About us
Publications
Home
Publications from 2020 and before are not direct results of the SFI MediaFutures, but are key results from our team members working on related topics in MediaFutures.
2020 |
| Addressing the New Item problem in video recommender systems by incorporation of visual features with restricted Boltzmann machines. Journal Article Naieme Hazrati; Mehdi Elahi In: Expert Systems, vol. e12645, pp. 1-20, 2020, (Pre SFI). Abstract | BibTeX | Tags: Cold Start, Multimedia, New Item, Recommender systems, Visually Aware, WP2: User Modeling Personalization and Engagement | Links: @article{Hazrati2020,Over the past years, the research of video recommender systems (RSs) has been mainly focussed on the development of novel algorithms. Although beneficial, still any algorithm may fail to recommend video items that the system has no form of data associated to them (New Item Cold Start). This problem occurs when a new item is added to the catalogue of the system and no data are available for that item. In content‐based RSs, the video items are typically represented by semantic attributes, when generating recommendations. These attributes require a group of experts or users for annotation, and still, the generated recommendations might not capture a complete picture of the users' preferences, for example, the visual tastes of users on video style. This article addresses this problem by proposing recommendation based on novel visual features that do not require human annotation and can represent visual aspects of video items. We have designed a novel evaluation methodology considering three realistic scenarios, that is, (a) extreme cold start, (b) moderate cold start and (c) warm‐start scenario. We have conducted a set of comprehensive experiments, and our results have shown the superior performance of recommendations based on visual features, in all of the evaluation scenarios. |
| Measuring Recommendation Explanation Quality: The Conflicting Goals of Explanations Conference Krisztian Balog; Filip Radlinski Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR '20), New York, 2020, (Pre SFI). Abstract | BibTeX | Tags: HCI design and evaluation methods, Human-centered computing, Information Systems, Recommender systems, WP2: User Modeling Personalization and Engagement | Links: @conference{Balog2020,Explanations have a large effect on how people respond to recommendations. However, there are many possible intentions a system may have in generating explanations for a given recommendation -from increasing transparency, to enabling a faster decision, to persuading the recipient. As a good explanation for one goal may not be good for others, we address the questions of (1) how to robustly measure if an explanation meets a given goal and (2) how the different goals interact with each other. Specifically, this paper presents a first proposal of how to measure the quality of explanations along seven common goal dimensions catalogued in the literature. We find that the seven goals are not independent, but rather exhibit strong structure. Proposing two novel explanation evaluation designs, we identify challenges in evaluation, and provide more efficient measurement approaches of explanation quality. |
| A Systematic Review and Taxonomy of Explanations in Decision Support and Recommender Systems Journal Article Ingrid Nunes; Dietmar Jannach In: User-Modeling and User-Adapted Interaction, vol. 27, no. 3-5, pp. 393-444, 2020, (Pre SFI). Abstract | BibTeX | Tags: Artificial Intelligence, Decision Support System, Expert System, Explanation, Knowledge-based system, Machine Learning, Recommender systems, Systematic review, Trust, WP2: User Modeling Personalization and Engagement | Links: @article{Nunes2020,With the recent advances in the field of artificial intelligence, an increasing number of decision-making tasks are delegated to software systems. A key requirement for the success and adoption of such systems is that users must trust system choices or even fully automated decisions. To achieve this, explanation facilities have been widely investigated as a means of establishing trust in these systems since the early years of expert systems. With today's increasingly sophisticated machine learning algorithms, new challenges in the context of explanations, accountability, and trust towards such systems constantly arise. In this work, we systematically review the literature on explanations in advice-giving systems. This is a family of systems that includes recommender systems, which is one of the most successful classes of advice-giving software in practice. We investigate the purposes of explanations as well as how they are generated, presented to users, and evaluated. As a result, we derive a novel comprehensive taxonomy of aspects to be considered when designing explanation facilities for current and future decision support systems. The taxonomy includes a variety of different facets, such as explanation objective, responsiveness, content and presentation. Moreover, we identified several challenges that remain unaddressed so far, for example related to fine-grained issues associated with the presentation of explanations and how explanation facilities are evaluated. |
