# Topic-Level Bayesian Surprise and Serendipity for Recommender Systems

arXiv: https://arxiv.org/abs/2308.06368 · HTML: https://mlsanity.com/paper/2308.06368/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 44 references that are in the map.
- First posted on arXiv 11 Aug 2023.

## Builds on (most cited first, 7 of 7)

- [Neural Collaborative Filtering](https://mlsanity.com/paper/1708.05031/) (2017)
- [Feedback Loop and Bias Amplification in Recommender Systems](https://mlsanity.com/paper/2007.13019/) (2020)
- [DGCN: Diversified Recommendation with Graph Convolutional Networks](https://mlsanity.com/paper/2108.06952/) (2021)
- [User-controllable Recommendation Against Filter Bubbles](https://mlsanity.com/paper/2204.13844/) (2022)
- [Kalman Filter for Online Classification of Non-Stationary Data](https://mlsanity.com/paper/2306.08448/) (2023)
- [PURS: Personalized Unexpected Recommender System for Improving User Satisfaction](https://mlsanity.com/paper/2106.02771/) (2021)
- [Latent Unexpected Recommendations](https://mlsanity.com/paper/2007.13280/) (2020)

## Built on by (most cited first, 1 of 1)

- [A Text-Based Recommender System that Leverages Explicit Affective State Preferences](https://mlsanity.com/paper/2505.20190/) (2025)

## Abstract (arXiv)

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.