF. Our method pushes the computation of the recommendation model to the user's device, and eliminates the need to exchange sensitive personal information; instead only the loss gradients of local (device-based) MF models need to be shared. Moreover, users can select the amount and type of information to be shared, for enhanced privacy. We demonstrate the effectiveness of this approach by considering different levels of user privacy in comparison with state-of-the-art alternatives.

Recommender systems (RS) share many features and objectives with reinforcement learning (RL) systems. The former aim to maximise user satisfaction by recommending the right items to the right users at the right time, the latter maximise future rewards by selecting state-changing actions in some environment. The concept of an RL gym has become increasingly important when it comes to supporting the development of RL models. A gym provides a simulation environment in which to test and develop RL agents, providing a state model, actions, rewards/penalties etc. In this paper we describe and demonstrate the PyRecGym gym, which is specifically designed for the needs of recommender systems research, by supporting standard test datasets (MovieLens, Yelp etc.), common input types (text, numeric etc.), and thereby offering researchers a reproducible research environment to accelerate experimentation and development of RL in RS.

We describe and evaluate a novel application of case-based reasoning to help marathon runners to achieve a personal best by: (a) predicting a challenging, but realistic race-time; and (b) recommending a race-plan to achieve this time.

Recommender systems are omni-present in our every day lives, guiding us through the vast amount of information available. However, in the academic world, personalised recommendations are less prominent, leaving students to navigate through the typically large space of available courses and modules manually. Since it is crucial for students to make informed choices about their learning pathways, we aim to improve the way students discover elective modules by developing a hybrid recommender system prototype that is specifically designed to help students find elective modules from a diverse set of subjects. We can improve the discoverability of long-tail options and help students broaden their horizons by combining notions of similarity and diversity.

We describe a novel, multi-task recommendation model, which jointly learns to perform rating prediction and recommendation explanation by combining matrix factorization, for rating prediction, and adversarial sequence to sequence learning for explanation generation. The result is evaluated using real-world datasets to demonstrate improved rating prediction performance, compared to state-of-the-art alternatives, while producing effective, personalized explanations.

The history of personalisation and recommender systems is, in large part, a web-tale: a story of sites and services that learn about users, in order to provide more tailored experiences. The rapid rise of mobile computing, combined with wearable sensors, and an increasingly connected IoT world, has begun to shift the potential for personalisation, from the virtual world of the web, to the physical world in which we live, work, and play. This talk will consider exciting new application opportunities for user modelling, personalisation, and recommendation in the area of personal health and fitness, with a particular emphasis on how these technologies can help people to exercise more effectively, and by drawing from recent results for marathon runners.

Collaborative filtering (CF) is a common recommendation approach that relies on user-item ratings. However, the natural sparsity of user-item rating data can be problematic in many domains and settings, limiting the ability to generate accurate predictions and effective recommendations. Moreover, in some CF approaches latent features are often used to represent users and items, which can lead to a lack of recommendation transparency and explainability. User-generated, customer reviews are now commonplace on many websites, providing users with an opportunity to convey their experiences and opinions of products and services. As such, these reviews have the potential to serve as a useful source of recommendation data, through capturing valuable sentiment information about particular product features. In this paper, we present a novel deep learning recommendation model, which co-learns user and item information from ratings and customer reviews, by optimizing matrix factorization and an attention-based GRU network. Using real-world datasets we show a significant improvement in recommendation performance, compared to a variety of alternatives. Furthermore, the approach is useful when it comes to assigning intuitive meanings to latent features to improve the transparency and explainability of recommender systems.

User-generated reviews are a plentiful source of user opinions and interests and can play an important role in a range of artificial intelligence contexts, particularly when it comes to recommender systems. In this paper, we describe how natural language processing and opinion mining techniques can be used to automatically mine useful recommendation knowledge from user generated reviews and how this information can be used by recommender systems in a number of classical settings.

We describe a novel application for recommender systems -- helping marathon runners to run a new personal-best race-time -- by predicting a challenging, but achievable target-time, and by recommending a tailored race-plan to achieve this time. A comprehensive evaluation of prediction accuracy and race-plan quality is provided using a large-scale dataset with almost 400,000 runners from the last 12 years of the Chicago marathon.

This paper describes an approach for generating rich and compelling explanations in recommender systems, based on opinions mined from user-generated reviews. The explanations highlight the features of a recommended item that matter most to the user and also relate them to other recommendation alternatives and the user's past activities to provide a context.

To help users discover relevant products and items recommender systems must learn about the likes and dislikes of users and the pros and cons of items. In this paper, we present a novel approach to building rich feature-based user profiles and item descriptions by mining user-generated reviews. We show how this information can be integrated into recommender systems to deliver better recommendations and an improved user experience.

