Fine-grained opinion mining : An application of online review analysis in the express industry

Citations Over Time

Abstract

Opinion mining of online review can identify the key aspects of consumer focusing, thus can provide the decision basis for business administrators to improve customer services. The paper proposes an opinion mining framework of online review, which uses review sentences as input, and fulfills two kinds of analysis tasks: one is clustering analysis, the other is sentiment classification. For clustering analysis, we adopt VC-Word2vec (Voting Based on Clustering Word2vec) to identify the aspects of online reviews. For Sentiment classification, we extract features of review sentences based on ED-TextRank (TextRank Based on Sentiment Dictionary), and by identifying sentimental words and increasing the weight of them, the accuracy of sentiment classification can be improved. As an application, we fulfill the online review analysis for express industry to verify the effectiveness and accuracy of the framework.

Related Papers

• → Support vector machines and Word2vec for text classification with semantic features(2015)457 cited
• → Review on Word2Vec Word Embedding Neural Net(2020)73 cited
• → Weighted word2vec based on the distance of words(2017)23 cited
• → LSTM and Bi-LSTM Models For Identifying Natural Disasters Reports From Social Media(2023)8 cited
• → Analyzing Semantic Relations of Word Vectors trained by The Word2vec Model(2019)1 cited