Topic-Level Bayesian Surprise and Serendipity for Recommender Systems
Authors:
- Tonmoy HasanTHTonmoy Hasan
- Razvan BunescuRBRazvan Bunescu
Preprint
Abstract
A recommender system that optimizes its recommendations solely to fit a user's history of ratings for consumed items can create a filter bubble, wherein the user does not get to experience items from novel, unseen categories. One approach to mitigate this undesired behavior is to recommend items with high potential for serendipity, namely surprising items that are likely to be highly rated. In this paper, we propose a content-based formulation of serendipity that is rooted in Bayesian surprise and use it to measure the serendipity of items after they are consumed and rated by the user. When coupled with a collaborative-filtering component that identifies similar users, this enables recommending items with high potential for serendipity. To facilitate the evaluation of topic-level models for surprise and serendipity, we introduce a dataset of book reading histories extracted from Goodreads, containing over 26 thousand users and close to 1.3 million books, where we manually annotate 449 books read by 4 users in terms of their time-dependent, topic-level surprise. Experimental evaluations show that models that use Bayesian surprise correlate much better with the manual annotations of topic-level surprise than distance-based heuristics, and also obtain better serendipitous item recommendation performance.Keywords
All Related Versions
- Version 1, 2023-08-11, ArXiv
- Version 2, 2023-10-18, ArXiv
- Published version: , 933.
This publication has 29 references indexed in Scilit:
- An optimized recommendation framework exploiting textual review based opinion mining for generating pleasantly surprising, novel yet relevant recommendationsPattern Recognition Letters, 2022
- Filter Bubbles, Echo Chambers, and Online News ConsumptionPublic Opinion Quarterly, 2016
- On Unexpectedness in Recommender SystemsACM Transactions on Intelligent Systems and Technology, 2014
- A literature review and classification of recommender systems researchExpert Systems with Applications, 2012
- Novel Recommendation Based on Personal Popularity Tendency2011
- Beyond accuracy2010
- Being accurate is not enough2006
- Improving recommendation lists through topic diversification2005
- Recommender systemsCommunications of the ACM, 1997
- Analysis of the normalized LMS algorithm with Gaussian inputsIEEE Transactions on Acoustics, Speech, and Signal Processing, 1986