@article{ubo_mods_00205246, author = {Loepp, Benedikt}, title = {Multi-list interfaces for recommender systems: Survey and future directions}, journal = {Frontiers in Big Data}, year = {2023}, publisher = {Frontiers Media}, address = {Lausanne}, volume = {6}, keywords = {Recommender systems; Multi-list recommendation; Carousels; User interfaces; User experience; Choice overload; Survey}, abstract = {For a long time, recommender systems presented their results in the form of simple item lists. In recent years, however, multi-list interfaces have become the de-facto standard in industry, presenting users with numerous collections of recommendations, one below the other, each containing items with common characteristics. Netflix’s interface, for instance, shows movies from certain genres, new releases, and lists of curated content. Spotify recommends new songs and albums, podcasts on specific topics, and what similar users are listening to. Despite their popularity, research on these so-called “carousels” is still limited. Few authors have investigated how to simulate the user behavior and how to optimize the recommendation process accordingly. The number of studies involving users is even smaller, with sometimes conflicting results. Consequently, little is known about how to design carousel-based interfaces for achieving the best user experience. This mini review aims to organize the existing knowledge and outlines directions that may improve the multi-list presentation of recommendations in the future.}, note = {in press}, issn = {2624-909X}, doi = {10.3389/fdata.2023.1239705}, url = {https://doi.org/10.3389/fdata.2023.1239705}, language = {en} } @incollection{ubo_mods_00204623, author = {Ziegler, Jürgen and Loepp, Benedikt}, editor = {Augstein, Mirjam and Herder, Eelco and Wörndl, Wolfgang}, title = {User-centered recommender systems}, booktitle = {Personalized Human-Computer Interaction}, series = {De Gruyter Textbook}, year = {2023}, edition = {2}, publisher = {De Gruyter Oldenbourg}, address = {Berlin}, pages = {33–58}, keywords = {Recommender systems; Visualization; Interactive recommending; Explanations; Evaluation}, isbn = {9783110988567}, doi = {10.1515/9783110988567-002}, url = {https://doi.org/10.1515/9783110988567-002}, language = {en}, abstract = {Recommender systems aim at facilitating users’ search and decision-making when they are faced with a large number of available options, such as buying products online or selecting music tracks to listen to. A broad range of machine learning models and algorithms has been developed that aim at predicting users’ assessment of unseen items and at recommending items that best match their interests. However, it has been shown that optimizing the system in terms of algorithm accuracy often does not result in a correspondingly high level of user satisfaction. Therefore, a more user-centric approach to developing recommender systems is needed that better takes into account users’ actual goals, the current context and their cognitive demands. In this chapter, we discuss a number of techniques and design aspects that can contribute to increasing transparency, user understanding and interactive control of recommender systems. Furthermore, we present methods for evaluating systems from a user perspective and point out future research directions.} } @inproceedings{loepp2023how, author = {Loepp, Benedikt and Ziegler, Jürgen}, booktitle = {RecSys ’23: Proceedings of the 17th ACM Conference on Recommender Systems}, title = {How Users Ride the Carousel: Exploring the Design of Multi-List Recommender Interfaces From a User Perspective}, year = {2023}, address = {New York, NY, USA}, publisher = {ACM}, isbn = {9798400702419}, url = {https://doi.org/10.1145/3604915.3610638}, doi = {10.1145/3604915.3610638}, abstract = {Multi-list interfaces are widely used in recommender systems, especially in industry, showing collections of recommendations, one below the other, with items that have certain commonalities. The composition and order of these "carousels" are usually optimized by simulating user interaction based on probabilistic models learned from item click data. Research that actually involves users is rare, with only few studies investigating general user experience in comparison to conventional recommendation lists. Hence, it is largely unknown how specific design aspects such as carousel type and length influence the individual perception and usage of carousel-based interfaces. This paper seeks to fill this gap through an exploratory user study. The results confirm previous assumptions about user behavior and provide first insights into the differences in decision making in the presence of multiple recommendation carousels.} } @inproceedings{ubo_mods_00191514, author = {Loepp, Benedikt}, title = {Recommender Systems Alone Are Not Everything: Towards a Broader Perspective in the Evaluation of Recommender Systems}, booktitle = {PERSPECTIVES ’22: Proceedings of the 2nd Workshop on Perspectives on the Evaluation of Recommender Systems}, year = {2022}, abstract = {Thus far, in most of the user experiments conducted in the area of recommender systems, the respective system is considered as an isolated component, i.e., participants can only interact with the recommender that is under investigation. This fails to recognize the situation of users in real-world settings, where the recommender usually represents only one part of a greater system, with many other options for users to find suitable items than using the mechanisms that are part of the recommender, e.g., liking, rating, or critiquing. For example, in current web applications, users can often choose from a wide range of decision aids, from text-based search over faceted filtering to intelligent conversational agents. This variety of methods, which may equally support users in their decision making, raises the question of whether the current practice in recommender evaluation is sufficient to fully capture the user experience. In this position paper, we discuss the need to take a broader perspective in future evaluations of recommender systems, and raise awareness for evaluation methods which we think may help to achieve this goal, but have not yet gained the attention they deserve.