ABSTRACT
With the vigorous development of e-commerce, reviews of online commodity has become an important data source for enterprises to improve the quality of goods and service. These comments contain the emotional tendencies of users on all aspects of a product. By performing a sentiment analysis of it, can not only help sellers understand the advantages and disadvantages of their products, but also provide data support for potential buyers'purchase decisions. This paper presents a new method of commodity attribute clustering based on combination neural networks. and the sentiment analysis of commodity reviews based on Word2vec, through Word2vec computing semantic similarity, establishing sentiment dictionary and using affective Dictionary to classify the test text. The experiment proves the validity and accuracy of the method in the Internet product reviews.
- Zhang Ziqiong, ye Qiang, Li Yijun. Overview of Internet product reviews sentiment analysis {J}. management science. 2010, 13(6): 84--96Google Scholar
- Lee S, Choeh J Y. Predicting the helpfulness of online reviews Using multilayer perceptron neural networks{J}. Expert Systems with Applications, 2014, 41(6): 3041--3046. Google ScholarDigital Library
- Cao Q, Duan W, Gan Q. Exploring determinants of voting for the "helpfulness" of online user reviews: A text mining approach{J}. Decision Support Systems, 2010,50(2):51l-521. Google ScholarDigital Library
- Hao Yuanyuan, Ye Qiang, Li Yijun. Research on the Factors Influencing the Usefulness of Online Review Based on Film Criticism Evidence {J}.Journal of Management Appreciation, 2010, 13 (8): 78--88.Google Scholar
- Chen Jiangtao. Zhang Jinlong, Zhang Yajun. Research on the Influencing Factors of the Usefulness of Online Comments on Commodities: Based on the Text Semantic Perspective {J}. Library and Information Work, 2012, 56 (10): 119--123.Google Scholar
- YiJ,NasukawaT,BunescuR,eta1.Sentimentanalyzer:Extracting sentiments about a given topic using natural language processing techniques {C}// Third IEEE International Confe-renceon Data Mining, 2003(ICDM2003). IEEE, 2003: 427--434 Google ScholarDigital Library
- Xiaoli Tang, Baiyu, Guiping Zhang et al. A Clustering Oriented Text modeling method {J}.Journal of Shanxi University (Nature and Social Sciences), 2014, 37 (4): 595--600.Google Scholar
- Yuan Cheng-xiang, Zhuang Yi, Li Hao-hong. Semantic Based Chinese Sentence Sentiment Analysis{C}// 2011 Eighth International Conference on Fuzzy Systems and Knowledge Discovery.IEEE.201 l:2099--2103Google Scholar
- Research on the Validity of Online Commodity Reviews Based on Word2vec
Recommendations
Research on the Construction of Sentiment Dictionary Based on Word2vec
ACAI '18: Proceedings of the 2018 International Conference on Algorithms, Computing and Artificial IntelligenceThe construction of sentiment dictionary is one of the most important basic tasks in the field of text mining. At the moment, there is no universal and complete sentiment dictionary in the field of text mining. In this study, a method of constructing ...
Chinese comments sentiment classification based on word2vec and SVMperf
We achieve similar features clustering using word2vec.A method for sentiment classification based on word2vec and SVMperf is proposed.Word2vec can extract deep semantic features between words.SVMperf trains faster and predicts more accurate than other ...
Mining and summarizing customer reviews
KDD '04: Proceedings of the tenth ACM SIGKDD international conference on Knowledge discovery and data miningMerchants selling products on the Web often ask their customers to review the products that they have purchased and the associated services. As e-commerce is becoming more and more popular, the number of customer reviews that a product receives grows ...
Comments