Recommender systems have become a familiar part of our online experiences, suggesting movies to watch, music to listen to, and books to read, among other things. To make relevant suggestions, recommender systems need an accurate picture of our preferences and interests and sometimes even our friends and influencers. This information can be difficult to come by and expensive to source. In this paper we describe a game-with-a-purpose designed to infer useful recommendation data as a side-effect of gameplay. The game is a simple, single-player matching game in which players attempt to match movies with their friends. It has been developed as a Facebook app and harnesses the social graph and likes of players as a source of game data. We describe the basic game mechanics and evaluate the utility of the recommendation knowledge that can be inferred from its gameplay as part of a live-user trial.

Recommender systems learn about our preferences to make targeted suggestions. In this paper we outline a novel game-with-a-purpose designed to infer preferences at scale as a side-effect of gameplay. We evaluate the utility of this data in a recommendation context as part of a small live-user trial.

Real-time information streams such as Twitter have become a common way for users to discover new information. For most users this means curating a set of other users to follow. However, at the moment the following granularity of Twitter is restricted to the level of individual users. Our research has highlighted that many following relationships are motivated by a subset of interests that are shared by the users in question. For example, user A might follow user B because of their technology related tweets, but shares little or no interest in their other tweets. As a result, this all-or-nothing following relationship can quickly overwhelm users' timelines with extraneous information. To improve this situation we propose a user profiling approach based on the topical categorisation of users' posted URLs. These topics can then be used to filter information streams so that they focus on more relevant information from the people they follow, based on their core interests. In particular, we present a system called CatStream that provides for a more fine-grained way to follow users on specific topics and filter our timelines accordingly. We present the results of a live-user study that shows how filtered timelines offer a better way to organise and filter their information streams. Most importantly users are generally satisfied with the categories predicted for their profiles and tweets.

This paper describes a novel approach to product recommendation that is based on opinionated product descriptions that are automatically mined from user-generated product reviews. We present a recommendation ranking strategy that combines similarity and sentiment to suggest products that are similar but superior to a query product according to the opinion of reviewers. We demonstrate the benefits of this approach across a variety of Amazon product domains.

In this paper we consider the application of content-based recommendation techniques to web curation services which allow users to curate and share topical collections of content (e.g. images, news, web pages etc.). Curation services like Pinterest are now a mainstay of the modern web and present a range of interesting recommendation challenges. In this paper we consider the task of recommending collections to users and evaluate a range of different content-based techniques across a variety of content signals. We present the results of a large-scale evaluation using data from the Scoop.it web page curation service

Human behavior, and in particular location behavior, is highly routine based. Modern mobile phones, through global position system (GPS) technology and cell tower and WiFi location identification, enable us to trace human location behavior at scales that were previously unattainable. The goal of this paper is to examine human location behavior, through mobile phone data, and investigate if links can be made between location behavior patterns and particular demographic and social characteristics about an individual. We hypothesize that an individual's daily predictability can be key to linking their behavior to certain characteristics, and we propose predictability and geographic areas of interest models to analyze this hypothesis. Experiments reveal that measurements, which are based on our proposed location predictability models, can correctly infer 17 different characteristics about an individual with an average accuracy of 85.5%.

User opinions and reviews are an important part of the modern web and all major e-commerce sites typically provide their users with the ability to provide and access customer reviews across their product catalog. Indeed this has become a vital part of the service provided by sites like Amazon and TripAdvisor, so much so that many of us will routinely check appropriate product reviews before making a purchase decision, regardless of whether we intend to purchase online or not. The importance of reviews has highlighted the need to help users to produce better reviews and in this paper we describe the development and evaluation of a Reviewer's Assistant for this purpose. We describe a browser plugin that is designed to work with major sites like Amazon and to provide users with suggestions as they write their reviews. These suggestions take the form of topics (e.g. product features) that a reviewer may wish to write about and the suggestions automatically adapt as the user writes their review. We describe and evaluate a number of different algorithms to identify useful topics to recommend to the user and go on to describe the results of a preliminary live-user trial.

User opinions and reviews are an important part of the modern web and all major e-commerce sites typically provide their users with the ability to provide and access customer reviews across their product catalog. The importance of reviews has driven the need to improve the review quality by providing interactive support for the reviewer and we will demonstrate the first version of an Intelligent Reviewer's Assistant for this purpose. Our browser plugin is designed to work with major sites like Amazon and to provide users with suggestions as they write their reviews. In particular, these suggestions take the form of topics (e.g. product features) that a reviewer may wish to write about and the suggestions automatically adapt as the user writes their review.

User generated content has become a valuable part of the Social Web, and high quality web content is used to influence buying decisions in a growing number of business domains. Numerous information quality frameworks have been proposed in the last years. Since 1989 at least twenty frameworks were written concerning information quality in different contexts. Most of these frameworks have been developed for databases or data warehousing in a business context. But information quality has also gained vital importance for collaboratively created content in the so-called Web 2.0. Based on literature reviews, recent publications, and Grounded Theory research on Web 2.0 sites, we propose an extended set and a new classification of information quality dimensions for the Social Web in general. Our comprehensive list of information quality dimensions can be applied to the engineering, analysis, and management of digital ecosystems and serves as a base for future research in this area.