}, url = {http://ceur-ws.org/Vol-3228/paper5.pdf} } @inproceedings{ubo_mods_00185435, author = {Kleemann, Timm and Loepp, Benedikt and Ziegler, Jürgen}, publisher = {ACM}, address = {New York, NY, USA}, title = {Towards Multi-Method Support for Product Search and Recommending}, booktitle = {Adjunct Proceedings of the 30th ACM Conference on User Modeling, Adaptation and Personalization (UMAP ’22)}, year = {2022}, pages = {74–79}, keywords = {Decision aids; Faceted filtering; Conversational recommender systems; Product advisors; Chatbots; Recommender systems; Search interfaces}, isbn = {978-1-4503-9232-7}, doi = {10.1145/3511047}, url = {https://dl.acm.org/doi/10.1145/3511047.3536408?cid=87958660357}, abstract = {Today, online shops offer a variety of components to support users in finding suitable items, ranging from filters and recommendations to conversational advisors and natural language chatbots. All these methods differ in terms of cognitive load and interaction effort, and, in particular, in their suitability for the specific user. However, it is often difficult for users to determine which method to use to reach their goal. Moreover, as the settings are not propagated between the methods, there is a lack of support for switching components. In this paper, we study the reasons for using the different components in more detail and present an initial proposal for a multi-method approach that provides a more seamless experience, allowing users to freely and flexibly choose from all available methods at any time.} } @inproceedings{ubo_mods_00167689, author = {Kleemann, Timm and Wagner, Magdalena and Loepp, Benedikt and Ziegler, Jürgen}, title = {Modeling User Interaction at the Convergence of Filtering Mechanisms, Recommender Algorithms and Advisory Components}, booktitle = {Mensch Und Computer 2021 – Tagungsband}, year = {2021}, publisher = {ACM}, address = {New York, NY, USA}, pages = {531–543}, keywords = {Human factors; User experience; User modeling; Search interfaces; Recommender systems}, isbn = {978-1-4503-8645-6}, doi = {10.1145/3473856}, url = {https://dl.acm.org/doi/10.1145/3473856.3473859?cid=87958660357}, language = {en}, abstract = {A variety of methods is used nowadays to reduce the complexity of product search on e-commerce platforms, allowing users, for example, to specify exactly the features a product should have, but also, just to follow the recommendations automatically generated by the system. While such decision aids are popular with system providers, research to date has mostly focused on individual methods rather than their combination. To close this gap, we propose to support users in choosing the right method for the current situation. As a first step, we report in this paper a user study with a fictitious online shop in which users were able to flexibly use filter mechanisms, rely on recommendations, or follow the guidance of a dialog-based product advisor. We show that from the analysis of the interaction behavior, a model can be derived that allows predicting which of these decision aids is most useful depending on the user’s situation, and how this is affected by demographics and personality.} } @inproceedings{ubo_mods_00167688, author = {Loepp, Benedikt}, title = {On the Convergence of Intelligent Decision Aids}, booktitle = {Mensch Und Computer 2021 – Workshopband}, year = {2021}, publisher = {Gesellschaft für Informatik e.V.}, address = {Bonn}, keywords = {Decision support; Human factors; Information filtering; Adaptive systems; Recommender systems; User experience; User modeling}, abstract = {On the one hand, users’ decision making in today’s web is supported in numerous ways, with mechanisms ranging from manual search over automated recommendation to intelligent advisors. The focus on algorithmic accuracy, however, is questioned more and more. On the other hand, although the boundaries between the mechanisms are blurred increasingly, research on user-related aspects is still conducted separately in each area. In this position paper, we present a research agenda for providing a more holistic solution, in which users are supported with the right decision aid at the right time depending on personal characteristics and situational needs.}, doi = {10.18420/muc2021-mci-ws02-371}, url = {https://doi.org/10.18420/muc2021-mci-ws02-371}, language = {en} } @phdthesis{ubo_mods_00164523, author = {Loepp, Benedikt}, title = {Interactive Methods for Model-based Collaborative Filtering Recommender Systems}, year = {2021}, address = {Duisburg, Essen}, keywords = {Recommender systems; Collaborative filtering; Interactive recommending; Matrix factorization; Empirical studies; User experience; User interfaces}, abstract = {Recommender systems have become very popular for reducing the information overload users are often confronted with in today’s web. Collaborative filtering is the method of choice for generating personalized recommendations, supporting users in finding items that best match their preferences, from news articles and movies to all kinds of consumer goods and services. Model-based techniques have achieved great success in terms of recommendation accuracy and algorithmic performance. While there is a large body of research on these aspects, only little effort has been spent on improving user control and experience. As a consequence, users of contemporary systems usually have no other option than rating single items to indicate their preferences and thus to influence the recommendations. In this thesis, we propose a set of interactive methods for model-based collaborative filtering recommender systems. With these methods, we aim at providing users richer possibilities to specify their preferences and to control the outcome of the systems according to situational needs. In general, users should be enabled to take a more active role throughout the process of finding suitable items. Guided by a structured model of user interaction, we first present a choice-based preference elicitation method. For systems that rely on matrix factorization, one of the most commonly applied techniques in the area of model-based collaborative filtering, this method provides an alternative to rating items in cold-start situations. Furthermore, we describe an algorithmic enhancement, content-boosted matrix factorization. Based on the additional item-related information that is considered by this method, we give several examples of advanced interactive features that allow users to control the recommendations in an even more expressive manner, also later in the process. Finally, we propose a concept called blended recommending. This concept is designed to merge model-based collaborative filtering with other established methods in a way that users can be supported also in complex scenarios with the full range of options they need to reach their search goal. All these methodological contributions are complemented by empirical evaluations. Overall, we conducted four user experiments with n=35, 46, 54 and 33 participants, respectively. The results underline that our methods can effectively be implemented in existing recommender systems in order to turn them into fully interactive, user-controlled applications. This is finally confirmed with the help of an integrated recommendation platform that demonstrates that all our developments can be combined with each other in a single holistic system.