Bias characterization, assessment, and mitigation in location-based recommender systems

P. Sánchez, A. Bellogín, L. Boratto

Data Mining and Knowledge Discovery Vol. 37, pp. 1885 - 1929

Summary:

Location-Based Social Networks stimulated the rise of services such as Location-based Recommender Systems. These systems suggest to users points of interest (or venues) to visit when they arrive in a specific city or region. These recommendations impact various stakeholders in society, like the users who receive the recommendations and venue owners. Hence, if a recommender generates biased or polarized results, this affects in tangible ways both the experience of the users and the providers’ activities. In this paper, we focus on four forms of polarization, namely venue popularity, category popularity, venue exposure, and geographical distance. We characterize them on different families of recommendation algorithms when using a realistic (temporal-aware) offline evaluation methodology while assessing their existence. Besides, we propose two automatic approaches to mitigate those biases. Experimental results on real-world data show that these approaches are able to jointly improve the recommendation effectiveness, while alleviating these multiple polarizations.

Spanish layman's summary:

En este artículo, analizamos cuatro sesgos distintos en el contexto de la recomendación de POIs y proponemos dos enfoques para mitigarlos. En el paper, demostramos que nuestras propuestas son capaces de mejorar la eficacia de las recomendaciones a la vez que alivian algunos de estos sesgos.

English layman's summary:

In this paper, we analyze four forms of polarization in the context of POI recommendation and we propose two approaches to mitigate them. In our experiments, we show that these approaches are able to jointly improve the recommendation effectiveness, while alleviating these multiple polarizations.

Keywords: POI recommendation · Bias mitigation · Polarization · Temporal evaluation

JCR Impact Factor and WoS quartile: 4,800 - Q2 (2022)

DOI reference: https://doi.org/10.1007/s10618-022-00913-5

Published on paper: September 2023.

Published on-line: February 2023.

Citation:
P. Sánchez, A. Bellogín, L. Boratto, Bias characterization, assessment, and mitigation in location-based recommender systems. Data Mining and Knowledge Discovery. Vol. 37, pp. 1885 - 1929, September 2023. [Online: February 2023]