User generated reviews are now a familiar and valuable part of most e-commerce sites since high quality reviews are known to influence purchasing decisions. In this demonstration we describe work on the Reviewer's Assistant (RA), which is a recommendation system that is designed to help users to write better quality reviews. It does this by suggesting relevant topics that they may wish to discuss based on the product they are reviewing and the content of their review so far.

Our research involves developing technology and techniques that apply the vast sea of real-time web data to interesting problems and topics. In this demo, we will present the on- going development of a novel real-time search and discovery service named Yokie (http://yok.ie, early technology description originally published in [1]). Yokie uses the large volume of hyperlink-laden messages on social networks like Twitter as the basis of its content and ranking systems. Curated sets of users (or "Search Parties") form the basis of sourcing the content from the networks, and the metadata of the containing messages form the basis of ranking and contextual retrieval of the hyperlinks. Each hyperlink is in- dexed with a compound set of terms from multiple tweets (should the given hyperlink be shared more than once). This indexing step is a novel example of collaborative tagging of resources. The application is live with more than 100 users, who have performed approximately 1000 queries. We will demonstrate the main techniques and novel ranking and re- trieval techniques and user features.

The purpose of this paper is to provide a deployment update for the HeyStaks social search system which uses recommendation techniques to add collaboration to mainstream search engines such as Google, Bing, and Yahoo. We describe our the results of initial deployments, including an assessment of the quality of HeyStaks' recommendations, and highlight some lessons learned in the marketplace

The digital camera revolution has changed the world of photography and now most people have access to, and even regularly carry, a digital camera. Often these cameras have been designed with simplicity in mind: they harness a variety of sophisticated technologies in order to automatically take care of all manner of complex settings (aperture, shutter speed, flash etc.) for point-and-shoot ease, these assistive features are usually incorporated directly into the cameras interface. However, there is little or no support for the end-user when it comes to helping them to compose or frame a scene. To this end we describe a novel recommendation process which uses a variety of intelligent and assistive interfaces to guide the user in taking relevant compositions given their current location and scene context. This application has been implemented on the Android platform and we describe its core user interaction, recommendation technologies and demonstrate its effectiveness in a number of real-world scenarios. Specifically we report on the results of a live-user trial of the technology in a real-world tourist setting.

Social services like Twitter are increasingly used to provide a conversational backdrop to real-world events in real-time. Sporting events are a good example of this and this year, millions of users tweeted their comments as they watched the World Cup matches from around the world. In this paper, we look at using these time-stamped opinions as the basis for generating video highlights for these soccer matches. We introduce the PASSEV system and describe and evaluate two basic summarization approaches.

Paper presented at the 2011 International Conference on Intelligent User Interfaces (IUI 2011), Stanford University, Palo Alto, CA, USA, February 13-16 2011

The explosive growth of online social networks in recent times has presented a powerful source of information to be utilised in personalised recommendations. Unsurprisingly there has already been a large body of work completed in the recommender system field to incorporate this social information into the recommendation process. In this paper we examine the practice of leveraging a user's social graph in order to generate recommendations. Using various neighbourhood selection strategies, we examine the user satisfaction and the level of perceived trust in the recommendations received.

Although collaborative searching is not supported by mainstream search engines, recent research has highlighted the inherently collaborative nature of many Web search tasks. In this article, we describe HeyStaks, a collaborative Web search framework that is designed to complement mainstream search engines. At search time, HeyStaks learns from the search activities of other users and leverages this information to generate recommendations based on results that others have found relevant for similar searches. The key contribution of this article is to extend the HeyStaks social search model by considering the search expertise, or reputation, of HeyStaks users and using this information to enhance the result recommendation process. In particular, we propose a reputation model for HeyStaks users that utilise the implicit collaboration events that take place between users as recommendations are made and selected. We describe a live-user trial of HeyStaks that demonstrates the relevance of its core recommendations and the ability of the reputation model to further improve recommendation quality. Our findings indicate that incorporating reputation into the recommendation process further improves the relevance of HeyStaks recommendations by up to 40%.

No abstract available.

While web search tasks are often inherently collaborative in nature, many search engines do not explicitly support collaboration during search. In this paper, we describe HeyStaks (www.heystaks.com), a system that provides a novel approach to collaborative web search. Designed to work with mainstream search engines such as Google, HeyStaks supports searchers by harnessing the experiences of others as the basis for result recommendations. Moreover, a key contribution of our work is to propose a reputation system for HeyStaks to model the value of individual searchers from a result recommendation perspective. In particular, we propose an algorithm to calculate reputation directly from user search activity and we provide encouraging results for our approach based on a preliminary analysis of user activity and reputation scores across a sample of HeyStaks users.

