A Novel Approach to Recommender System Based on Aspect-level Sentiment Analysis

DOI

10.2991/nceece-15.2016.259How to use a DOI?

Keywords

recommendation system; aspect-based sentiment analysis; opinion mining

Abstract

Traditional recommendation methods usually focus on utilizing user’s features obtained from structured behavior information, which only contains coarse grained user interests. This paper presents a novel approach to introduce aspect-based sentiment analysis (or opinion mining) into recommender systems. By extracting aspects from the user’s review text and determining the sentiment orientation of each aspect, we build the user and product model focusing on mining user’s interests and the practical evaluations about the product. Experimental results show that the recommendation utilizing this model conduces to better performance than common traditional recommendation methods.

Copyright

© 2016, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Yu Zhang
AU  - RuiFang Liu
AU  - AoDong Li
PY  - 2015/12
DA  - 2015/12
TI  - A Novel Approach to Recommender System Based on Aspect-level Sentiment Analysis
BT  - Proceedings of the 2015 4th National Conference on Electrical, Electronics and Computer Engineering
PB  - Atlantis Press
SP  - 1453
EP  - 1458
SN  - 2352-5401
UR  - https://doi.org/10.2991/nceece-15.2016.259
DO  - 10.2991/nceece-15.2016.259
ID  - Zhang2015/12
ER  -