| Beyond “one-size-fits-all” platforms: Applying Campbell's paradigm to test personalized energy advice in the Netherlands Journal Article Alain D. Starke; Martijn C. Willemsen; Chris C.P. Snijders In: vol. 59, no. January 2020, pp. 1-12, 2020. Abstract | BibTeX | Tags: Conservation advice, Energy efficiency, Rasch model, Recommender systems | Links: @article{Starke2020,When analyzing ways in which people save energy, most researchers and policy makers conceptually differentiate between curtailment (e.g. unplugging chargers) and efficiency measures (e.g. installing PV cells). However, such a two-dimensional approach is suboptimal from both a conceptual and policy perspective, as it does not consider individual differences that determine energy-saving behavior. We propose a different, one-dimensional approach, applying Campbell's Paradigm through the Rasch model, in which both curtailment and efficiency measures are intermixed on a single scale and ordered according to their behavioral costs. By matching these behavioral costs to individual energy-saving attitudes, we investigate to what extent attitude-tailored energy-saving advice can help consumers to save energy. We present the results of two studies. The first study (N = 263) reliably calibrated a one-dimensional Rasch scale that consists of 79 energy-saving measures, suitable for advice. The second study employed this scale to investigate how users (N = 196) evaluate attitude-tailored energy-saving advice in a web-based energy recommender system. Results indicate that Rasch-based recommendations can be used to effectively tailor energy-saving advice and that such attitude-tailored advice is more adequate than a number of non-personalized approaches. |
2019 |
| Are We Really Making Much Progress? A Worrying Analysis of Recent Neural Recommendation Approaches Conference Maurizio Ferrari Dacrema; Paolo Cremonesi; Dietmar Jannach Proceedings of the 2019 ACM Conference on Recommender Systems (RecSys 2019), Copenhagen, 2019, (Pre SFI). Abstract | BibTeX | Tags: Collaborative filtering, General and referance, Information Systems, Recommender systems, WP2: User Modeling Personalization and Engagement | Links: @conference{Dacrema2019,Deep learning techniques have become the method of choice for researchers working on algorithmic aspects of recommender systems. With the strongly increased interest in machine learning in general, it has, as a result, become difficult to keep track of what represents the state-of-the-art at the moment, e.g., for top-n recommendation tasks. At the same time, several recent publications point out problems in today’s research practice in applied machine learning, e.g., in terms of the reproducibility of the results or the choice of the baselines when proposing new models. In this work, we report the results of a systematic analysis of algorithmic proposals for top-n recommendation tasks. Specifically, we considered 18 algorithms that were presented at top-level research conferences in the last years. Only 7 of them could be reproduced with reasonable effort. For these methods, it however turned out that 6 of them can often be outperformed with comparably simple heuristic methods, e.g., based on nearest-neighbor or graph-based techniques. The remaining one clearly outperformed the baselines but did not consistently outperform a well-tuned nonneural linear ranking method. Overall, our work sheds light on a number of potential problems in today’s machine learning scholarship and calls for improved scientific practices in this area. |
2018 |
| Evaluation of Session-based Recommendation Algorithms Journal Article Malte Ludewig; Dietmar Jannach In: User-Modeling and User-Adapted Interaction, vol. 28, no. 4-5, pp. 331-390, 2018, (Pre SFI). Abstract | BibTeX | Tags: Evaluation, General and referance, Information Systems, Recommender systems, WP2: User Modeling Personalization and Engagement | Links: @article{Ludewig2018,Recommender systems help users find relevant items of interest, for example on e-commerce or media streaming sites. Most academic research is concerned with approaches that personalize the recommendations according to long-term user profiles. In many real-world applications, however, such long-term profiles often do not exist and recommendations therefore have to be made solely based on the observed behavior of a user during an ongoing session. Given the high practical relevance of the problem, an increased interest in this problem can be observed in recent years, leading to a number of proposals for session-based recommendation algorithms that typically aim to predict the user's immediate next actions. In this work, we present the results of an in-depth performance comparison of a number of such algorithms, using a variety of datasets and evaluation measures. Our comparison includes the most recent approaches based on recurrent neural networks like GRU4REC, factorized Markov model approaches such as FISM or FOSSIL, as well as simpler methods based, e.g., on nearest neighbor schemes. Our experiments reveal that algorithms of this latter class, despite their sometimes almost trivial nature, often perform equally well or significantly better than today's more complex approaches based on deep neural networks. Our results therefore suggest that there is substantial room for improvement regarding the development of more sophisticated session-based recommendation algorithms. |
| Sequence-Aware Recommender Systems Journal Article Massimo Quadrana; Paolo Cremonesi; Dietmar Jannach In: ACM Computing Surveys, vol. 51, no. 4, pp. 1-35, 2018, (Pre SFI). Abstract | BibTeX | Tags: Collaborative filtering, Computing Methodology, Information Systems, Recommender systems, WP2: User Modeling Personalization and Engagement | Links: @article{Quadrana2018,Recommender systems are one of the most successful applications of data mining and machine learning technology in practice. Academic research in the field is historically often based on the matrix completion problem formulation, where for each user-item-pair only one interaction (e.g., a rating) is considered. In many application domains, however, multiple user-item interactions of different types can be recorded over time. And, a number of recent works have shown that this information can be used to build richer individual user models and to discover additional behavioral patterns that can be leveraged in the recommendation process. In this work we review existing works that consider information from such sequentially-ordered user- item interaction logs in the recommendation process. Based on this review, we propose a categorization of the corresponding recommendation tasks and goals, summarize existing algorithmic solutions, discuss methodological approaches when benchmarking what we call sequence-aware recommender systems, and outline open challenges in the area. |
