【摘要】 基于中文网商评论,提出了一种产品质量薄弱环节分析方法,为企业提供产品质量改进方向。首先,开展数据预处理剔除无用信息,并利用结巴(Jieba)对评论分词和词性标注;其次,基于词性路径模板提取评论特征;然后,基于情感分析抽取负面评论,并利用语义相似性开展主题聚类,确定评论主题;最后,针对评论主题进行意见归纳,确定产品薄弱环节。此外,以手机评论为应用案例,证明了所提出的产品质量薄弱环节分析方法的有效性。更多还原

【Abstract】 This paper develops a framework of weak-link analysis for products based on the Chinese consumer reviews, which is helpful in guiding the quality improvement of products. The consumer reviews are firstly pre-processed to remove the useless information, and the Jieba is applied for the word segmentation and part of speech(POS) tagging. Then, the review features are extracted according to the POS path templates. Next, negative comments are collected by the sentiment analysis,and the opinion topics of those reviews are obtained by clustering according the semantic similarity.Finally, the weak-links of products are provided through the summarization of opinion topics. A real case study of mobile phone reviews is given to show the effectiveness of the proposed method.更多还原