The mobile space is evolving at an astonishing rate with over 4.1 billion subscribers in existence. The world is also witnessing an explosion in social web services with more users seeking novel ways of interacting with friends and family. We are interested in the combination of these two exciting research spaces: the social web and the mobile web. We believe that the social mobile web is going to be a highly influential research area in the near future and given the huge growth that both these fields have experienced in recent times we feel that now is an excellent time to discuss this nascent research space. This workshop continues the successful social mobile web workshop held as part of SocialCom in 2009. The workshop explores the current state of the social mobile web and combines technical presentations, demos and position papers to drive interaction and discussion among participants.

Poster presented at the 4th ACM Conference on Recommender Systems (RecSys 2010), Barcelona, Spain, September 26-30, 2010

Recently the world of the web has become more social and more real-time. Facebook and Twitter are perhaps the exemplars of a new generation of social, real-time web services and we believe these types of service provide a fertile ground for recommender systems research. In this paper we focus on one of the key features of the social web, namely the creation of relationships between users. Like recent research, we view this as an important recommendation problem -- for a given user, UT which other users might be recommended as followers/followees -- but unlike other researchers we attempt to harness the real-time web as the basis for profiling and recommendation. To this end we evaluate a range of different profiling and recommendation strategies, based on a large dataset of Twitter users and their tweets, to demonstrate the potential for effective and efficient followee recommendation.

Mobile phones are becoming increasingly popular as a means of information access while on-the-go. Mobile users are likely to be interested in locating different types of content. However, the mobile space presents a number of key challenges, many of which go beyond issues with device characteristics such as screen-size and input capabilities. In particular, changing contexts such as location, time, activity and social interactions are likely to impact on the types of information needs that arise. In order to offer personalized, effective mobile services we need to understand mobile users in more detail. Thus we carried out a four-week diary study of mobile information needs, looking in particular at the goal/intent behind mobile information needs, the topics users are interested in and the impact of mobile contexts such as location and time on user needs.

User-generated reviews are a common and valuable source of product information, yet little attention has been paid as to how best to present them to end-users. In this paper, we describe a classification-based recommender system that is designed to recommend the most helpful reviews for a given product. We present a large-scale evaluation of our approach using TripAdvisor hotel reviews, and we show that our approach is capable of suggesting superior reviews compared to a number of alternative recommendation benchmarks.

Recommending news stories to users, based on their preferences, has long been a favourite domain for recommender systems research. In this paper, we describe a novel approach to news recommendation that harnesses real-time micro-blogging activity, from a service such as Twitter, as the basis for promoting news stories from a user's favourite RSS feeds. A preliminary evaluation is carried out on an implementation of this technique that shows promising results.

Collaborative filtering (CF) has been successfully deployed over the years to compute predictions on items based on a user's correlation with a set of peers. The black-box nature of most CF applications leave the user wondering how the system arrived at its recommendation. This note introduces PeerChooser, a collaborative recommender system with an interactive graphical explanation interface. Users are provided with a visual explanation of the CF process and opportunity to manipulate their neighborhood at varying levels of granularity to reflect aspects of their current requirements. In this manner we overcome the problem of redundant profile information in CF systems, in addition to providing an explanation interface. Our layout algorithm produces an exact, noiseless graph representation of the underlying correlations between users. PeerChooser's prediction component uses this graph directly to yield the same results as the benchmark. User's then improve on these predictions by tweaking the graph to their current requirements. We present a user-survey in which PeerChooser compares favorably against a benchmark CF algorithm.

Mobile devices and the mobile Internet represent an extremely challenging search environment. Limited screenspace, restricted text-input and interactivity, and impatient users all conspire to exacerbate the shortcomings of modern Web search. Recently researchers have proposed that typically vague search queries be augmented by context information, as a way to help search engines to retrieve more relevant information. In this paper we propose a novel interface to support multi-dimensional, context-sensitive mobile search, combining context features such as location, time, and community preferences to offer a unique search experience that is well-adapted to the needs of mobile users.

In this paper we describe the results of a four-week diary study of mobile information needs, focusing on the intent behind mobile needs and the importance on context on such needs. We identified three key intents among diary entries: informational, geographical and personal information management (PIM). Furthermore, we found many of these information needs have high temporal and location dependencies.

Recent evidence suggests that mobile search is becoming an increasingly important way for mobile users to gain access to online information, especially as off-portal content continues to grow rapidly. In this paper we study the characteristics of mobile search by analysing approximately 6 million individual search requests generated by over 260,000 individual mobile searchers over a 7-day period during 2006. We analyse the patterns of queries used by mobile searchers and focus on key characteristics such as the clickthru rates of mobile searches in order to understand, for the first time, just how well mobile search engines are responding to user queries. Moreover, we compare our results to a number of recent mobile studies and highlight some of the key differences between mobile search and traditional Web search behaviours.

