Personalized micro video recommendation aims to recommend the micro videos tailored to user preference based on the user’s interaction history with the micro videos, which has drawn increasing attention from both the academic and industrial communities. Existing solutions primarily concentrate on video-level interactions between users and micro videos to model their preferences, and cannot distinguish the finer-grained users’ interactions with various modalities. Ignoring modality-level interactions prevents the full understanding of the user’s true and subtle preferences on micro videos. To this end, in this article, we propose a Contrastive Multimodal Interaction Graph Learning ( MVideoRec ) model to automatically and explicitly learn the modality-level interaction between users and micro videos for recommendations. Specifically, we designed a graph structure learning module with a sparsification strategy to infer modality-level interaction graph, which will be dynamically and iteratively updated based on the node representations obtained from the node representation learning module. Furthermore, to address the lack of ground truth labels, we propose to generate teacher view from video-level interaction graph and student view from modality-level interaction graph, as well as construct intra-modality and inter-modality contrastive pairwise instances to provide self-supervised signals. Extensive experiments on three real-world micro video datasets validate the effectiveness of MVideoRec.

Serendipity means unexpected discoveries that are valuable, with positive outcomes ranging from personal benefits to scientific breakthroughs. This study proposes a cross-domain recommendation model, called SerenCDR , to model serendipity. SerenCDR leverages the knowledge beyond one domain as well as mitigates the inherent data sparsity problem in serendipity recommendations. The novelty of SerenCDR lies in the fact that it is the first deep learning based cross-domain model for a serendipity task. More importantly, it does not rely on any overlapping users or overlapping items across different domains, which especially fits for the task of recommending serendipity, because serendipity in a single domain tends to be sparse; finding overlapping users or overlapping items in other domains is nearly impossible. To train and test SerenCDR , we have collected a two-domain ground truth dataset on serendipity, called SerenCDRLens . In addition, since we found that serendipity is sparse in SerenCDRLens , we designed an auxiliary loss function to supplement the main loss function to enhance serendipity learning. Through a series of experiments, we have harvested positive performance in recommending serendipity, empowering users with increased chances of bumping into unexpected but valuable discoveries.

Today’s recommender systems are criticized for recommending items that are too obvious to arouse users’ interests. Therefore, the research community has advocated some “beyond accuracy” evaluation metrics such as novelty, diversity, and serendipity with the hope of promoting information discovery and sustaining users’ interests over a long period of time. While bringing in new perspectives, most of these evaluation metrics have not considered individual users’ differences in their capacity to experience those “beyond accuracy” items. Open-minded users may embrace a wider range of recommendations than conservative users. In this article, we proposed to use curiosity traits to capture such individual users’ differences. We developed a model to approximate an individual’s curiosity distribution over different stimulus levels. We used an item’s surprise level to estimate the stimulus level and whether such a level is in the range of the user’s appetite for stimulus, called Comfort Zone . We then proposed a recommender system framework that considers both user preference and their Comfort Zone where the curiosity is maximally aroused. Our framework differs from a typical recommender system in that it leverages human’s Comfort Zone for stimuli to promote engagement with the system. A series of evaluation experiments have been conducted to show that our framework is able to rank higher the items with not only high ratings but also high curiosity stimulation. The recommendation list generated by our algorithm has a higher potential of inspiring user curiosity compared to the state-of-the-art deep learning approaches. The personalization factor for assessing the surprise stimulus levels further helps the recommender model achieve smaller (better) inter-user similarity.

Cross-domain recommender systems could potentially improve the recommendation performance by means of transferring abundant knowledge from the auxiliary domain to the target domain. They could help address some key challenges in recommender systems, such as data sparsity and cold start. However, most existing cross-domain recommendation approaches represent the user preferences based on a single kind of user’s feature or behavior and fail to explore the hidden interaction effects of different kinds of features or behaviors. In this article, we propose the S equential and G raphical Cross -Domain Recommendations with a Multi-View Hierarchical Transfer Gate (SGCross) to transfer user representations from multiple perspectives. The SGCross model constructs a user profile by learning the personal preference from a personal view, the dynamic preference from a temporal view, as well as the collaborative preference from a collaborative view. Specifically, a Multi-view Hierarchical Gate (MHG) is designed to transfer the informative representations of user knowledge on different views from the auxiliary domain separately, aiming to enhance the user representations. Furthermore, a two-stage attentive fusion module is designed to integrate transferred information at two levels: the domain level and the view level. Extensive experiments on the Amazon dataset and the Douban dataset have demonstrated that SGCross effectively improves the accuracy of cross-domain recommendations and outperforms the state-of-the-art baseline models.

