电子商务产品评论的情感特征提取与关注点分析  

Feature Extraction and Emotion Analysis of E-commerce Product Reviews

作　　者：熊英[1] 蔡文成 XIONG Ying, CAI Wencheng(School of Computer Science, Hubei Univ. of Tech., Wuhan 430068, Chin)

机构地区：[1]湖北工业大学计算机学院,湖北武汉430068

出　　处：《湖北工业大学学报》2018年第4期75-77,81,共4页Journal of Hubei University of Technology

基　　金：国家自然科学基金(41204112);湖北工业大学博士启动基金(BSQD2016017)

摘　　要：为挖掘大量的电子商务产品评论数据隐藏的巨大潜在价值,构建产品评论数据库,提取特征-情感词集,对情感极性进行计算并对关注点进行挖掘。实验结果表明:该方法得到的产品热门特征标签与官网热门标签高度吻合,可以推广到其他中文在线网络评论。In order to explore the huge potential value of data hiding in a large number of e-commerce products,this paper conducts data mining around network reviews,builds a product review database to extract the feature-emotion word sets,calculating the emotional polarity and mining the focus.The experimental results show that the popular feature tags of the product are highly consistent with the official website hot tags.The method can be used for other Chinese online network reviews and has practical application value.

关 键 词：评论挖掘 依存句法 特征提取 情感分析 

分 类 号：TP391.1[自动化与计算机技术—计算机应用技术]