Wearable technology presents a wealth of new HCI issues. In particular, this paper addresses the impact of the physical interaction between the user's body and the device's physical form on the user's mental representation of self and cognitive abilities, a blend of HCI and ergonomics that is unique to wearable computing. We explore the human sensory mechanisms that facilitate perception of worn objects and the elements of sensation that influence the comfort of worn objects, and discuss the psychological elements that may cause worn objects to be forgotten or detected, wearable or not. We discuss the implications of un-wearability on attention and cognitive capability.

We describe a novel document summarization technique that uses informational cues, such as social bookmarks or search queries, as the basis for summary construction by leveraging the snippet-generation capabilities of standard search engines. A comprehensive evaluation demonstrates how the social summarization technique can generate summaries that are of significantly higher quality that those produced by a number of leading alternatives.

We describe a social search technique that harnesses the search experiences of a community of searchers to generate result recommendations, in a collaborative fashion, to complement results returned from some underlying search engine. We describe a dynamic model of trust as a way to coordinate collaboration, and provide experimental results to show that search performance improves as the network evolves.

Delivering an effective mobile search service is challenging for many reasons. Certainly small-screen mobile handsets with limited text input capabilities do not make ideal search devices. In addition, the brevity of Mobile Internet content hampers effective indexing and limits retrieval opportunities. In this paper we focus on this indexing issue and describe an approach that leverages Web search engines as a source of content enrichment. We present an evaluation using a mobile news service that demonstrated significant improvements in search performance compared to a standard benchmark sys-tem.

Collaborative Web search (CWS) is an approach to personalizing search results, returned by an underlying search engine(s), to the preferences of a community of like-minded searchers. In this paper we propose an alternative architecture that facilitates a more flexible integration between CWS and the underlying search engine(s) and evaluate how community behaviour can be used to annotate search results with explanatory information to facilitate relevancy judgments.

The goal of this paper is to detail the integration of two "social Web" technologies - social search and social navigation - and to highlight the benefits of such integration on two levels. Firstly, both technologies harvest and harness "community wisdom" and in an integrated system each of the search and navigation components can benefit from the additional community wisdom gathered by the other when assisting users to locate relevant information. Secondly, by integrating search and browsing we facilitate the development of a unique interface that effectively blends search and browsing functionality as part of a seamless social information access service. This service allows users to effectively combine their search and browsing behaviors. In this paper we will argue that this integration provides significantly more than the simple sum of the parts.

Compound critiques allow users to simultaneously express directional preferences over several product attributes. Presenting the user with compound critiques is not a new idea. The original Find-Me Systems (e.g., Car Navigator) showed static compound critiques; they didn't change irrespective of user preferences or the product availability. Recently, a number of techniques for dynamically generating compound critiques have been proposed. While these techniques have been evaluated in isolation, to date no direct comparison of these (in terms of their interfacing characteristics and recommendation performance) has been reported. Motivated by this, our research groups have come together to carry out this comparison for the approaches we each take. The user study platform that we have developed facilitates the comparison of various critiquing based recommenders. In this paper we report the first set of results from a comprehensive real-user evaluation of two dynamic compound critique systems using this evaluation platform.

In this paper we report on our work to date concerning the development of a course recommender system for University College Dublin's on-line enrollment application. We outline the factors that influence student choices and propose solutions to address some of the key considerations that are identified. We empirically evaluate our approach using historical student enrolment data and show that promising performance is achieved with our initial design.

Conversational recommender systems are designed to help users to more efficiently navigate complex product spaces by alternatively making recommendations and inviting users' feedback. Compound critiquing techniques provide an efficient way for users to feed back their preferences (in terms of several simultaneous product attributes) when interfacing with conversational recommender systems. For example, in the laptop domain a user might wish to express a preference for a laptop that is "Cheaper, Lighter, with a Larger Screen". While recently a number of techniques for dynamically generating compound critiques have been proposed, to date there has been a lack of direct comparison of these approaches in a real-user study. In this paper we will compare two alternative approaches to the dynamic generation of compound critiques based on ideas from data mining and multi-attribute utility theory. We will demonstrate how both approaches support users to more efficiently navigate complex product spaces highlighting, in particular, the influence of product complexity and interface strategy on recommendation performance and user satisfaction.

As online information continues to grow at an exponential rate our ability to access this information effectively does not, and users are often frustrated by how difficult it is to locate the right information quickly and easily. So-called personalization technology is a potential solution to this information overload problem: by automatically learning about the needs and preferences of users, personalized information access solutions have the potential to offer users a more proactive and intelligent form of information access that is sensitive to their long-term preferences and current needs. In this paper, we document two case-studies of the use of personalization techniques to support information browsing and search. In addition, we consider the inevitable privacy issues that go hand-in-hand with profiling and personalization techniques and highlight the importance of striking the right balance between privacy and personalization when it comes to the development and deployment of practical systems.

