Re-finding is the process of searching for information that a user has previously encountered and is a common activity carried out with information retrieval systems. In this work, we investigate re-finding in the context of vertical search, differentiating and modeling user re-finding behavior within different media and topic domains, including images, news, reference material, and movies. We distinguish the re-finding behavior in vertical domains from re-finding in a general search context and engineer features that are effective in differentiating re-finding across the domains. The features are then used to build machine-learned models, achieving an accuracy of re-finding detection in verticals of 85.7% on average. Our results demonstrate that detecting re-finding in specific verticals is more difficult than examining re-finding for general search tasks. We then investigate the effectiveness of differentiating re-finding behavior in two restricted contexts: We consider the case where the history of a searcher’s interactions with the search system is not available. In this scenario, our features and models achieve an average accuracy of 77.5% across the domains. We then examine the detection of re-finding during the early part of a search session. Both of these restrictions represent potential real-world search scenarios, where a system is attempting to learn about a user but may have limited information available. Finally, we investigate in which types of domains re-finding is most difficult. Here, it would appear that re-finding images is particularly challenging for users. This research has implications for search engine design, in terms of adapting search results by predicting the type of user tasks and potentially enabling the presentation of vertical-specific results when re-finding is identified. To the best of our knowledge, this is the first work to investigate the issue of vertical re-finding.

We present a study of which baseline to use when testing a new retrieval technique. In contrast to past work, we show that measuring a statistically significant improvement over a weak baseline is not a good predictor of whether a similar improvement will be measured on a strong baseline. Sometimes strong baselines are made worse when a new technique is applied. We investigate whether conducting comparisons against a range of weaker baselines can increase confidence that an observed effect will also show improvements on a stronger baseline. Our results indicate that this is not the case -- at best, testing against a range of baselines means that an experimenter can be more confident that the new technique is unlikely to significantly harm a strong baseline. Examining recent past work, we present evidence that the information retrieval (IR) community continues to test against weak baselines. This is unfortunate as, in light of our experiments, we conclude that the only way to be confident that a new technique is a contribution is to compare it against nothing less than the state of the art.

The proliferation of online video content has triggered numerous works on its evolution and popularity, as well as on the effect of social sharing on content propagation. In this paper, we focus on the observable dependencies between the virality of video content on a micro-blogging social network (in this case, Twitter) and the popularity of such content on a video distribution service (YouTube). To this end, we collected and analysed a corpus of Twitter posts containing links to YouTube clips and the corresponding video meta-data from YouTube. Our analysis highlights the unique properties of content that is both popular and viral, which allows such content to attract high number of views on YouTube and achieve fast propagation on Twitter. With this in mind, we proceed to the predictions of popular-and-viral clips and propose a framework that can, with high degree of accuracy and low amount of training data, predict videos that are likely to be popular, viral, and both. The key contribution of our work is the focus on cross-system dynamics between YouTube and Twitter. We conjecture and validate that cross-system prediction of both popularity and virality of videos is feasible, and can be performed with a reasonably high degree of accuracy. One of our key findings is that YouTube features capturing user engagement, have strong virality prediction capabilities. This findings allows to solely rely on data extracted from a video sharing service to predict popularity and virality aspects of videos.

Many types of recommender systems rely on a rich ensemble of user, item, and context features when generating recommendations for users. The features can be either manually engineered or automatically extracted from the available data, such that feature engineering becomes an important step in the recommendation process. In this work, we propose to leverage graph based representation of the data in order to generate and automatically populate features. We represent the standard user-item rating matrix and some domain metadata, as graph vertices and edges. Then, we apply a suite of graph theory and network analysis metrics to the graph based data representation, to populate features that augment the original user-item ratings data. The augmented data is fed into a classifier that predicts unknown user ratings, which are used for the generation of recommendations. We evaluate the proposed methodology using the recently released Yelp business ratings dataset. Our results indicate that the automatically populated graph features allow for more accurate and robust predictions, with respect to both the variability and sparsity of ratings.

We investigate the application of a light-weight approach to result list clustering for the purposes of diversifying search results. We introduce a novel post-retrieval approach, which is independent of external information or even the full-text content of retrieved documents; only the retrieval score of a document is used. Our experiments show that this novel approach is beneficial to effectiveness, albeit only on certain baseline systems. The fact that the method works indicates that the retrieval score is potentially exploitable in diversity.

