Incorporating Impressions to Graph-Based Recommenders
Entity
UAM. Departamento de Ingeniería InformáticaPublisher
CEUR Workshop ProceedingsDate
2023-09-18Citation
RecSys 2023. CEUR, Singapore, September 18-22, 2023ISSN
1613-0073Subjects
Recommender Systems; Impression; Slate; Exposure; Taxonomy; InformáticaRights
© 2023 Copyright for this paper by its authors.Abstract
Graph-based approaches have become an effective strategy to model the users’ preferences in recommender systems accurately; however, despite their excellent recommendation quality, the literature still needs to incorporate impressions
(past recommendations) into existing approaches. By their definition, impressions contain the selection of the most relevant items for the user; enriching the users’ profiles with those items may lead to higher-quality recommendations. In this
work, we propose and empirically explore the effectiveness of two approaches that include impressions into graph-based recommenders. Both approaches are simple yet extensible as they do not change the definitions of the recommenders; but transform their main data structure: the graph’s adjacency matrix. The results of our experiments suggest that our approaches may improve the recommendation quality of graph-based recommenders that do not use impressions; however, we also find that beyond-accuracy metrics may become negatively affected.
Files in this item
Google Scholar:Pérez Maurera, Fernando B.
-
Ferrari Dacrema, Maurizio
-
Castells, Pablo
-
Cremonesi, Paolo
This item appears in the following Collection(s)
Related items
Showing items related by title, author, creator and subject.