东北林业大学本科生毕业论文模板可研报告.doc

毕 业 论 文 用户评论中产品特征的挖掘方法研究 学生姓名： 李焱 专业班级： 信息管理与信息系统2011级1班 指导教师： 王名扬 副教授 学 院： 信息与计算机工程学院 2015年6月  用户评论中产品特征的挖掘方法研究重要的意义频繁项集作为集合结合剪枝、冗余性剪枝以及形容词邻近度剪枝算法对候选产品特征进行筛选过滤，以提高产品特征的挖掘性能，得到更加准确的产品特征集。通过在三种不同商品的用户评论语料进行实验验证，发现基于形容词邻近度剪枝的方法的引入购买商品提供参考，同时，也为生产商及代销商了解用户关心的产品特征，更好的促进产品销售提供帮助。 关键词　产品特征；文本挖掘；关联规则；剪枝算法  Research on the Approaches of Mining Product Features from Customer Reviews Abstract At present, more and more people buy things on the Internet with the good development of Internet in China. At the same time, customer reviews become important references of customer when they buy things. Because the number of popular products’ reviews is more than 10 thousand, it is difficult for customers to mining worthwhile information in reviews quickly. Therefore, the research on the approaches of mining product features from customer reviews is significant. The paper brings in Apriori association rule mining algorithm which is used to discover internal associations between items. Mining frequent item set as product features in customers’ reviews which has been segmented. After that, in order to diminish meaningless and redundant features, the paper conducts the adjacent rule pruning, redundancy pruning and the adjective adjacent rule pruning which is newly added to filter from the candidate product features. The approach improves the mining algorithm performance and gets more correct product feature set. Then the paper does experiments in three different products’ reviews, finding the adding of the adjective adjacent rule pruning algorithm provides better mining results. The better results can provide a reference for customers to purchase merchandise, and provide producers and dealers with information that what product features are more concerned by customers so as to propel the selling of products. Keywords　 product features; text mining; association rule; pruning algorithm 目录 摘要 Abstract 1 前言 1 1.1 研究背景和意义 1 1.1.1 研究背景 1 1.1.2 研究意义 1 1.2 国内外研究现