}, school = {University of Duisburg-Essen}, doi = {10.17185/duepublico/74289}, url = {https://doi.org/10.17185/duepublico/74289} } @incollection{ubo_mods_00160728, author = {Ziegler, Jürgen and Loepp, Benedikt}, title = {Empfehlungssysteme}, booktitle = {Handbuch Digitale Wirtschaft}, year = {2020}, publisher = {Springer Gabler}, address = {Wiesbaden, Germany}, pages = {717–741}, keywords = {Empfehlungen; Personalisierung; E-Commerce; Recommender Systems; Collaborative Filtering; Usability}, isbn = {978-3-658-17290-9}, doi = {10.1007/978-3-658-17291-6_52}, url = {https://link.springer.com/chapter/10.1007%2F978-3-658-17291-6_52}, editor = {Kollmann, Tobias}, abstract = {Empfehlungssysteme stellen heute eine zentrale Komponente vieler Online-Plattformen dar, die bei Online-Shops und vielen anderen Anwendungen häufig zum Einsatz kommt. Ziel ist es, dem Kunden entsprechend seinen persönlichen Präferenzen Produkte oder andere Artikel vorzuschlagen, die für ihn von Interesse sind und potenziell zu einem Kauf oder generell zur Nutzung führen. Empfehlungssysteme haben eine erhebliche wirtschaftliche Bedeutung, da sie in vielen Fällen zu einem signifikanten Anteil zu Erfolgsfaktoren wie Click-through-Raten oder Käufen beitragen. Wir stellen in diesem Kapitel die unterschiedlichen Ansätze zur automatisierten Empfehlungsgebung vor und beschreiben konkrete Techniken zu deren Umsetzung. Weiterhin gehen wir auf wesentliche Aspekte der Gestaltung und Bewertung von Empfehlungssystemen ein und diskutieren anwenderrelevante Themen wie Usability und Vertrauen in systemgenerierte Empfehlungen.} } @inproceedings{ubo_mods_00154785, author = {Naveed, Sidra and Loepp, Benedikt and Ziegler, Jürgen}, title = {On the Use of Feature-based Collaborative Explanations: An Empirical Comparison of Explanation Styles}, booktitle = {ExUM ’20: Proceedings of the International Workshop on Transparent Personalization Methods based on Heterogeneous Personal Data}, year = {2020}, publisher = {ACM}, address = {New York}, pages = {226–232}, keywords = {User Experience}, doi = {10.1145/3386392.3399303}, url = {https://dl.acm.org/doi/10.1145/3386392.3399303?cid=87958660357}, abstract = {Current attempts to explain recommendations mostly exploit a single type of data, i.e. usually either ratings provided by users for items in collaborative filtering systems, or item features in content-based systems. While this might be sufficient in straightforward recommendation scenarios, the complexity of other situations could require the use of multiple datasources, for instance, depending on the product domain. Even though hybrid systems have a long and successful history in recommender research, the connections between user ratings and item features have only rarely been used for offering more informative and transparent explanations. In previous work, we presented a prototype system based on a feature-weighting mechanism that constitutes an exception, allowing to recommend both items and features based on ratings while offering advanced explanations based on content data. In this paper, we empirically evaluate this prototype in terms of user-oriented aspects and user experience against to widely accepted baselines. Two user studies show that our novel approach outperforms conventional collaborative filtering, while a pure content-based system was perceived in a similarly positive light. Overall, the results draw a promising picture, which becomes particularly apparent from a user perspective when participants were specifically asked to use the explanations: they indicated in their qualitative feedback that they understood them and highly appreciated their availability.} } @inproceedings{ubo_mods_00144402, author = {Loepp, Benedikt and Ziegler, Jürgen}, title = {Measuring the Impact of Recommender Systems – A Position Paper on Item Consumption in User Studies}, booktitle = {Proceedings of the 1st Workshop on Impact of Recommender Systems (ImpactRS ’19)}, year = {2019}, keywords = {User Studies}, url = {https://impactrs19.github.io/papers/short4.pdf}, abstract = {While participants of recommender systems user studies usually cannot experience recommended items, it is common practice that researchers ask them to fill in questionnaires regarding the quality of systems and recommendations. While this has been shown to work well under certain circumstances, it sometimes seems not possible to assess user experience without enabling users to consume items, raising the question of whether the impact of recommender systems has always been measured adequately in past user studies. In this position paper, we aim at exploring this question by means of a literature review and at identifying aspects that need to be further investigated in terms of their influence on assessments in users studies, for instance, the difference between consumption of products or only of related information as well as the effect of domain, domain knowledge and other possibly confounding factors.} } @inproceedings{ubo_mods_00142455, author = {Loepp, Benedikt and Donkers, Tim and Kleemann, Timm and Ziegler, Jürgen}, title = {Impact of Consuming Suggested Items on the Assessment of Recommendations in User Studies on Recommender Systems}, booktitle = {Proceedings of the 28th International Joint Conference on Artificial Intelligence (IJCAI ’19)}, year = {2019}, publisher = {IJCAI Organization}, pages = {6201–6205}, keywords = {Recommender Systems}, doi = {10.24963/ijcai.2019/863}, url = {https://doi.org/10.24963/ijcai.2019/863}, abstract = {User studies are increasingly considered important in research on recommender systems. Although participants typically cannot consume any of the recommended items, they are often asked to assess the quality of recommendations and of other aspects related to user experience by means of questionnaires. Not being able to listen to recommended songs or to watch suggested movies, might however limit the validity of the obtained results. Consequently, we have investigated the effect of consuming suggested items. In two user studies conducted in different domains, we showed that consumption may lead to differences in the assessment of recommendations and in questionnaire answers. Apparently, adequately measuring user experience is in some cases not possible without allowing users to consume items. On the other hand, participants sometimes seem to approximate the actual value of recommendations reasonably well depending on domain and provided information.