Aspect-level opinion mining of online customer reviews

Crowd intelligence: Analyzing online product reviews for preference measurement

“…Prior studies have developed various opinion mining methods for this purpose using natural language processing or text mining techniques (Cambria, Schuller, Xia, & Havasi, 2013;Dai et al, 2015;Hu & Liu, 2004;Popescu & Etzioni, 2007;Wei, Chen, Yang, & Yang, 2010;Xu, Cheng, Tan, Liu, & Shen, 2013;Yan et al, 2015). Because we aim to measure aggregate consumer preferences from online product reviews, developing a new product feature extraction method is not the main focus of our study; instead, we employ and extend existing methods to support our product feature extraction.…”

Opinion Mining and Information Fusion: A survey

“…The work by Xueke et al [116] exhibits a new methodology to expand sentiment lexicons. The authors propose a generative topic model based in Latent Dirichlet Allocation (LDA) [117], to extract aspect-specific opinion words and their correspondent sentiment polarity.…”

“…Fusion of OM ResourcesEnhanced SenticNet With Affective Labels for Concept-Based Opinion Mining[70] 2013 Identifying Features in Opinion Mining Via Intrinsic and Extrinsic Domain Relevance[115] 2014 Aspect-Level Opinion Mining of Online Customer Reviews[116] 2013A Graph-Based Comprehensive Reputation Model: Exploiting the Social Extracting Opinion Targets and Opinion Words from Online Reviews Based on the Word Alignment Model [124] 2014 Mining Opinion and Sentiment for Stock Return Prediction Based on Web-Forum Messages [125] 2013 Aspect-Based Polarity Classification for SemEval Task 4…”

Incorporating Language Patterns and Domain Knowledge into Feature-Opinion Extraction

“…Li et al [7] introduced a dependency-sentiment-LDA, which relaxes the sentiment independent assumption and is an extension of a joint sentiment and topic model, Sentiment-LDA, which is also proposed by the authors. Xu et al [13] propose a generative topic model, the Joint Aspect/Sentiment (JAS) model, to jointly extract aspects and aspect-dependent sentiment lexicons from online customer reviews.…”