Search engines continue to struggle to provide everyday users with a service capable of delivering focussed results that are relevant to their information needs. Moreover, traditional search engines really only provide users with a starting point for their information search. That is, upon selecting a page from a search result list, the interaction between user and search engine is effectively over and the user must continue their search alone. In this article, we argue that a comprehensive search service needs to provide the user with more help, both at the result list level and beyond, and we outline some recommendations for intelligent Web search support. We introduce the SearchGuide Web search support system and we describe how it fulfils the requirements for a search support system, providing evaluation results where applicable.

It is likely that mobile phones will soon come to rival more traditional devices as the primary platform for information access. Consequently, it is important to understand the emerging information access behavior of mobile Internet (MI) users especially in relation to their use of mobile handsets for information browsing and query-based search. In this article, we describe the results of a recent analysis of the MI habits of more than 600,000 European MI users, with a particular emphasis on the emerging interest in mobile search. We consider a range of factors including whether there are key differences between browsing and search behavior on the MI compared to the Web. We highlight how browsing continues to dominate mobile information access, but go on to show how search is becoming an increasingly popular information access alternative especially in relation to certain types of mobile handsets and information needs. Moreover, we show that sessions involving search tend to be longer and more data-rich than those that do not involve search. We also look at the type of queries used during mobile search and the way that these queries tend to be modified during the course of a mobile search session. Finally we examine the overlap among mobile search queries and the different topics mobile users are interested in.

In this paper we investigate environmental factors that can result in users having different preferences and behaviors at different times of the day. An analysis is carried out of a large sample of user data for Wireless Application Protocol (WAP) browsing to determine whether user surfing patterns vary depending on time. We examine traffic on an hourly and daily basis, and show that accesses to particular categories of pages vary relative to time. We also build Markov models, which are temporal; to predict user navigation, and illustrate those predictive models are more accurate and beneficial to mobile Internet users than traditional methods. This analysis provides insight into improving the effectiveness and efficiency of navigation prediction.

We describe and evaluate an approach to capturing and re-using search expertise within a community of like minded searchers, such as the employees of a company or organisation. Within knowledge based industries, search expertise - the ability to quickly and accurately locate information according to a specific information need - is an important corporate asset and in our approach we attempt to capture this knowledge by mining the title and snippet texts of results that have been selected by community members in response to their queries. Our assumption is that the snippet text of a result must play a role in helping users to judge the initial relevance of that result and that the snippet terms of selected results must contain especially informative terms about the goals and preferences of the searchers. In other words, results are selected because the user recognises certain combinations of terms in their snippets which are related to their information needs. Our approach seeks to build a community-based snippet index that reflects the evolving interests of a group of searchers. This index is then used to re-rank the results returned by some underlying search engine by boosting the ranking of key results that have been frequently selected for similar queries by community members in the past.

Consumers are often overwhelmed by the range of product choices available, especially online, and recommender systems have emerged as an important tool for helping users to navigate through complex product spaces based on their preferences. In this paper we describe work that concentrates on how research ideas from two complimentary research communities (recommender systems and intelligent user interfaces) can be married to improve online recommender systems. In particular, we are interested in content-based recommendation domains that rely heavily on explicit feature-level feedback from users. Oftentimes this type of feedback is difficult for users to provide and we look at how this might be addressed through product visualization techniques in this paper, focusing on the iCARE System for recommending suitable eyeglasses to individual users.

Group recommender systems introduce a whole set of new challenges for recommender systems research. The notion of generating a set of recommendations that will satisfy a group of users, with potentially competing interests, is challenging in itself. In addition to this we must consider how to record and combine the preferences of many different users as they engage in simultaneous recommendation dialogs. In this paper we introduce a group recommender system that is designed to provide assistance to a group of friends trying to plan a skiing vacation.

Systems that adapt to input from users are susceptible to attacks from those same users. Recommender systems are common targets for such attacks since there are financial, political and many other motivations for influencing the promotion or demotion of recommendable items [2].Recent research has shown that incorporating trust and reputation models into the recommendation process can have a positive impact on the accuracy and robustness of recommendations. In this paper we examine the effect of using five different trust models in the recommendation process on the robustness of collaborative filtering in an attack situation. In our analysis we also consider the quality and accuracy of recommendations. Our results caution that including trust models in recommendation can either reduce or increase prediction shift for an attacked item depending on the model-building process used, while highlighting approaches that appear to be more robust.

We describe and evaluate an approach to personalizing Web search that involves post-processing the results returned by some underlying search engine so that they re .ect the interests of a community of like-minded searchers.To do this we leverage the search experiences of the community by mining the title and snippet texts of results that have been selected by community members in response to their queries. Our approach seeks to build a community-based snippet index that re .ects the evolving interests of a group of searchers. This index is then sed to re-rank the results returned by the underlying search engine by boosting the ranking of key results that have been freq ently selected for similar q eries by community members in the past.

