EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

An experimental study on the performance of collaborative filtering based on user reviews for large-scale datasets

Sumaia Al-Ghuribi, Shahrul Azman Mohd Noah, Mawal Mohammed

PeerJ Computer Science · 25.08.2023 · 9 · e1525

DOI: 10.7717/peerj-cs.1525 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PeerJ Computer Science, online erschienen am 25.08.2023. Verfasst von Sumaia Al-Ghuribi und 2 weiteren Autor:innen. Beteiligte Einrichtung: Center for Artificial Intelligence Technology, Universiti Kebangsaan Malaysia, Bangi, Selangor, Malaysia. Die Arbeit wurde bisher 14-mal zitiert (Crossref) und nennt 62 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: The Universiti Kebangsaan Malaysia.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Collaborative filtering (CF) approaches generate user recommendations based on user similarities. These similarities are calculated based on the overall (explicit) user ratings. However, in some domains, such ratings may be sparse or unavailable. User reviews can play a significant role in such cases, as implicit ratings can be derived from the reviews using sentiment analysis, a natural language processing technique. However, most current studies calculate the implicit ratings by simply aggregating the scores of all sentiment words appearing in reviews and, thus, ignoring the elements of sentiment degrees and aspects of user reviews. This study addresses this issue by calculating the implicit rating differently, leveraging the rich information in user reviews by using both sentiment words and aspect–sentiment word pairs to enhance the CF performance. It proposes four methods to calculate the implicit ratings on large-scale datasets: the first considers the degree of sentiment words, while the second exploits the aspects by extracting aspect-sentiment word pairs to calculate the implicit ratings. The remaining two methods combine explicit ratings with the implicit ratings generated by the first two methods. The generated ratings are then incorporated into different CF rating prediction algorithms to evaluate their effectiveness in enhancing the CF performance. Evaluative experiments of the proposed methods are conducted on two large-scale datasets: Amazon and Yelp. Results of the experiments show that the proposed ratings improved the accuracy of CF rating prediction algorithms and outperformed the explicit ratings in terms of three predictive accuracy metrics.

Schlagwörter

Stichwörter der Autor:innen

Collaborative filteringRecommender systemsSentiment analysisUser reviews

Autor:innen und Institutionen

  • Center for Artificial Intelligence Technology, Universiti Kebangsaan Malaysia, Bangi, Selangor, Malaysia.
  • Department of Computer Science, Faculty of Applied Sciences, Taiz University, Taiz, Yemen.
  • Department of Software Engineering, Prince Sattam Bin Abdulaziz University, Alkharj, Saudi Arabia.

Förderung

  • The Universiti Kebangsaan Malaysia

Zitieren

APA

Al-Ghuribi, S., Mohd Noah, S. A., & Mohammed, M. (2023). An experimental study on the performance of collaborative filtering based on user reviews for large-scale datasets. PeerJ Computer Science, 9, e1525. https://doi.org/10.7717/peerj-cs.1525

Vancouver

Al-Ghuribi S, Mohd Noah SA, Mohammed M. An experimental study on the performance of collaborative filtering based on user reviews for large-scale datasets. PeerJ Computer Science. 2023;9:e1525. doi:10.7717/peerj-cs.1525

BibTeX
@article{AlGhuribi2023,
  author = {Al-Ghuribi, Sumaia and Mohd Noah, Shahrul Azman and Mohammed, Mawal},
  title = {An experimental study on the performance of collaborative filtering based on user reviews for large-scale datasets},
  journal = {PeerJ Computer Science},
  year = {2023},
  volume = {9},
  pages = {e1525},
  doi = {10.7717/peerj-cs.1525}
}
Kostenlos starten →