Search personalization and diversification are often seen as opposing alternatives to cope with query uncertainty, where, given an ambiguous query, it is either preferable to adapt the search result to a specific aspect that may interest the user (personalization) or to regard multiple aspects in order to maximize the probability that some query aspect is relevant to the user (diversification). In this work, we question this antagonistic view, and hypothesize that these two directions may in fact be effectively combined and enhance each other. We research the introduction of the user as an explicit random variable in state of the art diversification methods, thus developing a generalized framework for personalized diversification. In order to evaluate our hypothesis, we conduct an evaluation with real users using crowdsourcing services. The obtained results suggest that the combination of personalization and diversification achieves competitive performance, improving the base-line, plain personalization, and plain diversification approaches in terms of both diversity and accuracy measures.

The intent-oriented search diversification methods developed in the field so far tend to build on generative views of the retrieval system to be diversified. Core algorithm components in particular redundancy assessment are expressed in terms of the probability to observe documents, rather than the probability that the documents be relevant. This has been sometimes described as a view considering the selection of a single document in the underlying task model. In this paper we propose an alternative formulation of aspect-based diversification algorithms which explicitly includes a formal relevance model. We develop means for the effective computation of the new formulation, and we test the resulting algorithm empirically. We report experiments on search and recommendation tasks showing competitive or better performance than the original diversification algorithms. The relevance-based formulation has further interesting properties, such as unifying two well-known state of the art algorithms into a single version. The relevance-based approach opens alternative possibilities for further formal connections and developments as natural extensions of the framework. We illustrate this by modeling tolerance to redundancy as an explicit configurable parameter, which can be set to better suit the characteristics of the IR task, or the evaluation metrics, as we illustrate empirically.

Diversification and personalization methods are common ap-proaches to deal with the one-size-fits-all paradigm of Web search engines. We performed a user study with 190 subjects where we analyzed the effects of diversification and personalization methods in a Web search engine. The obtained results suggest that our proposed combination of diversification and personalization factors may be a way to overcome the notion of intrusiveness in personalized approaches.

Diversity as a relevant dimension of retrieval quality is receiving increasing attention in the Information Retrieval and Recommender Systems (RS) fields. The problem has nonetheless been approached under different views and formulations in IR and RS respectively, giving rise to different models, methodologies, and metrics, with little convergence between both fields. In this poster we explore the adaptation of diversity metrics, techniques, and principles from ad-hoc IR to the recommendation task, by introducing the notion of user profile aspect as an analogue of query intent. As a particular approach, user aspects are automatically extracted from latent item features. Empirical results support the proposed approach and provide further insights.

We present a model for exploiting community-based usage information for video retrieval, where implicit usage information from past users is exploited in order to provide enhanced assistance in video retrieval tasks, and alleviate the effects of the semantic gap problem. We propose a graph-based model for all types of implicit and explicit feedback, in which the relevant usage information is represented. Our model is designed to capture the complex interactions of a user with an interactive video retrieval system, including the representation of sequences of user-system interaction during a search session. Building upon this model, four recommendation strategies are defined and evaluated. An evaluation strategy is proposed based on simulated user actions, which enables the evaluation of our recommendation strategies over a usage information pool obtained from 24 users performing four different TRECVid tasks. Furthermore, the proposed simulation approach is used to simulate usage information pools with different characteristics, with which the recommendation approaches are further evaluated on a larger set of tasks, and their performance is studied with respect to the scalability and quality of the available implicit information.

In this paper we examine the use of multi faceted recommendations to aid users while carrying out exploratory video retrieval tasks. These recommendations are integrated into ViGOR (Video Grouping, Organisation and Retrieval), a system which employs grouping techniques to facilitate video retrieval tasks. Two types of recommendations based on past usage history are utilised, the first attempts to couple the multi-faceted nature of explorative video retrieval tasks with the current user interests in order to provide global recommendations, while the second exploits the organisational features of ViGOR in order to provide recommendations based on a specific aspect of the user's task.