} } @inproceedings{ubo_mods_00140448, author = {Loepp, Benedikt and Ziegler, Jürgen}, title = {Towards Interactive Recommending in Model-based Collaborative Filtering Systems}, booktitle = {Proceedings of the 13th ACM Conference on Recommender Systems (RecSys ’19)}, year = {2019}, publisher = {ACM}, address = {New York, NY, USA}, pages = {546–547}, keywords = {User Experience}, isbn = {978-1-4503-6243-6}, doi = {10.1145/3298689.3346949}, abstract = {Numerous attempts have been made for increasing the interactivity in recommender systems, but the features actually available in today’s systems are in most cases limited to rating or re-rating single items. We present a demonstrator that showcases how model-based collaborative filtering recommenders may be enhanced with advanced interaction and preference elicitation mechanisms in a holistic manner. Hereby, we underline that by employing methods we have proposed in the past it becomes possible to easily extend any matrix factorization recommender into a fully interactive, user-controlled system. By presenting and deploying our demonstrator, we aim at gathering further insights, both into how the different mechanisms may be intertwined even more closely, and how interaction behavior and resulting user experience are influenced when users can choose from these mechanisms at their own discretion.}, url = {https://dl.acm.org/doi/10.1145/3298689.3346949?cid=87958660357} } @inproceedings{ubo_mods_00138305, author = {Kunkel, Johannes and Loepp, Benedikt and Dolff, Esther and Ziegler, Jürgen}, title = {LittleMissFits: Ein Game-With-A-Purpose zur Evaluierung subjektiver Verständlichkeit von latenten Faktoren in Empfehlungssystemen}, booktitle = {Mensch und Computer 2019 – Workshopband}, year = {2019}, publisher = {Gesellschaft für Informatik e.V.}, pages = {49–56}, keywords = {Nutzerkontrolle}, doi = {10.18420/muc2019-ws-576}, url = {https://dx.doi.org/10.18420/muc2019-ws-576}, abstract = {Empfehlungssysteme, die mit Hilfe latenter Faktormodelle Empfehlungen generieren, arbeiten äußerst genau und sind entsprechend weit verbreitet. Da die Berechnung der Empfehlungen jedoch auf der statistischen Auswertung von Benutzerbewertungen basiert, gestaltet es sich schwierig, die Empfehlungen dem Nutzer gegenüber zu erklären. Daher werden die Systeme häufig als intransparent wahrgenommen und können oft ihr volles Potential nicht entfalten. Erste Ansätze zeigen allerdings, dass die latenten Faktoren solcher Modelle semantische Eigenschaften der Produkte widerspiegeln. Dabei ist bislang unklar, ob die zum Teil sehr komplexe Parametrisierung, die z.B. die Anzahl der Faktoren festlegt, Auswirkungen auf die semantische Verständlichkeit hat. Da dies sehr von der subjektiven Wahrnehmung abhängt, präsentieren wir mit LittleMissFits ein Online-Spiel, das es erlaubt, mittels Crowd-Sourcing die Konsistenz der latenten Faktoren zu untersuchen. Die Ergebnisse einer Nutzerstudie mit diesem Spiel zeigen, dass eine höhere Anzahl von Faktoren das Modell weniger verständlich erscheinen lässt. Darüber hinaus fanden sich Unterschiede innerhalb der Faktormodelle bezüglich der Verständlichkeit der einzelnen Faktoren. Zusammengenommen stellen die Ergebnisse eine wertvolle Grundlage dar, um künftig die Transparenz entsprechender Empfehlungssysteme zu steigern.} } @article{ubo_mods_00109856, author = {Loepp, Benedikt and Donkers, Tim and Kleemann, Timm and Ziegler, Jürgen}, volume = {121}, pages = {21–41}, title = {Interactive Recommending with Tag-Enhanced Matrix Factorization (TagMF)}, journal = {International Journal of Human Computer Studies}, year = {2019}, keywords = {Collaborative Filtering, Empirical studies, Human factors, Interactive recommending, Matrix Factorization, Recommender Systems, Tags, User experience, User interfaces, User profiles}, doi = {10.1016/j.ijhcs.2018.05.002}, url = {https://doi.org/10.1016/j.ijhcs.2018.05.002}, abstract = {We introduce TagMF, a model-based Collaborative Filtering method that aims at increasing transparency and offering richer interaction possibilities in current Recommender Systems. Model-based Collaborative Filtering is currently the most popular method that predominantly uses Matrix Factorization: This technique achieves high accuracy in recommending interesting items to individual users by learning latent factors from implicit feedback or ratings the community of users provided for the items. However, the model learned and the resulting recommendations can neither be explained, nor can users be enabled to influence the recommendation process except by rating (more) items. In TagMF, we enhance a latent factor model with additional content information, specifically tags users provided for the items. The main contributions of our method are to use this integrated model to elucidate the hidden semantics of the latent factors and to let users interactively control recommendations by changing the influence of the factors through easily comprehensible tags: Users can express their interests, interactively manipulate results, and critique recommended items—at cold-start when no historical data is yet available for a new user, as well as in case a long-term profile representing the current user’s preferences already exists. To validate our method, we performed offline experiments and conducted two empirical user studies where we compared a recommender that employs TagMF against two established baselines, standard Matrix Factorization based on ratings, and a purely tag-based interactive approach. This user-centric evaluation confirmed that enhancing a model-based method with additional information positively affects perceived recommendation quality. Moreover, recommendations were considered more transparent and users were more satisfied with their final choice. Overall, learning an integrated model and implementing the interactive features that become possible as an extension to contemporary systems with TagMF appears beneficial for the subjective assessment of several system aspects, the level of control users are able to exert over the recommendation process, as well as user experience in general.