# Combating the Filter Bubble: Designing for Serendipity in a University Course Recommendation System

arXiv: https://arxiv.org/abs/1907.01591 · HTML: https://mlsanity.com/paper/1907.01591/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Jul 2019.

## Built on by (most cited first, 11 of 11)

- [A Human-Centered Review of Algorithms in Decision-Making in Higher Education](https://mlsanity.com/paper/2302.05839/) (2023)
- [Finding Paths for Explainable MOOC Recommendation: A Learner Perspective](https://mlsanity.com/paper/2312.10082/) (2023)
- [A Toolbox for Modelling Engagement with Educational Videos](https://mlsanity.com/paper/2401.05424/) (2023)
- [FaiREO: User Group Fairness for Equality of Opportunity in Course Recommendation](https://mlsanity.com/paper/2109.05931/) (2021)
- [Insights into undergraduate pathways using course load analytics](https://mlsanity.com/paper/2212.09974/) (2022)
- [From Interests to Insights: An LLM Approach to Course Recommendations Using Natural Language Queries](https://mlsanity.com/paper/2412.19312/) (2024)
- [Masked Deep Q-Recommender for Effective Question Scheduling](https://mlsanity.com/paper/2112.10125/) (2021)
- [BHEISR: Nudging from Bias to Balance -- Promoting Belief Harmony by Eliminating Ideological Segregation in Knowledge-based Recommendations](https://mlsanity.com/paper/2307.02797/) (2023)
- [TrueLearn: A Python Library for Personalised Informational Recommendations with (Implicit) Feedback](https://mlsanity.com/paper/2309.11527/) (2023)
- [How Good Are Large Language Models for Course Recommendation in MOOCs?](https://mlsanity.com/paper/2504.08208/) (2025)
- [Skill-based Explanations for Serendipitous Course Recommendation](https://mlsanity.com/paper/2508.19569/) (2025)

## Abstract (arXiv)

Collaborative filtering based algorithms, including Recurrent Neural Networks (RNN), tend towards predicting a perpetuation of past observed behavior. In a recommendation context, this can lead to an overly narrow set of suggestions lacking in serendipity and inadvertently placing the user in what is known as a "filter bubble." In this paper, we grapple with the issue of the filter bubble in the context of a course recommendation system in production at a public university. Most universities in the United States encourage students to explore developing interests while simultaneously advising them to adhere to course taking norms which progress them towards graduation. These competing objectives, and the stakes involved for students, make this context a particularly meaningful one for investigating real-world recommendation strategies. We introduce a novel modification to the skip-gram model applied to nine years of historic course enrollment sequences to learn course vector representations used to diversify recommendations based on similarity to a student's specified favorite course. This model, which we call multifactor2vec, is intended to improve the semantics of the primary token embedding by also learning embeddings of potentially conflated factors of the token (e.g., instructor). Our offline testing found this model improved accuracy and recall on our course similarity and analogy validation sets over a standard skip-gram. Incorporating course catalog description text resulted in further improvements. We compare the performance of these models to the system's existing RNN-based recommendations with a user study of undergraduates (N = 70) rating six characteristics of their course recommendations. Results of the user study show a dramatic lack of novelty in RNN recommendations and depict the characteristic trade-offs that make serendipity difficult to achieve.