Extracting Aspect Opinions from Reviews in Spanish for Aspect-based Recommendations

Opinions about item's aspects in user reviews may be a valuable source of information for improving Recommender Systems performance. Despite important advances in Natural Language Processing and Machine Learning fields that allow the extraction of such information from texts written in English,...

Full description

Saved in:
Bibliographic Details
Published inProceedings - International Conference of the Chilean Computer Science Society pp. 1 - 8
Main Authors Campos, Pedro G., Canales, Javier, Risso, Nathalie, Vidal, Christian
Format Conference Proceeding
LanguageEnglish
Published IEEE 15.11.2021
Subjects
Aspect Extraction
Aspect-based Recommender Systems
Computer science
Data mining
Machine learning
Natural language processing
Recommender systems
Spanish Reviews
Online AccessGet full text
ISSN2691-0632
DOI10.1109/SCCC54552.2021.9650415

Cover

More Information
Summary:Opinions about item's aspects in user reviews may be a valuable source of information for improving Recommender Systems performance. Despite important advances in Natural Language Processing and Machine Learning fields that allow the extraction of such information from texts written in English, there is still work to do in the case of texts in other languages. In this work, we adapt known unsupervised aspect extraction approaches to extract opinions from reviews written in Spanish. Our results show that the exploitation of aspects extracted automatically from reviews written in Spanish allow to improve considerably the top-k recommendation lists generated by Aspect-based Recommender Systems.
ISSN:2691-0632
DOI:10.1109/SCCC54552.2021.9650415