} } @inproceedings{ubo_mods_00116566, author = {Loepp, Benedikt and Donkers, Tim and Kleemann, Timm and Ziegler, Jürgen}, title = {Impact of Item Consumption on Assessment of Recommendations in User Studies}, booktitle = {Proceedings of the 12th ACM Conference on Recommender Systems (RecSys ’18)}, year = {2018}, publisher = {ACM}, address = {New York, NY, USA}, pages = {49–53}, keywords = {User Studies}, isbn = {978-1-4503-5901-6}, doi = {10.1145/3240323.3240375}, url = {https://dl.acm.org/doi/10.1145/3240323.3240375?cid=87958660357}, abstract = {In user studies of recommender systems, participants typically cannot consume the recommended items. Still, they are asked to assess recommendation quality and other aspects related to user experience by means of questionnaires. Without having listened to recommended songs or watched suggested movies, however, this might be an error-prone task, possibly limiting validity of results obtained in these studies. In this paper, we investigate the effect of actually consuming the recommended items. We present two user studies conducted in different domains showing that in some cases, differences in the assessment of recommendations and in questionnaire results occur. Apparently, it is not always possible to adequately measure user experience without allowing users to consume items. On the other hand, depending on domain and provided information, participants sometimes seem to approximate the actual value of recommendations reasonably well.} } @inproceedings{ubo_mods_00115757, author = {Loepp, Benedikt and Ziegler, Jürgen}, title = {Recommending Running Routes: Framework and Demonstrator}, booktitle = {Proceedings of the 2nd Second Workshop on Recommendation in Complex Scenarios (ComplexRec ’18)}, year = {2018}, pages = {26–29}, keywords = {Sports}, url = {http://toinebogers.com/workshops/complexrec2018/resources/proceedings.pdf#page=26}, abstract = {Recommending personalized running routes is a challenging task. When the runner’s specific background as well as needs, preferences and goals are taken into account, a recommender cannot only rely on e.g. a set of existing routes ran by others, but needs to individually generate each route while considering many different aspects that determine whether a suggestion will satisfy the runner in the end, e.g. height meters or areas passed. We describe a framework that summarizes these aspects, allowing to generate personalized running routes. Based on this framework, we present a prototypical smartphone app that we implemented to actually demonstrate how running routes can be recommended based on the different requirements a runner might have. A first small study where users had to try this app and ran some of the recommended routes underlines the general effectiveness of our approach.} } @inproceedings{ubo_mods_00115227, author = {Kunkel, Johannes and Loepp, Benedikt and Ziegler, Jürgen}, title = {Understanding Latent Factors Using a GWAP}, booktitle = {Proceedings of the Late-Breaking Results track part of the Twelfth ACM Conference on Recommender Systems (RecSys ’18)}, year = {2018}, keywords = {Game with a Purpose}, url = {https://arxiv.org/abs/1808.10260}, abstract = {Recommender systems relying on latent factor models often appear as black boxes to their users. Semantic descriptions for the factors might help to mitigate this problem. Achieving this automatically is, however, a non-straightforward task due to the models’ statistical nature. We present an output-agreement game that represents factors by means of sample items and motivates players to create such descriptions. A user study shows that the collected output actually reflects real-world characteristics of the factors.} } @inproceedings{ubo_mods_00114940, author = {Kunkel, Johannes and Loepp, Benedikt and Ziegler, Jürgen}, title = {Ein Online-Spiel zur Benennung latenter Faktoren in Empfehlungssystemen}, booktitle = {Mensch und Computer 2018 – Tagungsband}, year = {2018}, publisher = {Gesellschaft für Informatik e.V.}, keywords = {Games with a Purpose}, abstract = {Empfehlungssysteme, die auf latenten Faktormodellen basieren, sind dafür bekannt sehr genaue Vorschläge zu generieren. Häufig werden diese Systeme jedoch von Nutzern als intransparent wahrgenommen. Semantische Beschreibungen der latenten Faktoren könnten helfen, dieses Problem zu lindern. Solche Beschreibungen automatisch zu ermitteln gestaltet sich allerdings aufgrund der statistischen Herleitung der Faktoren aus numerischen Bewertungsdaten als schwierig. In diesem Beitrag stellen wir ein Output-Agreement-Spiel vor, das Spieler dazu motiviert, anhand repräsentativer Produkte Beschreibungen zu den Faktoren zu erstellen. Eine durchgeführte Nutzerstudie zeigt, dass das Spiel viel Spaß bereitet und die erhobenen Beschreibungen realweltliche Eigenschaften der Faktoren widerspiegeln.}, doi = {10.18420/muc2018-mci-0108}, url = {https://dl.gi.de/handle/20.500.12116/16729} } @inproceedings{ubo_mods_00104370, author = {Donkers, Tim and Loepp, Benedikt and Ziegler, Jürgen}, booktitle = {Proceedings of the 1st Workshop on Explainable Smart Systems (ExSS ’18)}, title = {Explaining Recommendations by Means of User Reviews}, year = {2018}, keywords = {Explanations}, url = {http://ceur-ws.org/Vol-2068/exss8.pdf}, abstract = {The field of recommender systems has seen substantial progress in recent years in terms of algorithmic sophistication and quality of recommendations as measured by standard accuracy metrics. Yet, the systems mainly act as black boxes for the user and are limited in their capability to explain why certain items are recommended. This is particularly true when using abstract models which do not easily lend themselves for providing explanations. In many cases, however, recommendation methods are employed in scenarios where users not only rate items, but also provide feedback in the form of tags or written product reviews. Such user-generated content can serve as a useful source for deriving explanatory information that may increase the user’s understanding of the underlying criteria and mechanisms that led to the results. In this paper, we describe a set of developments we undertook to couple such textual content with common recommender techniques. These developments have moved from integrating tags into collaborative filtering to employing topics and sentiments expressed in reviews to increase transparency and to give users more control over the recommendation process. Furthermore, we describe our current research goals and a first concept concerning extraction of more complex argumentative explanations from textual reviews and presenting them to users.