Lib-SibGMU -- A University Library Circulation Dataset for Recommender Systems Developmen

TL;DR

Lib-SibGMU is an open university library dataset released under CC BY 4.0, enabling research on recommender systems, with benchmark results showing fastText as an effective vectorizer for user history.

Contribution

The paper introduces Lib-SibGMU, a new open dataset for library recommender systems, and benchmarks algorithms, highlighting fastText's effectiveness as a vectorizer.

Findings

FastText vectorizer delivers competitive results.

Benchmarking of major algorithms on the dataset.

Open-source dataset facilitates research in library recommender systems.

Abstract

We opensource under CC BY 4.0 license Lib-SibGMU - a university library circulation dataset - for a wide research community, and benchmark major algorithms for recommender systems on this dataset. For a recommender architecture that consists of a vectorizer that turns the history of the books borrowed into a vector, and a neighborhood-based recommender, trained separately, we show that using the fastText model as a vectorizer delivers competitive results.