The recent California Consumer Privacy Act (CCPA) requires that personal data shall be limited to what is necessary for business purposes. Business services shall “implement technical safeguards that prohibit re-identification of the consumer to whom the information may pertain”. For recommender systems, we believe the legal concepts of limitation and technical safeguard are not specific enough to operationalize in practice. This study makes efforts to map the legislative challenges to practice of reducing personal data. More importantly, we borrowed the notion of uncertainty from the machine learning community, and added it as another aspect of recommendation utility, in addition to recommendation accuracy, to guide the data reduction process. The benefit of using uncertainty is that we have more comprehensive consideration while reducing the personal data. In addition, two major types of uncertainty in machine learning models: aleatoric uncertainty and epistemic uncertainty, helped us formulate two groups of data reduction strategies: within-user and between-user. We conducted a series of analyses regarding uncertainty change and accuracy loss caused by different data reduction strategies. We found that at the aggregate level, data reduction is feasible with certain data reduction strategies. At the individual level, the recommendation utility (both uncertainty and accuracy) loss incurred by data reduction disparately impacts different users — a finding which has implications for fairness and transparency of AI models. Our results reveal the difficulty and intricacy of the data reduction problem in the context of recommender systems.

Serendipity is a notion that means an unexpected but valuable discovery. Due to its elusive and subjective nature, serendipity is difficult to study even with today's advances in machine learning and deep learning techniques. Both ground truth data collecting and model developing are the open research questions. This paper addresses both the data and the model challenges for identifying serendipity in recommender systems. For the ground truth data collecting, it proposes a new and scalable approach by using both user generated reviews and a crowd sourcing method. The result is a large-scale ground truth data on serendipity. For model developing, it designed a self-enhanced module to learn the fine-grained facets of serendipity in order to mitigate the inherent data sparsity problem in any serendipity ground truth dataset. The self-enhanced module is general enough to be applied with many base deep learning models for serendipity. A series of experiments have been conducted. As the result, a base deep learning model trained on our collected ground truth data, as well as with the help of the self-enhanced module, outperforms the state-of-the-art baseline models in predicting serendipity.

Automatically finding contradictions from text is a fundamental yet under-studied problem in natural language understanding and information retrieval. Recently, topology, a branch of mathematics concerned with the properties of geometric shapes, has been shown useful to understand semantics of text. This study presents a topological approach to enhancing deep learning models in detecting contradictions in text. In addition, in order to better understand contradictions, we propose a classification with six types of contradictions. Following that, the topologically enhanced models are evaluated with different contradictions types, as well as different text genres. Overall we have demonstrated the usefulness of topological features in finding contradictions, especially the more latent and more complex contradictions in text.

As the popularity of online travel platforms increases, users tend to make ad-hoc decisions on places to visit rather than preparing the detailed tour plans in advance. Under the situation of timeliness and uncertainty of users’ demand, how to integrate real-time context into dynamic and personalized recommendations have become a key issue in travel recommender system. In this article, by integrating the users’ historical preferences and real-time context, a location-aware recommender system called TRACE ( T ravel R einforcement Recommendations Based on Location- A ware C ontext E xtraction) is proposed. It captures users’ features based on location-aware context learning model, and makes dynamic recommendations based on reinforcement learning. Specifically, this research: (1) designs a travel reinforcing recommender system based on an Actor-Critic framework, which can dynamically track the user preference shifts and optimize the recommender system performance; (2) proposes a location-aware context learning model, which aims at extracting user context from real-time location and then calculating the impacts of nearby attractions on users’ preferences; and (3) conducts both offline and online experiments. Our proposed model achieves the best performance in both of the two experiments, which demonstrates that tracking the users’ preference shifts based on real-time location is valuable for improving the recommendation results.

The growing amount of online information today has increased opportunity to discover interesting and useful information. Various recommender systems have been designed to help people discover such information. No matter how accurately the recommender algorithms perform, users' engagement with recommended results has been complained being less than ideal. In this study, we touched on two human-centered objectives for recommender systems: user satisfaction and curiosity, both of which are believed to play roles in maintaining user engagement and sustain such engagement in the long run. Specifically, we leveraged the concept of surprise and used an existing computational model of surprise to identify relevantly surprising health articles aiming at improving user satisfaction and inspiring their curiosity. We designed a user study to first test the validity of the surprise model in a health news recommender system, called LuckyFind. Then user satisfaction and curiosity were evaluated. We find that the computational surprise model helped identify surprising recommendations at little cost of user satisfaction. Users gave higher ratings on interestingness than usefulness for those surprising recommendations. Curiosity was inspired more for those individuals who have a larger capacity to experience curiosity. Over half of the users have changed their preferences after using LuckyFind, either discovering new areas, reinforcing their existing interests, or stopping following those they did not want anymore. The insights of the research will make researchers and practitioners rethink the objectives of today's recommender systems as being more human-centered beyond algorithmic accuracy.