} } @inproceedings{ubo_mods_00090488, author = {Donkers, Tim and Loepp, Benedikt and Ziegler, Jürgen}, chapter = {}, title = {Sequential User-based Recurrent Neural Network Recommendations}, year = {2017}, publisher = {ACM}, address = {New York, NY, USA}, pages = {152–160}, keywords = {Sequential Recommendations}, doi = {10.1145/3109859.3109877}, url = {https://dl.acm.org/doi/10.1145/3109859.3109877?cid=87958660357}, abstract = {Recurrent Neural Networks are powerful tools for modeling sequences. They are flexibly extensible and can incorporate various kinds of information including temporal order. These properties make them well suited for generating sequential recommendations. In this paper, we extend Recurrent Neural Networks by considering unique characteristics of the Recommender Systems domain. One of these characteristics is the explicit notion of the user recommendations are specifically generated for. We show how individual users can be represented in addition to sequences of consumed items in a new type of Gated Recurrent Unit to effectively produce personalized next item recommendations. Offline experiments on two real-world datasets indicate that our extensions clearly improve objective performance when compared to state-of-the-art recommender algorithms and to a conventional Recurrent Neural Network.}, booktitle = {Proceedings of the 11th ACM Conference on Recommender Systems (RecSys ’17)} } @inproceedings{ubo_mods_00089097, author = {Feuerbach, Jan and Loepp, Benedikt and Barbu, Catalin-Mihai and Ziegler, Jürgen}, title = {Enhancing an Interactive Recommendation System with Review-based Information Filtering}, booktitle = {Proceedings of the 4th Joint Workshop on Interfaces and Human Decision Making for Recommender Systems (IntRS ’17)}, series = {CEUR workshop proceedings}, year = {2017}, volume = {1884}, pages = {2–9}, keywords = {User Reviews}, abstract = {Integrating interactive faceted filtering with intelligent recommendation techniques has shown to be a promising means for increasing user control in Recommender Systems. In this paper, we extend the concept of blended recommending by automatically extracting meaningful facets from social media by means of Natural Language Processing. Concretely, we allow users to influence the recommendations by selecting facet values and weighting them based on information other users provided in their reviews. We conducted a user study with an interactive recommender implemented in the hotel domain. This evaluation shows that users are consequently able to find items fitting interests that are typically difficult to take into account when only structured content data is available. For instance, the extracted facets representing the opinions of hotel visitors make it possible to effectively search for hotels with comfortable beds or that are located in quiet surroundings without having to read the user reviews.}, url = {http://ceur-ws.org/Vol-1884/paper1.pdf} } @inproceedings{ubo:80746, author = {Loepp, Benedikt and Ziegler, Jürgen}, chapter = {}, title = {On User Awareness in Model-Based Collaborative Filtering Systems}, year = {2017}, keywords = {User Experience}, url = {https://iuiaware2017.files.wordpress.com/2016/11/on_user_awareness_in_model-based_collaborative_filtering_systems2.pdf}, abstract = {In this paper, we discuss several aspects that users are typically not fully aware of when using model-based Collaborative Filtering systems. For instance, the methods prevalently used in conventional recommenders infer abstract models that are opaque to users, making it difficult to understand the learned profile, and consequently, why certain items are recommended. Further, users are not able to keep an overview of the item space, and thus the alternatives that in principle could also be suggested. By summarizing our experiences on exploiting latent factor models for increasing control and transparency, we show that the respective techniques may also contribute to make users more aware of their preferences’ representation, the rationale behind the results, and further items of potential interest.}, booktitle = {Proceedings of the 1st Workshop on Awareness Interfaces and Interactions (AWARE ’17)} } @inproceedings{ubo:80745, author = {Kunkel, Johannes and Loepp, Benedikt and Ziegler, Jürgen}, chapter = {}, title = {A 3D Item Space Visualization for Presenting and Manipulating User Preferences in Collaborative Filtering}, year = {2017}, publisher = {ACM}, address = {New York, NY, USA}, pages = {3–15}, keywords = {3D Visualizations}, doi = {10.1145/3025171.3025189}, url = {https://dl.acm.org/doi/10.1145/3025171.3025189?cid=87958660357}, abstract = {While conventional Recommender Systems perform well in automatically generating personalized suggestions, it is often difficult for users to understand why certain items are recommended and which parts of the item space are covered by the recommendations. Also, the available means to influence the process of generating results are usually very limited. To alleviate these problems, we suggest a 3D map-based visualization of the entire item space in which we position and present sample items along with recommendations. The map is produced by mapping latent factors obtained from Collaborative Filtering data onto a 2D surface through Multidimensional Scaling. Then, areas that contain items relevant with respect to the current user’s preferences are shown as elevations on the map, areas of low interest as valleys. In addition to the presentation of his or her preferences, the user may interactively manipulate the underlying profile by raising or lowering parts of the landscape, also at cold-start. Each change may lead to an immediate update of the recommendations. Using a demonstrator, we conducted a user study that, among others, yielded promising results regarding the usefulness of our approach.