Markus Zanker

Observing Group Decision Making Processes

Most research on group recommender systems relies on the assumption that individuals have conflicting preferences; in order to generate group recommendations the system should identify a fair way of aggregating these preferences. Both empirical studies and theoretical frameworks have tried to identify the most effective preference aggregation techniques without coming to definite conclusions. In this paper, we propose to approach group recommendation from the group dynamics perspective and analyze the group decision making process for a particular task (in the travel domain). We observe several individual and group properties and correlate them to choice satisfaction. Supported by these initial results we therefore advocate for the development of new group recommendation techniques that consider group dynamics and support the full group decision making process.

Contrasting Offline and Online Results when Evaluating Recommendation Algorithms

Most evaluations of novel algorithmic contributions assess their accuracy in predicting what was withheld in an offline evaluation scenario. However, several doubts have been raised that standard offline evaluation practices are not appropriate to select the best algorithm for field deployment. The goal of this work is therefore to compare the offline and the online evaluation methodology with the same study participants, i.e. a within users experimental design. This paper presents empirical evidence that the ranking of algorithms based on offline accuracy measurements clearly contradicts the results from the online study with the same set of users. Thus the external validity of the most commonly applied evaluation methodology is not guaranteed.

Recommending Based on Implicit Feedback

Recommender systems have shown to be valuable tools for filtering, ranking, and discovery in a variety of application domains such as e-commerce, media repositories or document-based information in general that includes the various scenarios of Social Information Access discussed in this book. One key to the success of such systems lies in the precise acquisition or estimation of the user’s preferences. While general recommender systems research often relies on the existence of explicit preference statements for personalization, such information is often very sparse or unavailable in real-world applications. Information that allows us to assess the relevance of certain items indirectly through a user’s actions and behavior (implicit feedback) is in contrast often available in abundance. In this chapter we categorize different types of implicit feedback and review their use in the context of recommender systems and Social Information Access applications. We then extend the categorization scheme to be suitable to recent application domains. Finally, we present state-of-the-art algorithmic approaches, discuss challenges when using implicit feedback signals in particular with respect to popularity biases, and discuss selected recent works from the literature.

Researching Individual Satisfaction with Group Decisions in Tourism: Experimental Evidence

The goal of the present study was to investigate how satisfied individuals are with the final outcome of a group decision-making process on a joint travel destination. Using an experimental paradigm (N total = 200, N groups = 55) it was obvious to hypothesize that individuals would especially be satisfied with the final group decision when it matched their own initial travel preference and that they would be dissatisfied in case it mismatched their initial preference. However, in addition the influence of personality and group dynamics differences (Thomas-Kilmann Conflict Mode Instrument, Five Factor Model) as well as travel types of the individual decision maker on the satisfaction level with the group decision outcome as the dependent variable were further researched. The paper concludes with implications for e-tourism, especially with regards to the development of interactive tools for group travel.

Replication and Reproduction in Recommender Systems Research - Evidence from a Case-Study with the rrecsys Library

Recommender systems (RS) are a real-world application domain for Artificial Intelligence standing at the core of massively used e-commerce and social-media platforms like Amazon, Netflix, Spotify and many more. The research field of recommendation systems now has already a more than 20 years long tradition and issues like replication of results and reproducibility of algorithms become more important. Therefore this work is oriented towards better understanding the underlying challenges of reproducibility of offline measurements of recommendation techniques. We therefore introduce rrecsys, an open-source package in R, that implements many popular RS algorithms, expansion capabilities and has an integrated offline evaluation mechanism following an accepted methodology. In addition, we present a case study on the usability of the library along with results of benchmarking the provided algorithms with other open-source implementations.

Towards a deep learning model for hybrid recommendation

The deep learning wave is propagating through many research areas and communities. In the last years it quickly propagated to Recommendation Systems, a research area which aims to recommend items to users. Indeed, many deep learning models and architectures have been proposed for Recommendation Systems to improve collaborative filtering and content based algorithms. In this paper we propose a hybrid recommendation system combining user ratings and natural language text processing to solve the 0/1 recommendation problem. In particular, we describe a deep learning architecture combining two information sources, namely natural language text and user rating. Natural language text is used to learn a user-specific content-based classifier, while user ratings are used to develop user-adaptive collaborative filtering recommendations. We perform numerical experiments on MovieLens 1M and reach first preliminary, but promising results, showing the proposed architecture has the potential to combine content-based and collaborative filtering recommendation mechanisms using a deep learning supervisor.

Visual Analysis of Recommendation Performance

rrecsys is a novel library in R for developing and assessing recommendation algorithms. In this demo, we extend rrecsys with functions for visual analytics of recommendation performance, that is one of the strong capabilities of the R environment. In particular, we show how the library can be used to depict dataset characteristics, train and test recommendation algorithms and to visually assess, for instance, their capability to exploit long-tail items for making correct predictions.

Replicating and Improving Top-N Recommendations in Open Source Packages

Collaborative filtering techniques have been studied extensively during the last decade. Many open source packages (Apache Mahout, LensKit, MyMediaLite, rrecsys etc.) have them implemented, but typically the top-N recommendation lists are only based on a highest predicted ratings approach. However, exploiting frequencies in the user/item neighbourhood for the formation of the top-N recommendation lists has been shown to provide superior accuracy results in offline simulations. In this paper, we have therefore implemented extensions to the open source recommendation package for the R language - denoted rrecsys - and compare its performance across open source packages for reasons of replicability. Our experimental results clearly demonstrate that using the most frequent items in neighborhood approach significantly outperforms the highest predicted rating approach on two public datasets.

Exploring Users' Perception of Rating Summary Statistics

Collaborative filtering systems heavily depend on user feedback expressed in product ratings to select and rank items to recommend. These summary statistics of rating values carry two important descriptors about the assessed items, namely the total number of ratings and the mean rating value. In this study we explore how these two signals influence the decisions of online users based on choice-based conjoint experiments. Results show that users are more inclined to follow the mean indicator as opposed to the total number of ratings. Empirical results can serve as an input to developing algorithms that foster items with a, consequently, higher probability of choice based on their rating summarizations or their it explainability due to these ratings when ranking recommendations.

Picture-based navigation for diagnosing post-harvest diseases of apple

This demo presents a conversational navigation approach for a diagnostic application of postharvest diseases of apple with the goal to educate users on the diagnosed diseases as well as to recommend consequences for the storage facility and what action to take for the next growing period. It thus builds on earlier works on picture-based navigation for conversational recommender systems and provides evidence for its usability based on a first small-scale comparative usability study.