On the Use of Feature-based Collaborative Explanations: An Empirical Comparison of Explanation Styles

Naveed, S., Loepp, B., & Ziegler, J. (2020). ExUM ’20: Proceedings of the International Workshop on Transparent Personalization Methods Based on Heterogeneous Personal Data, 226–232.

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.

Additional information

Resources

Related publications

Measuring the Impact of Recommender Systems – A Position Paper on Item Consumption in User Studies

Challenges in User-Centered Engineering of AI-based Interactive Systems

Feature-driven interactive recommendations and explanations with collaborative filtering approach

More »