2017 |
| Exploring the semantic gap for movie recommendations Conference Mehdi Elahi; Yashar Deldjoo; Farshad Bakhshandegan Moghaddam; Leonardo Cella; Stefano Cerada; Paolo Cremonesi Proceedings of the Eleventh ACM Conference on Recommender Systems, Association for Computing Machinery New York, 2017, (Pre SFI). Abstract | BibTeX | Tags: Information Systems, Recommender systems, WP2: User Modeling Personalization and Engagement | Links: @conference{Elahi2017,In the last years, there has been much attention given to the semantic gap problem in multimedia retrieval systems. Much effort has been devoted to bridge this gap by building tools for the extraction of high-level, semantics-based features from multimedia content, as low-level features are not considered useful because they deal primarily with representing the perceived content rather than the semantics of it. In this paper, we explore a different point of view by leveraging the gap between low-level and high-level features. We experiment with a recent approach for movie recommendation that extract low-level Mise-en-Scéne features from multimedia content and combine it with high-level features provided by the wisdom of the crowd. To this end, we first performed an offline performance assessment by implementing a pure content-based recommender system with three different versions of the same algorithm, respectively based on (i) conventional movie attributes, (ii) mise-en-scene features, and (iii) a hybrid method that interleaves recommendations based on movie attributes and mise-en-scene features. In a second study, we designed an empirical study involving 100 subjects and collected data regarding the quality perceived by the users. Results from both studies show that the introduction of mise-en-scéne features in conjunction with traditional movie attributes improves both offline and online quality of recommendations. |
2016 |
| Recommender Systems - Beyond Matrix Completion Journal Article Dietmar Jannach; Alexander Tuzhilin; Markus Zanker In: Communications of the ACM, vol. 59, no. 11, pp. 94-102, 2016, (Pre SFI). Abstract | BibTeX | Tags: Recommender systems, WP2: User Modeling Personalization and Engagement | Links: @article{Jannach2016,Recommender systems have become a natural part of the user experience in today's online world. These systems are able to deliver value both for users and providers and are one prominent example where the output of academic research has a direct impact on the advancements in industry. In this article, we have briefy reviewed the history of this multidis-ciplinary field and looked at recent efforts in the research community to consider the variety of factors that may influence the long-term success of a recommender system. The list of open issues and success factors is still far from complete and new challenges arise constantly that require further research. For example, the huge amounts of user data and preference signals that become available through the Social Web and the Internet of Things not only leads to technical challenges such as scalability, but also to societal questions concerning user privacy. Based on our reflections on the developments in the field, we finally emphasize the need for a more holistic research approach that combines the insights of different disciplines. We urge that research focuses even more on practical problems that matter and are truly suited to increase the utility of recommendations from the viewpoint of the users. |
| Alleviating the new user problem in collaborative filtering by exploiting personality information Journal Article Ignacio Fernandez Tobias; Matthias Braunhofer; Mehdi Elahi; Francesco Ricci; Ivan Cantador In: User Modeling and User-Adapted Interaction, vol. 26, no. 2-3, pp. 221-255, 2016, (Pre SFI). Abstract | BibTeX | Tags: Active Learning, Cold-start, Collaborative filtering, Cross-domain, Recommender systems, User Personality, WP2: User Modeling Personalization and Engagement | Links: @article{Tobias2016,The new user problem in recommender systems is still challenging, and there is not yet a unique solution that can be applied in any domain or situation. In this paper we analyze viable solutions to the new user problem in collaborative filtering (CF) that are based on the exploitation of user personality information: (a) personality-based CF, which directly improves the recommendation prediction model by incorporating user personality information, (b) personality-based active learning, which utilizes personality information for identifying additional useful preference data in the target recommendation domain to be elicited from the user, and (c) personality-based cross-domain recommendation, which exploits personality information to better use user preference data from auxiliary domains which can be used to compensate the lack of user preference data in the target domain. We benchmark the effectiveness of these methods on large datasets that span several domains, namely movies, music and books. Our results show that personality-aware methods achieve performance improvements that range from 6 to 94 % for users completely new to the system, while increasing the novelty of the recommended items by 3–40 % with respect to the non-personalized popularity baseline. We also discuss the limitations of our approach and the situations in which the proposed methods can be better applied, hence providing guidelines for researchers and practitioners in the field. |