ConSent: Context-based sentiment analysis

被引：52

作者：

Katz, Gilad ^{[1
]}

Ofek, Nir ^{[1
]}

Shapira, Bracha ^{[1
]}

机构：

[1] Ben Gurion Univ Negev, Dept Informat Syst Engn, IL-84105 Beer Sheva, Israel

来源：

KNOWLEDGE-BASED SYSTEMS | 2015年 / 84卷

关键词：

Sentiment analysis; Context; Machine learning; Noisy data; CUSTOMER SATISFACTION; QUERY PERFORMANCE; LOYALTY;

D O I：

10.1016/j.knosys.2015.04.009

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

We present ConSent, a novel context-based approach for the task of sentiment analysis. Our approach builds on techniques from the field of information retrieval to identify key terms indicative of the existence of sentiment. We model these terms and the contexts in which they appear and use them to generate features for supervised learning. The two major strengths of the proposed model are its robustness against noise and the easy addition of features from multiple sources to the feature set. Empirical evaluation over multiple real-world domains demonstrates the merit of our approach, compared to state-of the art methods both in noiseless and noisy text. (C) 2015 Elsevier B.V. All rights reserved.

引用

页码：162 / 178

页数：17