摘要近年来，在网络上进行购物活动已经成为人们日常生活的重要部分，在使用 产品之后顾客往往被要求填写商品评论以供他人参考。本项研究的目的就在于挖 掘并且总结给定商品的所有用户评论，并以结构化的形式呈现，让顾客和生产商 们能够简单明了的获得所需要的商品的评价信息。不同于以往的文本总结，我们 的总结方法是基于所挖掘出的商品特征的，只对评论中提到的商品特征进行总结 并以结构化的形式展现。工作流程如下:(1)挖掘那些受到顾客评价的商品特征；(2) 识别出评论的观点语句并且判定每一个句子是肯定的还是否定的；(3)总结结果并 以结构化形式进行展现。最后我们进行了实验，通过对网上商城的商品评论数进 行总结对比来验证我们的评价系统的有效性。68523

毕业论文关键词 文本挖掘 情感分类 商品评论 特征抽取

Title       Mining and Summarizing Customer Reviews on the E-commerce Websites

Abstract

As e-commerce is becoming more and more popular recent years,people buying products on the Web are often asked to review the products that they have purchased for others to reference. In this research,we aim to mine and to summarize all the customers reviews of a product and show them in chats for merchants and customers to get the information of products easily.This summarization task is different from traditional text summarization because wo only mine the features of the product on which the customers have expressed their opinions and we show the results in chats. Our task is performed in three steps:(1)mining product features that have been commented on by customers;(2)identifying opinion sentences in each review and deciding whether each opinion sentences is positive or negative;(3)summarizing the results.Finally,Our experimental results using reviews of a number of a products sold online demonstrate the effectiveness of the techniques.

Keywords Text mining, Sentiment classification, Products’ reviews, Feature extraction

目 次

1 引言 1

1．1 研究背景 1

1．2 国内外研究现状 2

1．3 研究目的 3

1.4 相关工作介绍 4

1.5 研究目标 6

1.6 研究内容 6

2 系统设计与实现 7

2．1 原评论的获取 8

2．2 分词 11

2．3 属性特征统计 14

2．4 基于 Apriori、word2vec、LDA 三大算法的混合模型特征聚类算法 18

2．5 情感语义分析 面向电商评论的数据挖掘技术与系统:http://www.751com.cn/jisuanji/lunwen_77086.html