KNNs of Semantic Encodings for Rating Prediction

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

This paper explores a novel application of textual semantic similarity to user-preference representation for rating prediction. The approach represents a user's preferences as a graph of textual snippets from review text, where the edges are defined by semantic similarity. This textual, memory-based approach to rating prediction enables review-based explanations for recommendations. The method is evaluated quantitatively, highlighting that leveraging text in this way outperforms both strong memory-based and model-based collaborative filtering baselines.

Original languageEnglish
Title of host publicationProceedings - 2023 IEEE 9th International Conference on Collaboration and Internet Computing, CIC 2023
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages82-91
Number of pages10
ISBN (Electronic)9798350339123
DOIs
Publication statusPublished - 1 Jan 2023
Event9th IEEE International Conference on Collaboration and Internet Computing, CIC 2023 - Atlanta, United States
Duration: 1 Nov 20233 Nov 2023

Publication series

NameProceedings - 2023 IEEE 9th International Conference on Collaboration and Internet Computing, CIC 2023

Conference

Conference9th IEEE International Conference on Collaboration and Internet Computing, CIC 2023
Country/TerritoryUnited States
CityAtlanta
Period1/11/233/11/23

Keywords

  • Graphs and net-works
  • Natural Language Processing
  • Web text analysis

Fingerprint

Dive into the research topics of 'KNNs of Semantic Encodings for Rating Prediction'. Together they form a unique fingerprint.

Cite this