English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Collaborative filtering based algorithms, including Recurrent Neural Networks(RNN), tend towards predicting a perpetuation of past observed behavior. In arecommendation context, this can lead to an overly narrow set of suggestionslacking 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 bubblein the context of a course recommendation system in production at a publicuniversity. Most universities in the United States encourage students toexplore developing interests while simultaneously advising them to adhere tocourse taking norms which progress them towards graduation. These competingobjectives, and the stakes involved for students, make this context aparticularly meaningful one for investigating real-world recommendationstrategies. We introduce a novel modification to the skip-gram model applied tonine years of historic course enrollment sequences to learn course vectorrepresentations used to diversify recommendations based on similarity to astudent's specified favorite course. This model, which we call multifactor2vec,is intended to improve the semantics of the primary token embedding by alsolearning embeddings of potentially conflated factors of the token (e.g.,instructor). Our offline testing found this model improved accuracy and recallon 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-basedrecommendations with a user study of undergraduates (N = 70) rating sixcharacteristics of their course recommendations. Results of the user study showa dramatic lack of novelty in RNN recommendations and depict the characteristictrade-offs that make serendipity difficult to achieve.

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