An effective model for aspect based opinion mining for social reviews

Abstract

Aspect-based opinion mining is a combination of Natural Language Processing (NLP) and Sentiment-Analysis. There are three main levels of sentiment-analysis; document level, sentence level and aspect level. In this study, we focus on aspect level sentiment analysis or aspect based opinion mining. Regarding this, several studies have been conducted; however, none of these previously reported studies have proven to be effective and intelligent for mining aspects using the critical factors. While analyzing, aspect based opinion mining, certain factors have to be considered, which are: implicit aspects, multi-aspect sentences, comparative sentences, domain or language adaptability and accuracy. Such factors help in analyzing an effective aspect based opinion mining model. In this paper, several models have been critically evaluated on aforementioned criteria. It has been observed that none of these models covers all the critical factors in aspect based opinion mining systems. Additionally, most of the models have been applied for products or services instead of social reviews. There is a growing need of effectively performing aspect based opinion mining on social networks data. This paper presents an effective model for aspect based opinion mining which cover most of the critical factors for effective opinion mining. However, the implementation of this model is beyond the scope of this paper.

DOI: 10.1109/ICDIM.2015.7381851

2 Figures and Tables

Cite this paper

@article{Mir2015AnEM, title={An effective model for aspect based opinion mining for social reviews}, author={Jibran Mir and Muhammad Usman}, journal={2015 Tenth International Conference on Digital Information Management (ICDIM)}, year={2015}, pages={49-56} }