}, booktitle = {Proceedings of the 22nd International Conference on Intelligent User Interfaces (IUI ’17)} } @inproceedings{ubo:73248, author = {Loepp, Benedikt and Barbu, Catalin-Mihai and Ziegler, Jürgen}, chapter = {}, title = {Interactive Recommending: Framework, State of Research and Future Challenges}, year = {2016}, pages = {3–13}, keywords = {Survey}, abstract = {In this paper, we present a framework describing the various aspects of recommender systems that can serve for empowering users by giving them more interactive control and transparency in the recommendation process. While conventional recommenders mostly operate like black boxes that cannot be influenced by the user, we identify four aspects properly connected with the recommendation algorithm—namely input data, user model, external con-text model and presentation—as essential points in which a system may be enhanced by additional interaction possibilities. In light of this framework, we take a closer look at prior and present solutions to integrate recommender systems with more interactivity and describe future research challenges. Regarding these challenges, we especially focus on experiences gained in our own work and outline future research we have planned in the area of interactive recommending.}, url = {http://ceur-ws.org/Vol-1705/02-paper.pdf}, booktitle = {Proceedings of the 1st Workshop on Engineering Computer-Human Interaction in Recommender Systems (EnCHIReS ’16)} } @inproceedings{ubo:72538, author = {Donkers, Tim and Loepp, Benedikt and Ziegler, Jürgen}, chapter = {}, title = {Towards Understanding Latent Factors and User Profiles by Enhancing Matrix Factorization with Tags}, year = {2016}, keywords = {Explanations}, url = {http://ceur-ws.org/Vol-1688/paper-20.pdf}, abstract = {With the interactive recommending approach we have recently proposed, users are given more control over model-based Collaborative Filtering while the results are perceived as more transparent. Integrating the latent factors derived by Matrix Factorization with tags users provided for the items has, however, even more advantages. In this paper, we show how general understanding of the abstract factor space, and of user and item positions inside it, can benefit from the semantics introduced by considering additional information. Moreover, our approach allows us to explain the user’s (former latent) preference profile by means of tags.}, booktitle = {Poster Proceedings of the 10th ACM Conference on Recommender Systems (RecSys ’16)} } @inproceedings{ubo:69909, author = {Donkers, Tim and Loepp, Benedikt and Ziegler, Jürgen}, chapter = {}, title = {Tag-Enhanced Collaborative Filtering for Increasing Transparency and Interactive Control}, year = {2016}, publisher = {ACM}, address = {New York, NY, USA}, pages = {169–173}, keywords = {User Experience}, abstract = {To increase transparency and interactive control in Recommender Systems, we extended the Matrix Factorization technique widely used in Collaborative Filtering by learning an integrated model of user-generated tags and latent factors derived from user ratings. Our approach enables users to manipulate their preference profile expressed implicitly in the (intransparent) factor space through explicitly presented tags. Furthermore, it seems helpful in cold-start situations since user preferences can be elicited via meaningful tags instead of ratings. We evaluate this approach and present a user study that to our knowledge is the most extensive empirical study of tag-enhanced recommending to date. Among other findings, we obtained promising results in terms of recommendation quality and perceived transparency, as well as regarding user experience, which we analyzed by Structural Equation Modeling.}, doi = {10.1145/2930238.2930287}, url = {https://dl.acm.org/doi/10.1145/2930238.2930287?cid=87958660357}, booktitle = {Proceedings of the 24th Conference on User Modeling Adaptation and Personalization (UMAP ’16)} } @inproceedings{ubo:57156, author = {Donkers, Tim and Loepp, Benedikt and Ziegler, Jürgen}, chapter = {}, title = {Merging Latent Factors and Tags to Increase Interactive Control of Recommendations}, year = {2015}, abstract = {We describe a novel approach that integrates user-generated tags with standard Matrix Factorization to allow users to interactively control recommendations. The tag information is incorporated during the learning phase and relates to the automatically derived latent factors. Thus, the system can change an item’s score whenever the user adjusts a tag’s weight. We implemented a prototype and performed a user study showing that this seems to be a promising way for users to interactively manipulate the set of items recommended based on their user profile or in cold-start situations.}, url = {http://ceur-ws.org/Vol-1441/recsys2015_poster12.pdf}, booktitle = {Poster Proceedings of the 9th ACM Conference on Recommender Systems (RecSys ’15)} } @inproceedings{ubo:57124, author = {Kunkel, Johannes and Loepp, Benedikt and Ziegler, Jürgen}, chapter = {}, title = {3D-Visualisierung zur Eingabe von Präferenzen in Empfehlungssystemen}, year = {2015}, pages = {123–132}, publisher = {De Gruyter Oldenbourg}, address = {Berlin}, abstract = {In diesem Beitrag stellen wir ein interaktives Empfehlungssystem vor, bei dem Nutzer ihre Präferenzen in einer dreidimensionalen Visualisierung des Produktraums eingeben können. Die Darstellung in Form einer Landschaft spiegelt dabei das Profil des aktuellen Nutzers wider, und ermöglicht diesem sowohl in Kaltstartsituationen als auch bei der späteren Anpassung eines existierenden Profils interaktiv seine Präferenzen anzugeben. Die Methode basiert auf den von allen Nutzern abgegebenen Bewertungen und benötigt kein inhaltliches Wissen über die Produkte. Die durchgeführte Nutzerstudie zeigt, dass die Visualisierung nachvollziehbar und hilfreich erscheint. Bezüglich der Eingabe von Präferenzen durch Modellierung der Landschaft ergaben sich ebenfalls vielversprechende Ergebnisse, u. a. auch im Hinblick auf User Experience und Empfehlungsqualität.}, doi = {10.1515/9783110443929-014}, url = {http://dx.doi.org/10.1515/9783110443929-014}, booktitle = {Mensch und Computer 2015 – Tagungsband} } @article{ubo:54267, author = {Loepp, Benedikt and Herrmanny, Katja and Ziegler, Jürgen}, title = {Merging Interactive Information Filtering and Recommender Algorithms: Model and Concept Demonstrator}, journal = {i-com}, year = {2015}, volume = {14}, number = {1}, pages = {5–17}, issn = {2196-6826}, doi = {10.1515/icom-2015-0006}, url = {http://dx.doi.org/10.1515/icom-2015-0006}, abstract = {To increase controllability and transparency in recommender systems, recent research has been putting more focus on integrating interactive techniques with recommender algorithms. In this paper, we propose a model of interactive recommending that structures the different interactions users can have with recommender systems. Furthermore, as a novel approach to interactive recommending, we describe a technique that combines faceted information filtering with different algorithmic recommender techniques. We refer to this approach as blended recommending. We also present an interactive movie recommender based on this approach and report on its user-centered design process, in particular an evaluation study in which we compared our system with a standard faceted filtering system. The results indicate a higher level of perceived user control, more detailed preference settings, and better suitability when the search goal is vague.