In an effort to address and overcome some of the open issues that hinder effective access and interaction of multimedia content, this workshop will bring together individuals from a number of research communities, including but not limited to Multimedia Distribution and Access, Social Network Analysis, Multimedia Content Analysis, and User Modelling Adaptation and Personalization. It is our belief that a synergetic approach involving these areas of work can exceed their individual potentials, leading to improved access, understanding, and retrieval of multimedia content. The main objective of this workshop is to provide a forum to disseminate work that explicitly exploits the synergy between multimedia content analysis, personalisation, and next generation networking and community aspects of social networks. We believe that this integration could result on robust, personalized multimedia services, providing users with an improved multimedia experience.

We present and evaluate various content-based recommendation models that make use of user and item profiles defined in terms of weighted lists of social tags. The studied approaches are adaptations of the Vector Space and Okapi BM25 information retrieval models. We empirically compare the recommenders using two datasets obtained from Delicious and Last.fm social systems, in order to analyse the performance of the approaches in scenarios with different domains and tagging behaviours.

This is the author's version of the work. It is posted here for your personal use. Not for redistribution. The definitive Version of Record was published in Proceedings of the 33rd international ACM SIGIR conference on Research and development in information retrieval, http://dx.doi.org/10.1145/1835449.1835636

In this paper we present an innovative approach for aiding users in the difficult task of video search. We use community based feedback mined from the interactions of previous users of our video search system to aid users in their search tasks. This feedback is the basis for providing recommendations to users of our video retrieval system. The ultimate goal of this system is to improve the quality of the results that users find, and in doing so, help users to explore a large and difficult information space and help them consider search options that they may not have considered otherwise. In particular we wish to make the difficult task of search for video much easier for users. The results of a user evaluation indicate that we achieved our goals, the performance of the users in retrieving relevant videos improved, and users were able to explore the collection to a greater extent.

In this paper we present a technique for ranking the most important types or categories for a given query. Rather than trying to find the category of the query, known as query categorization, our approach seeks to find the most important types related to the query results. Not necessarily the query category falls into this ranking of types and therefore our approach can be complementary.

Personalized content retrieval aims at improving the retrieval process by taking into account the particular interests of individual users. However, not all user preferences are relevant in all situations. It is well known that human preferences are complex, multiple, heterogeneous, changing, even contradictory, and should be understood in context with the user goals and tasks at hand. In this paper, we propose a method to build a dynamic representation of the semantic context of ongoing retrieval tasks, which is used to activate different subsets of user interests at runtime, in a way that out-of-context preferences are discarded. Our approach is based on an ontology-driven representation of the domain of discourse, providing enriched descriptions of the semantics involved in retrieval actions and preferences, and enabling the definition of effective means to relate preferences and context

Semantic search has been one of the motivations of the semantic Web since it was envisioned. We propose a model for the exploitation of ontology-based knowledge bases to improve search over large document repositories. In our view of information retrieval on the semantic Web, a search engine returns documents rather than, or in addition to, exact values in response to user queries. For this purpose, our approach includes an ontology-based scheme for the semiautomatic annotation of documents and a retrieval system. The retrieval model is based on an adaptation of the classic vector-space model, including an annotation weighting algorithm, and a ranking algorithm. Semantic search is combined with conventional keyword-based retrieval to achieve tolerance to knowledge base incompleteness. Experiments are shown where our approach is tested on corpora of significant scale, showing clear improvements with respect to keyword-based search

We discuss the use of a reliable user requirements methodology for gathering essential data relating to user needs in advanced, personalised multimedia content applications. We revise the implications of these requirements in the development of advanced personalised searching and browsing tools aimed at assisting the end-consumer by complementing explicit user requests with implicit user preferences, to better meet individual user needs. We examine the important technical challenges such as representing conceptual-level user interests, and coping with the subtleties of user preferences, such as variability and heterogeneity, which we see as critical for the success of personalisation techniques. We consider the fact that personalisation is not always appropriate, and it is sometimes preferable to disable it to avoid obtrusiveness.

Rank aggregation is a pervading operation in IR technology. We hypothesize that the performance of score-based aggregation may be affected by artificial, usually meaningless deviations consis-tently occurring in the input score distributions, which distort the combined result when the individual biases differ from each other. We propose a score-based rank aggregation model where the source scores are normalized to a common distribution before being combined. Early experiments on available data from several TREC collections are shown to support our proposal.