Extending associative classifier to detect helpful online reviews with uncertain classes

DOI

10.2991/ifsa-eusflat-15.2015.160How to use a DOI?

Keywords

Review helpfulness, binary classification, class probability, associative classifier

Abstract

While online product reviews are valuable sources of information to facilitate consumers’ purchase decisions, it is deemed meaningful and important to distinguish helpful reviews from unhelpful ones for consumers fac-ing huge amounts of reviews nowadays. Thus, in light of review classification, this paper proposes a novel ap-proach to identifying review helpfulness. In doing so, a Bayesian inference is introduced to estimate the proba-bilities of the reviews belonging to respective classes, which differs from the traditional approach that only assigns class labels in a binary manner. Furthermore, an extended fuzzy associative classifier, namely GARCfp, is developed to train review helpfulness classification models based on review class probabilities and fuzzily partitioned review feature values. Finally, data experi-ments conducted on the reviews from amazon.com re-veal the effectiveness of the proposed approach.

Copyright

© 2015, 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  - Zunqiang Zhang
AU  - Yue Ma
AU  - Guoqing Chen
AU  - Qiang Wei
PY  - 2015/06
DA  - 2015/06
TI  - Extending associative classifier to detect helpful online reviews with uncertain classes
BT  - Proceedings of the 2015 Conference of the International Fuzzy Systems Association and the European Society for Fuzzy Logic and Technology
PB  - Atlantis Press
SP  - 1134
EP  - 1139
SN  - 1951-6851
UR  - https://doi.org/10.2991/ifsa-eusflat-15.2015.160
DO  - 10.2991/ifsa-eusflat-15.2015.160
ID  - Zhang2015/06
ER  -