Many systems use past behavior, preferences and environmental factors to attempt to predict user navigation on the Internet. However we believe that many of these models have shortcomings, in that they do not take into account that users may have many different sets of preferences. Here we investigate an environmental factor, namely time, in making predictions about user navigation. We present methods for creating temporal rules that describe user navigation patterns. We also show the benefit of using these rules to predict user navigation and also show the benefits of these models over traditional methods. An analysis is carried out on a sample of usage logs for Wireless Application Protocol (WAP) browsing, and the results of this analysis verify our hypothesis.

Search engine results are usually presented in some form of text summary (e.g., document title, some snippets of the page's content, a URL, etc). Based on the information contained within these summaries users make relevance judgments about what links best suit their information needs. Current research suggests that these relevance judgments are in the service of some search strategy. In this paper, we model two different search strategies (the comparison and threshold strategies) and determine how well they fit data gathered from an experiment on user search within a simulated Google environment.

Technological developments in content-based analysis of digital video information are undergoing much progress, with ideas for fully automatic systems now being proposed and demonstrated. Yet because we do not yet have robust operational video retrieval systems that can be deployed and used, the usual HCI practise of conducting a usage study and an informed iterative system design is thus not possible. Físchlár-News is one of the first automatic, content-based broadcast news analysis and archival systems that process broadcast news video so that users can search, browse, and play it in an easy-to-use manner with a conventional web browser. The system incorporates a number of state-of-the-art research components, some of which are not yet considered mature technology, yet it has been built to be robust enough to be deployed to users who are interested in access to daily news throughout a university campus. In this article we report and discuss a user-evaluation study conducted with 16 users, each of whom utilized the system freely for a one month period. Results from a detailed qualitative analysis are presented, looking at collected questionnaires, incident diaries, and interaction-log data. The findings suggest that our users employed the system in conjunction with their other news update methods, such as watching TV news at home and browsing online news websites at their workplace, their major concerns being up-to-dateness and coverage of the news content. They tried to accommodate the system to fit their established web browsing habits, and they found local news content and the ability to play self-contained news stories on their desktop as major values of the system. Our study also resulted in a detailed wishlist of new features which will help in the further development of both our and others' systems.

Conversational recommender systems are commonly used to help users to navigate through complex product-spaces by alternatively making product suggestions and soliciting user feedback in order to guide subsequent suggestions. Recently, there has been a surge of interest in developing effective interfaces that support user interaction in domains of limited user expertise. Critiquing has proven to be a popular and successful user feedback mechanism in this regard, but is typically limited to the modification of single features. We review a novel approach to critiquing, dynamic critiquing, that allows users to modify multiple features simultaneously by choosing from a range of so-called compound critiques that are automatically proposed based on their current position within the product-space. In addition, we introduce the results of an important new live-user study that evaluates the practical benefits of dynamic critiquing.

Recommender systems have proven to be an important response to the information overload problem, by providing users with more proactive and personalized information services. And collaborative filtering techniques have proven to be an vital component of many such recommender systems as they facilitate the generation of high-quality recom-mendations by leveraging the preferences of communities of similar users. In this paper we suggest that the traditional emphasis on user similarity may be overstated. We argue that additional factors have an important role to play in guiding recommendation. Specifically we propose that the trustworthiness of users must be an important consideration. We present two computational models of trust and show how they can be readily incorporated into standard collaborative filtering frameworks in a variety of ways. We also show how these trust models can lead to improved predictive accuracy during recommendation.

In 2000 the entire World-Wide Web consisted of just 21 terabytes of information; now it grows by 3 times this every single day. This phenomenal growth frames the information overload problem that is threatening to stall the information revolution going forward. In short, users are finding it increasingly difficult to locate the right information at the right time in the right way. Search engine technologies are struggling to cope with the sheer quantity of information that is available, a problem that is greatly exacerbated by the apparent inability of Web users to formulate effective search queries that accurately reflect their current information needs. This talk will focus on how so-called personalization techniques are being used in response to the information overload problem.Personalization research brings together ideas from artificial intelligence, user profiling, information retrieval and user-interface design to provide users with more proactive and intelligent information services that are capable of predicting the needs of individuals and adapting to their implicit preferences. We will describe how personalization techniques have been successfully applied to the two dominant modes of information access, browsing and search, with reference to deployed applications in the mobile Internet and Web search arenas. Particular attention will be paid to the natural tension that exists between the potential value of personalization, on the one hand, and the perceived privacy risk associated with profiling, on the other. We will highlight certain recent approaches to personalization that appear to achieve a useful balance between personalization and privacy and argue that realizing this personalization-privacy sweet spot may be the key to the large-scale success of personalization technologies in the future.

