| 基于LDA及语义相似度的商品评论情感分类研究 |
| |
| 引用本文： | 曾寰,龙小建,刘华. 基于LDA及语义相似度的商品评论情感分类研究[J]. 井冈山大学学报(自然科学版), 2019, 40(4): 46-51 |
| |
| 作者姓名： | 曾寰 龙小建 刘华 |
| |
| 作者单位： | 井冈山大学电子与信息工程学院,江西,吉安 343009;井冈山大学继续教育与培训学院,江西,吉安 343009 |
| |
| 基金项目： | 吉安市社会科学研究项目（18GH113） |
| |
| 摘 要： | 提出一种结合LDA及语义相似度的商品评论情感分类方法。该方法首先使用LDA对商品语料库建模,获取文档-主题矩阵;人工选择k对褒义词、贬义词,基于HowNet语义相似度计算主题(评价对象+观点内容)与各个褒义词和贬义词的相似度,达到对观点词极性判断,计算文本观点词情感极性的加权和作为文本的情感极性。实验表明,与基于向量空间的SVM分类方法相比,该情感分类方法在分类指标上表现更好。
|
| 关 键 词： | 情感分类 LDA 语义相似度 观点词 |
| 收稿时间： | 2019-01-18 |
| 修稿时间： | 2019-05-10 |
SENTIMENT CLASSIFICATION RESEARCH IN PRODUCT REVIEWS BASED ON LDA AND SEMANTIC SIMILARITY |
| |
| ZENG Huan,LONG Xiao-jian and LIU Hua. SENTIMENT CLASSIFICATION RESEARCH IN PRODUCT REVIEWS BASED ON LDA AND SEMANTIC SIMILARITY[J]. Journal of Jinggangshan University(Natural Sciences Edition), 2019, 40(4): 46-51 |
| |
| Authors: | ZENG Huan LONG Xiao-jian LIU Hua |
| |
| Affiliation: | School of Electronics and Information engineering;Jinggangshan University, Ji''an, Jiangxi 343009, China,School of Continuing Education, Jinggangshan University, Ji''an, Jiangxi 343009, China and School of Electronics and Information engineering;Jinggangshan University, Ji''an, Jiangxi 343009, China |
| |
| Abstract: | A product reviews classification method based on LDA and semantic similarity is proposed, The method firstly uses LDA to model the reviews corpus and get the review-topic matrix. Artificially, it selects k positive and negative words and use "HowNet" semantic similarity to calculate the similarity of opinion content words with each positive and negative words to get the polarity of opinion word. The weighted polarity sum of words will be the polarity of the review. The experiment result shows, compared with SVM classification method based on vector space text representation, the proposed method works better in classification index. |
| |
| Keywords: | sentiment classification LDA semantic similarity opinion word |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
| 点击此处可从《井冈山大学学报(自然科学版)》浏览原始摘要信息 |
|
点击此处可从《井冈山大学学报(自然科学版)》下载免费的PDF全文 |
|
