《计算机应用研究》|Application Research of Computers

面向高校学生微博的跨粒度情感分析

Cross-grained sentiment analysis oriented to college student microblog

免费全文下载 (已被下载 次)  
获取PDF全文
作者 刘丽,岳亚伟
机构 山西农业大学 软件学院,山西 太谷 030801
统计 摘要被查看 次,已被下载
文章编号 1001-3695(2019)06-004-1618-05
DOI 10.19734/j.issn.1001-3695.2017.12.0815
摘要 传统的微博情感分析通常会忽略不带感情色彩的情感词对微博情感的影响,并缺乏对复杂句式的分析。因此提出了一种结合条件随机场(conditional random filed,CRF)和复杂句式的跨粒度情感分析方法。该方法在CRF模型的基础上,融合复杂句式特征和语义依存特征,对学生微博进行细粒度情感分析,识别出微博文本中的情感要素。在此基础上,通过基于复杂句式的粗粒度情感分析方法分析微博文本的情感倾向,实现对学生总体情感倾向的跨粒度分析。实验结果显示,跨粒度情感分析方法的提出,使得情感要素识别的综合准确率达到了88%左右,微博情感分析的综合准确率达到了87%左右。比起传统的情感分析方法,准确率更高,分类效果更好。
关键词 高校学生微博; 条件随机场; 复杂句式; 跨粒度; 情感分析
基金项目 青年科技创新基金资助项目(2017016)
本文URL http://www.arocmag.com/article/01-2019-06-004.html
英文标题 Cross-grained sentiment analysis oriented to college student microblog
作者英文名 Liu Li, Yue Yawei
机构英文名 School of Software,Shanxi Agricultural University,Taigu Shanxi 030801,China
英文摘要 Traditional sentiment analysis of micro-blog often ignore the influence of sentiment words without sentimental color on micro-blog sentiment, and lack of analysis for complex sentence. To solve the problem, this paper proposed a method of cross-grained sentiment analysis based on conditional random filed and complex sentence, which fused complex sentence and semantic dependency features on the basis of CRF. It could identify sentiment elements by analyzing microblog sentiment in fine-grained. It used the method of coarse-grained sentiment analysis based on complex sentence analyze sentimental tendency of student microblog. Finally, the experimental results show that the accuracy on sentiment elements can reach 88%, furthermore, the accuracy of microblog sentimental tendency can reach 87%. Compare to traditional method, the proposed method has higher accuracy and better performance.
英文关键词 college student microblog; conditional random filed(CRF); complex sentence; cross-grained; sentiment analysis
参考文献 查看稿件参考文献
 
收稿日期 2017/12/23
修回日期 2018/2/22
页码 1618-1622
中图分类号 TP391.1
文献标志码 A