Benedikt Loepp

Choice-based preference elicitation for collaborative filtering recommender systems

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.

Blended Recommending: Integrating Interactive Information Filtering and Algorithmic Recommender Techniques

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.

A 3D Item Space Visualization for Presenting and Manipulating User Preferences in Collaborative Filtering

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 users 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.

Sequential User-based Recurrent Neural Network Recommendations

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.

Tag-Enhanced Collaborative Filtering for Increasing Transparency and Interactive Control

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.

Merging Interactive Information Filtering and Recommender Algorithms – Model and Concept Demonstrator

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.

Impact of item consumption on assessment of recommendations in user studies

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.

Interactive recommending with Tag-Enhanced Matrix Factorization (TagMF)

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.

Eine Sandbox zur physisch-virtuellen Exploration von Ausgrabungsstätten.

In diesem Beitrag stellen wir die Archäologische Sandbox vor: Ein Tangible User Interface (TUI) mit dem archäologische Ausgrabungsstätten und dort gefundene Artefakte exploriert werden können. Das System zielt auf den Einsatz in Museen ab, die ihren Besuchern den Zusammenhang von ausgestellten Exponaten und der Ausgrabungsstätte näherbringen möchten, an der diese gefunden wurden. Den Kern des TUIs bildet eine mit Sand gefüllte Box, auf dessen Oberfläche eine geografische Karte projiziert wird. Durch das Graben im Sand an der richtigen Stelle werden Informationen zu an diesem Ort gefundenen Ausstellungsstücken abgerufen. Eine durchgeführte qualitative Interviewstudie bestätigt die intuitive Bedienbarkeit und die intrinsisch motivierenden Interaktionsmöglichkeiten des Systems.

Empirische Bedarfsanalyse zur intermodalen Navigation und dem Einsatz von Informationssystemen zur Förderung ihrer Attraktivität

Eine vermehrt intermodale Fortbewegung ist in Zeiten, in denen angesichts uberfullter Innenstadte und Strasen die Verringerung des Verkehrsaufkommens und Verlagerung des motorisierten Individualverkehrs auf umweltfreundlichere Alternativen zunehmend relevanter werden, von groser Bedeutung. Heute gangige Navigationslosungen und Routenplaner sind bezuglich der Unterstutzung komplexer, insbesondere intermodaler Mobilitatsketten jedoch oft nur unzureichend entwickelt: Es mangelt einerseits an einer einheitlichen Integration der Informationen unterschiedlicher Verkehrsmittel, andererseits vor allem an Personalisierungsmoglichkeiten und einer intelligenten Anpassung der Systeme an die momentane Situation des Nutzers (vgl. [7], 0). Oft werden beispielsweise Angebote wie Carund Bikesharing noch auser Acht gelassen, und auch der Kontext als wichtige Determinante bei der Wahl einer Route – fur einen beruflichen Termin bei schlechter Witterung kann ein Fahrrad etwa weniger geeignet sein als bei einem Familienausflug unter sonnigen Bedingungen – bleibt meist unberucksichtigt.