Recommender systems help users find items that are relevant or interesting. These recommendations are based on the users profile, past behavior, and items similarity. Various recommender system algorithms presented in literature have achieved high accuracy in predicting relevant recommendations similar to the users profile. Even though with high accuracy, these results tend to be over-specified with obvious recommendations that are too similar to what the user already knows, failing to arouse users long-term interest. This survey paper presents a literature review on serendipity as one of the beyond accuracy measures to overcome the over-specialization problem. The survey starts with an introduction of the concept of serendipity, followed by several definitions of serendipity found in the literature. Then the main components of serendipity are presented novelty, surprise, and value. After that, the survey discusses several well-known serendipity recommender systems. While most surveys in serendipity categorize frameworks based on types of recommender systems, this survey categorizes serendipitous frameworks based on the conceptual view of serendipity. Finally, a discussion with various evaluation strategies on serendipity will be presented.

The concept of surprise has special significance in information retrieval in attracting user attention and arousing curiosity. In this paper, we introduced two computational measures of calculating the amount of surprise contained in a piece of text, and validated with the perceived surprise by users with different background knowledge expertise. We utilized a crowdsourcing approach and a lab-based user study to reach a large amount of users. The implication could be used to propose or refine future computational approaches to better predict human feeling of surprise triggered by reading a body of text.

Faceted search has become a common feature on most search interfaces in e-commerce websites, digital libraries, government’s open information portals, and so on. Beyond the existing studies on developing algorithms for faceted search and empirical studies on facet usage, this study investigated user real-time interactions with facets over the course of a search from both data science and human factor perspectives. It adopted a Random Forest (RF) model to successfully predict facet use using search dynamic variables. In addition, the RF model provided a ranking of variables by their predictive power, which suggests that the search process follows rhythmic flow of a sequence within which facet addition is mostly influenced by its immediately preceding action. In the follow-up user study, we found that participants used facets at critical points from the beginning to end of search sessions. Participants used facets for distinctive reasons at different stages. They also used facets implicitly without applying the facets to their search. Most participants liked the faceted search, although a few participants were concerned about the choice overload introduced by facets. The results of this research can be used to understand information seekers and propose or refine a set of practical design guidelines for faceted search.

The rapid growth of Web 2.0 and wide popularity of social media have brought the challenge of digesting and understanding large amounts of user-generated text. Automatically finding contradictions from user opinionated text is a potential solution to help sense-making and decision-making process from those user opinions. However, the problem of contradiction detection is understudied in social media analysis field. This study presents a computational approach to detecting contradictions in user opinionated text. Specifically, a typology of contradictions was proposed, and then the state-of-art deep learning models were adopted and enhanced by three methods of incorporating sentiment analysis. The enhanced models were evaluated with Amazon's customer reviews. The best model was selected and applied to a collection of tweets from Twitter to demonstrate its usefulness in understanding contradiction semantically and quantitatively in a large amount of user opinionated text.

Our natural tendency to be curious is increasingly important now that we are exposed to vast amounts of information. We often cope with this overload by focusing on the familiar: information that matches our expectations. In this paper we present a framework for interactive serendipitous information discovery based on a computational model of surprise. This framework delivers information that users were not actively looking for, but which will be valuable to their unexpressed needs. We hypothesize that users will be surprised when presented with information that violates the expectations predicted by our model of them. This surprise model is balanced by a value component which ensures that the information is relevant to the user. Within this framework we have implemented two surprise models, one based on association mining and the other on topic modeling approaches. We evaluate these two models with thirty users in the context of online health news recommendation. Positive user feedback was obtained for both of the computational models of surprise compared to a baseline random method. This research contributes to the understanding of serendipity and how to "engineer" serendipity that is favored by users.

With the rapid growth of the cyber attacks, cyber threat intelligence (CTI) sharing becomes essential for providing advance threat notice and enabling timely response to cyber attacks. Our goal in this paper is to develop an approach to extract low-level cyber threat actions from publicly available CTI sources in an automated manner to enable timely defense decision making. Specifically, we innovatively and successfully used the metrics of entropy and mutual information from Information Theory to analyze the text in the cybersecurity domain. Combined with some basic NLP techniques, our framework, called ActionMiner has achieved higher precision and recall than the state-of-the-art Stanford typed dependency parser, which usually works well in general English but not cybersecurity texts.

The concept of surprise is central to human learning and development. However, compared to accuracy, surprise has received little attention in the IR community, yet it is an essential component of the information seeking process. This workshop brings together researchers and practitioners of IR to discuss the topic of computational surprise, to set a research agenda, and to examine how to build datasets for research into this fascinating topic. The themes in this workshop include discussion of what can be learned from some well-known surprise models in other fields, such as Bayesian surprise; how to evaluate surprise based on user experience; and how computational surprise is related to the newly emerging areas, such as fake news detection, computational contradiction, clickbait detection, etc.

