| 本文已被：浏览 3864次 下载 6355次 |
码上扫一扫！ |
|
|
| 基于社交关系的微博主题情感挖掘 |
|
黄发良1,2,3, 于戈1,4, 张继连5, 李超雄2, 元昌安6, 卢景丽7
|
|
1.东北大学 计算机科学与工程学院, 辽宁 沈阳 110819;2.福建师范大学 软件学院, 福建 福州 350108;3.福建省公共服务大数据挖掘与应用工程技术研究中心, 福建 福州 350108;4.医学影像计算教育部重点实验室(东北大学), 辽宁 沈阳 110819;5.广西财经学院 信息与统计学院, 广西 南宁 530003;6.广西师范学院 计算机与信息工程学院, 广西 南宁 530023;7.Grasslands Research Centre, Palmerston North, 11008, New Zealand
|
|
| 摘要: |
| 微博情感分析是社交媒体挖掘中的重要任务之一，在个性化推荐、舆情分析等方面具有重要的理论和应用价值.挖掘性能良好且可同步进行文档主题分析与情感分析的主题情感模型，近年来在以微博为代表的社交媒体情感分析中备受关注.然而，绝大多数现有主题情感模型都只简单地假设不同微博的情感极性是互相独立的，这与微博生态的现实状况不相一致，从而导致这些模型无法对用户的真实情感进行有效建模.基于此，综合考虑了微博用户相互关联的事实，提出了基于LDA和微博用户关系的主题情感模型SRTSM（social relation topic sentiment model）.该模型在LDA中加入情感层与微博用户关系参数，利用微博用户关系与微博主题学习微博的情感极性.针对新浪微博真实数据集上的大量实验结果表明：与代表性算法JST，Sentiment-LDA及DPLDA相比较，SRTSM模型能够对用户真实情感与讨论主题进行更加有效的分析建模. |
| 关键词: 情感分析 微博情感分析 主题情感模型 社交关系 社会媒体处理 |
| DOI：10.13328/j.cnki.jos.005157 |
| 分类号:TP311 |
| 基金项目:国家重点基础研究发展计划（973）（2012CB316201）；国家自然科学基金（61433008，61363009，61363037）；福建省教育厅K类科技项目（JK2016007） |
|
| Mining Topic Sentiment in Micro-Blogging Based on Micro-Blogger Social Relation |
|
HUANG Fa-Liang1,2,3, YU Ge1,4, ZHANG Ji-Lian5, LI Chao-Xiong2, YUAN Chang-An6, LU Jing-Li7
|
|
1.School of Computer Science and Engineering, Northeastern University, Shenyang 110819, China;2.Faculty of Software, Fujian Normal University, Fuzhou 350108, China;3.Fujian Engineering Research Center of Public Service Big Data Mining and Application, Fuzhou 350108, China;4.Key Laboratory of Medical Image Computing of Ministry of Education(Northeastern University), Shenyang 110819, China;5.School of Information and Statistics, Guangxi University of Finance and Economics, Nanning 530003, China;6.College of Computer and Information Engineering, Guangxi Teachers Education University, Nanning 530023, China;7.Grasslands Research Centre, Palmerston North, 11008, New Zealand
|
| Abstract: |
| Sentiment analysis in micro-blogging is an important task in mining social media, and has important theoretical and application value in personalized recommendation and public opinion analysis. Topic sentiment models have attracted much attention due to their good performance and ability of synchronized topic and the sentiment analysis in micro-blogs. However, most existing models simply assume that topic sentiment distributions of different micro-blogs are independent, which is contrary to the realistic status in micro-blogging and thus further leads to unsatisfactory modeling of micro-blogger's true sentiment. To address the issues, a probabilistic model, SRTSM (social relation topic sentiment model) is proposed. The new model introduces sentiment and micro-blogger social relation into LDA inference framework and achieves synchronized detection of sentiment and topic in micro-blogging. Extensive experiments on Sina Weibo show that SRTSM outperforms state-of-the-art unsupervised approaches including JST, SLDA and DPLDA significantly in terms of sentiment classification accuracy. |
| Key words: sentiment analysis microblog sentiment analysis topic sentiment model social relation social media processing |