The I-SPY meta-search engine uses a technique called collaborative Web search to leverage the past search behaviour (queries and selections) of a community of users in order to promote search results that are relevant to the community. In this paper we describe recent studies to clarify the benefits of this approach in situations when the behaviour of users cannot be relied upon in terms of their ability to consistently select relevant results during search sessions.

There are many systems that attempt to predict user navigation on the Internet through the use of past behavior, preferences and environmental factors. We believe that many of these models have shortcomings, in that they do not take into account that users may have many different sets of preferences, specifically, we investigate time as an environmental factor in making predictions about user navigation. We present a method for segmenting log files in order to learn time dependent models to predict user navigation patterns and show the benefits of these models over traditional methods. An analysis is carried out on a sample of usage logs for wireless application protocol (WAP) browsing, and the results of this analysis verify our hypothesis.

We present an innovative approach to personalized Web search that exploits the search behaviour of a community of users to re-rank future result-lists according to the implied preferences of this group. Evaluation results demonstrate the precision and recall benefits of our collaborative search technique and we show how personalization can be achieved without the need for individual user profiling.

Recommender systems bring together ideas from information retrieval and filtering, user profiling, adaptive interfaces and machine learning in an attempt to offer users more personalized and responsive search systems. Conversational recommenders guide a user through a sequence of iterations, suggesting specific items, and using feedback from users to refine their suggestions in subsequent iterations. Different recommender systems look for different types of feedback from users. In this paper we examine the role of critiquing, a form of feedback in which the user indicates a preference over a particular feature of a recommended item. For example, when shopping for a PC a user might indicate that they like the current suggestion but they are looking for something "cheaper"; "cheaper" is a critique over the price feature of the PC case. Sometimes it is useful to critique multiple features simultaneously (compound critiques). In this paper we describe how a recommender can automatically discover useful compound critiques during the recommendation session and how these critiques can be used to improve recommendation efficiency.

Recommender systems research combines techniques from user modeling and information filtering in order to build search systems that are better able to respond to the preferences of individual users during the search for a particular item or product. Collaborative recommenders leverage the preferences of communities of similar users in order to guide the search for relevant items. The success of collaborative recommendation has always been restrained by the so-called sparsity problem, in which a lack of available user similarity knowledge ultimately limits the formation of high-quality user communities and has a subsequent impact on recommender accuracy. This article presents an approach to addressing the sparsity problem by describing and evaluating how implicit similarity knowledge can be discovered and exploited using data-mining techniques and an approach to recommendation that is inspired by case-based reasoning research.

Case‐base maintenance is an important emerging issue for case‐base reasoners as they scale up to handle real‐world problems in unstable environments. Over time, the contents of a case base may become out of date or inconsistent with the target problem space, and maintenance strategies must be devised to help recognize and repair these problems by deleting, adding, or modifying cases, for example. In this article we describe a maintenance framework called collaborative maintenance (CM), which has been designed to facilitate, monitor, and control the incremental update of live, dynamic case bases. Our approach is novel in that it automatically supports a distributed, interactive maintenance process—users are permitted to recommend case updates, and the collaborative maintenance process ensures that these recommendations are properly reviewed and actioned.

Case‐based reasoning (CBR) systems solve problems by retrieving and adapting the solutions to similar problems that have been stored previously as a case base of individual problem solving episodes or cases. The maintenance problem refers to the problem of how to optimize the performance of a CBR system during its operational lifetime. It can have a significant impact on all the knowledge sources associated with a system (the case base, the similarity knowledge, the adaptation knowledge, etc.), and over time, any one, or more, of these knowledge sources may need to be adapted to better fit the current problem‐solving environment. For example, many maintenance solutions focus on the maintenance of case knowledge by adding, deleting, or editing cases. This has lead to a renewed interest in the issue of case competence, since many maintenance solutions must ensure that system competence is not adversely affected by the maintenance process. In fact, we argue that ultimately any generic maintenance solution must explicitly incorporate competence factors into its maintenance policies. For this reason, in our work we have focused on developing explanatory and predictive models of case competence that can provide a sound foundation for future maintenance solutions. In this article we provide a comprehensive survey of this research, and we show how these models have been used to develop a number of innovative and successful maintenance solutions to a variety of different maintenance problems.

Case based reasoning (CBR) is an artificial intelligence technique that emphasises the role of past experience during future problem solving. New problems are solved by retrieving and adapting the solutions to similar problems, solutions that have been stored and indexed for future reuse as cases in a case-base. The power of CBR is severely curtailed if problem solving is limited to the retrieval and adaptation of a single case, so most CBR systems dealing with complex problem solving tasks have to use multiple cases. The paper describes and evaluates the technique of hierarchical case based reasoning, which allows complex problems to be solved by reusing multiple cases at various levels of abstraction. The technique is described in the context of Deja Vu, a CBR system aimed at automating plant-control software design.