With the rapid growth of the cyber attacks, sharing of cyber threat intelligence (CTI) becomes essential to identify and respond to cyber attack in timely and cost-effective manner. However, with the lack of standard languages and automated analytics of cyber threat information, analyzing complex and unstructured text of CTI reports is extremely time- and labor-consuming. Without addressing this challenge, CTI sharing will be highly impractical, and attack uncertainty and time-to-defend will continue to increase.

Modern enterprises collect, process, and analyze security data from various system and network logs. Previous studies show that, handling large security datasets and detecting anomalies from those are key challenges faced by most of todays' enterprises. Unfortunately most security professionals are inexperienced at performing data analysis. In this paper, we study published works analyzing one publicly accessible log dataset (Sandia Dataset) published by Los Alamos National Laboratory. We evaluate their data analysis methodology as well as results and found significant flaws in most analysis methodologies.

Since the adoption of faceted search in a small number of academic libraries in 2006, faceted search interfaces have gained popularity in academic and public libraries. This article clarifies whether faceted search improves the interactions between searchers and library catalogs and sheds light on ways that facets are used during a library search. To study searchers' behaviors in natural situations, we collected from the servers a data set with more than 1.5 million useful search logs. Logs were parsed, statistically analyzed, and manually studied using visualization tools to gain a general understanding of how facets are used in the search process. A user experiment with 24 subjects was conducted to further understand contextual information, such as the searchers' motivations and perceptions. The results indicate that most searchers were able to understand the concept of facets naturally and easily. The faceted search was not able to shorten the search time but was able to improve the search accuracy. Facets were used more for open‐ended tasks and difficult tasks that require more effort to learn, investigate, and explore. Overall, the results weaved a detailed “story” about the ways that people use facets and the ways that facets help people use library catalogs.

The goal of this study was to investigate and compare user search activities of 2 discovery tools at an academic library. The implementation of a new discovery tool (Primo by Ex Libris) to replace an existing system (VuFind) provided a unique opportunity to collect transaction logs of both systems and examine user search behavior in an empirical test. Results from a transaction log analysis and a user study of this study have contributed to the understanding of users’ search behavior and their preferences and perceptions of the two systems. We find both commonalities and differences between VuFind and Primo for users’ interactions. The combination use of the transaction log analysis and user study could be applied to other similar search systems assessments.

Abstract In an effort to understand how academic scientists seek information relevant to their research in today's environment of ubiquitous electronic access, a correlation framework is built and regression analysis is applied to the survey results from 2,063 academic researchers in natural science, engineering, and medical science at five research universities in the United States. Previous work has reported descriptive statistics about these scientists' information‐seeking behavior. This study extends that work to examine relationships between scientists' information‐seeking behaviors and their personal and environmental factors. Several regression models, including the Poisson model, the logit model, and the ordered logit model, are built to interpret the correlation among scientists' behaviors. In addition, exploratory factor analysis is used for data reduction. Overall, many factors were found to affect the specific information‐seeking behaviors of scientists, including demographic, psychological, role‐related, and environmental factors. Of the factors having an effect, academic position was the most important determinant of information behavior.

Many search systems provide users with recommended queries during online information seeking. Although usage statistics are often used to recommend queries, this information is usually not displayed to the user. In this study, we investigate how the presentation of this information impacts use of query suggestions. Twenty-three subjects used an experimental search system to find documents about four topics. Eight query suggestions were provided for each topic: four were high quality queries and four were low quality queries. Fake usage information indicating how many other people used the queries was also provided. For half the queries this information was high and for the other half this information was low. Results showed that subjects could distinguish between high and low quality queries and were not influenced by the usage information. Qualitative data revealed that subjects felt favorable about the suggestions, but the usage information was less important for the search task used in this study.

Abstract As new technologies and information delivery systems emerge, the way in which individuals search for information to support research, teaching, and creative activities is changing. To understand different aspects of researchers' information‐seeking behavior, this article surveyed 2,063 academic researchers in natural science, engineering, and medical science from five research universities in the United States. A Web‐based, in‐depth questionnaire was designed to quantify researchers' information searching, information use, and information storage behaviors. Descriptive statistics are reported. Additionally, analysis of results is broken out by institutions to compare differences among universities. Significant findings are reported, with the biggest changes because of increased utilization of electronic methods for searching, sharing, and storing scholarly content, as well as for utilizing library services. Generally speaking, researchers in the five universities had similar information‐seeking behavior, with small differences because of varying academic unit structures and myriad library services provided at the individual institutions.