} } @inproceedings{ubo:53366, author = {Loepp, Benedikt and Herrmanny, Katja and Ziegler, Jürgen}, chapter = {}, title = {Blended Recommending: Integrating Interactive Information Filtering and Algorithmic Recommender Techniques}, year = {2015}, publisher = {ACM}, address = {New York, NY, USA}, abstract = {We present a novel approach that integrates algorithmic recommender techniques with interactive faceted filtering methods. We refer to this approach as blended recommending. It allows users to interact with a set of filter facets representing criteria that can serve as input for different recommendation methods including both collaborative and content-based filtering. Users can select filter criteria from these facets and weight them to express their preferences and to exert control over the hybrid recommendation process. In contrast to hard Boolean filtering, the method aggregates the weighted criteria and calculates a ranked list of recommendations that is visualized and immediately updated when users change the filter settings. Based on this approach, we implemented an interactive movie recommender, MyMovieMixer. In a user study, we compared the system with a conventional faceted filtering system that served as a baseline to obtain insights into user interaction behavior and to assess recommendation quality for our system. The results indicate, among other findings, a higher level of perceived user control, more detailed preference settings, and better suitability when the search goal is vague.}, doi = {10.1145/2702123.2702496}, pages = {975–984}, url = {https://dl.acm.org/doi/10.1145/2702123.2702496?cid=87958660357}, booktitle = {Proceedings of the 33rd International Conference on Human Factors in Computing Systems (CHI ’15)} } @inproceedings{ubo:48983, author = {Herrmanny, Katja and Schering, Sandra and Berger, Ralf and Loepp, Benedikt and Günter, Timo and Hussein, Tim and Ziegler, Jürgen}, chapter = {}, title = {MyMovieMixer: Ein hybrider Recommender mit visuellem Bedienkonzept}, year = {2014}, publisher = {De Gruyter Oldenbourg}, address = {Berlin}, pages = {45–54}, doi = {10.1524/9783110344486.45}, url = {http://dx.doi.org/10.1524/9783110344486.45}, abstract = {In diesem Beitrag stellen wir ein neuartiges, auf direkter Manipulation beruhendes Bedienkonzept für komplexe hybride Empfehlungssysteme anhand des von uns entwickelten Film-Recommenders MyMovieMixer vor. Der Ansatz ermöglicht es den Nutzern, ein hybrides Recommender-System mit einem komplexen Zusammenwirken verschiedener Filtermethoden durch interaktive und visuelle Methoden intuitiv zu steuern. Gleichzeitig wird die Transparenz der Empfehlungsgenerierung deutlich erhöht. Die Ergebnisse einer empirischen Evaluation des Systems zeigen, dass der Ansatz in Bezug auf Usability, User Experience, Intuitivität, Transparenz, wahrgenommene Empfehlungsqualität und somit letztlich im Hinblick auf die Nutzerzufriedenheit vielversprechend ist. }, booktitle = {Mensch und Computer 2014 – Tagungsband} } @inproceedings{ubo:46601, author = {Loepp, Benedikt and Hussein, Tim and Ziegler, Jürgen}, chapter = {}, title = {Choice-based Preference Elicitation for Collaborative Filtering Recommender Systems}, year = {2014}, pages = {3085–3094}, publisher = {ACM}, address = {New York, NY, USA}, isbn = {978-1-4503-2473-1}, doi = {10.1145/2556288.2557069}, abstract = {We present an approach to interactive recommending that combines the advantages of algorithmic techniques with the benefits of user-controlled, interactive exploration in a novel manner. The method extracts latent factors from a matrix of user rating data as commonly used in Collaborative Filtering, and generates dialogs in which the user iteratively chooses between two sets of sample items. Samples are chosen by the system for low and high values of each latent factor considered. The method positions the user in the latent factor space with few interaction steps, and finally selects items near the user position as recommendations. In a user study, we compare the system with three alternative approaches including manual search and automatic recommending. The results show significant advantages of our approach over the three competing alternatives in 15 out of 24 possible parameter comparisons, in particular with respect to item fit, interaction effort and user control. The findings corroborate our assumption that the proposed method achieves a good trade-off between automated and interactive functions in recommender systems.}, url = {https://dl.acm.org/doi/10.1145/2556288.2557069?cid=87958660357}, booktitle = {Proceedings of the 32nd International Conference on Human Factors in Computing Systems (CHI ’14)} } @inproceedings{ubo:42828, author = {Loepp, Benedikt and Hussein, Tim and Ziegler, Jürgen}, chapter = {}, title = {Interaktive Empfehlungsgenerierung mit Hilfe latenter Produktfaktoren}, year = {2013}, publisher = {Oldenbourg}, address = {München}, abstract = {In diesem Beitrag beschreiben wir ein Verfahren zur Generierung interaktiver Empfehlungsdialoge auf Basis latenter Produktfaktoren. Der Ansatz verbindet auf neuartige Weise Methoden zur automatischen Generierung von Empfehlungen mit interaktiven, explorativen Methoden der Produktsuche. Das vorgestellte Verfahren nutzt verborgene Muster in Produktbewertungen (latente Faktoren) und erzeugt auf dieser Basis visuelle Dialoge, die den Nutzer schrittweise und intuitiv durch einen Explorationsprozess führen. In einer Nutzerstudie konnten wir zeigen, dass ein derartiger interaktiver Empfehlungsprozess hinsichtlich des Aufwandes und der Zufriedenheit mit den erzielten Resultaten eine deutliche Verbesserung gegenüber rein manuellen oder rein automatischen Verfahren bieten kann.}, pages = {17–26}, doi = {10.1524/9783486781229.17}, url = {http://dx.doi.org/10.1524/9783486781229.17}, booktitle = {Mensch & Computer 2013 – Tagungsband} }