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

一种改进的带有情感信息的词向量学习方法

Improved approach of word vector learning via sentiment information

免费全文下载 (已被下载 次)  
获取PDF全文
作者 张巍,史文鑫,刘冬宁,滕少华
机构 广东工业大学 计算机学院,广州 510006
统计 摘要被查看 次,已被下载
文章编号 1001-3695(2017)08-2287-04
DOI 10.3969/j.issn.1001-3695.2017.08.010
摘要 词语的情感信息对于情感分析任务至关重要,现有大多数基于词向量的无监督学习方法只能对词语的语法语境建模,但忽略了词语的情感信息。针对这一问题,提出了一种结合监督学习和非监督学习的词向量学习方法,既能够获得词语的语义信息又能够获得情感内容。在相关实验中,对词向量分析作了直观的举例对比,并将该方法用于情感分类任务中,通过引入新的评论数据集对该方法进行验证。实验结果表明,融合了语义与情感的词向量方法效果良好,能更为精确地对情感信息进行分类、更为客观地对用户信息进行评价,助力社交网络良性发展。
关键词 情感分析;词向量;语义;分类
基金项目 国家自然科学基金资助项目(61402118)
广东省科技计划资助项目(2013B090200017,2013B010401029,2013B010401034,2015B090901016)
本文URL http://www.arocmag.com/article/01-2017-08-010.html
英文标题 Improved approach of word vector learning via sentiment information
作者英文名 Zhang Wei, Shi Wenxin, Liu Dongning, Teng Shaohua
机构英文名 SchoolofComputer,GuangdongUniversityofTechnology,Guangzhou510006,China
英文摘要 The sentiment information is crucial to sentiment analysis task. In learning continuous word representation, typical existing unsupervised algorithms only model the syntactic context of words but fail to capture the sentiment information of text. To solve this problem, this paper presented a hybrid method to capture both semantic information and sentiment content in word vector via unsupervised and supervised learning. By applying this method into sentiment classification task, this paper also compares the method from other different methods. Experiments results show that the proposed method can achieve a better result and improve classification performance effectively, which can evaluate clients’ information kindly and objectively and contribute to other text classification tasks in social network.
英文关键词 sentiment analysis; word vector; semantic; classification
参考文献 查看稿件参考文献
  [1] 张林, 钱冠群, 樊卫国, 等. 轻型评论的情感分析研究[J] . 软件学报, 2014, 25(12):2790-2807.
[2] Pang Bo, Lee L. Opinion mining and sentiment analysis[J] . Foundations and Trends in Information Retrieval, 2008, 2(1-2):1-135.
[3] Bengio Y, Courville A, Vincent P. Representation learning:a review and new perspectives[J] . IEEE Trans on Pattern Analysis and Machine Intelligence, 2013, 35(8):1798-1828.
[4] Socher R, Perelygin A, Wu J, et al. Recursive deep models for semantic compositionality over a sentiment treebank[C] //Proc of Confe-rence on Empirical Methods in Natural Language Processing. 2013:1631-1642.
[5] Yessenalina A, Cardie C. Compositional matrix-space models for sentiment analysis[C] //Proc of Conference on Empirical Methods in Natural Language Processing. 2011:172-182.
[6] Collobert R, Weston J, Bottou L. Natural language processing (almost) from scratch[J] . Journal of Machine Learning Research, 2011, 12(1):2493-2537.
[7] Mikolov T, Chen K, Corrado G. Efficient estimation of word representations in vector space[J/OL] . 2013. https://arxiv. org/pdf/1301. 3781v3. pdf.
[8] Tang Duyu, Wei Furu, Yang Nan, et al. Learning sentiment-specific word embedding for Twitter sentiment classification[C] //Proc of Meeting of the Association for Computational Linguistics. Stroudsburg:Association for Computational Linguistics, 2014:1555-1565.
[9] Zheng Xiaoqing, Chen Hanyang, Xu Tianyu. Deep learning for Chinese word segmentation and POS tagging[C] //Proc of Conference on Empirical Methods in Natural Language Processing. 2013:647-657.
[10] Bengio Y, Ducharme R, Vincent P. A neural probabilistic language model[J] . Journal of Machine Learning Research, 2003(3):1137-1155.
[11] Pang Bo, Lee L, Vaithyanathan S. Thumbs up? Sentiment classification using machine learning techniques[C] //Proc of Conference on Empirical Methods in Natural Language Processing. 2002:79-86.
[12] Turney P. Thumbs up or thumbs down? Semantic orientation applied to unsupervised classification of reviews[C] //Proc of Meeting of the Association for Computational Linguistics. Stroudsburg:Association for Computational Linguistics, 2002:417-424.
[13] Bespalov D, Bai Bing, Qi Yanjun. Sentiment classification based on supervised latent n-gram analysis[C] //Proc of the 20th ACM International Conference on Information and Knowledge Management. New York:ACM Press, 2011:375-382.
[14] Bespalov D, Qi Yanjun, Bai Bing. Sentiment classification with supervised sequence embedding[C] //Proc of European Conference on Machine Learning and Knowledge Discovery in Databases. Berlin:Springer, 2012:159-174.
[15] Maas A, Daly R, Pham P. Learning word vectors for sentiment analysis[C] //Proc of Meeting of the Association for Computational Linguistics. Strudsburg:Association for Computational Linguistics, 2011:142-150.
[16] Pang Bo, Lee L. A sentimental education:sentiment analysis using subjectivity summarization based on minimum cuts[C] //Proc ofthe 42nd Annual Meeting on Associations for Computational Linguistics. Strudsburg:Association for Computational Linguistics, 2004:271-278.
收稿日期 2016/6/5
修回日期 2016/7/20
页码 2287-2290
中图分类号 TP391.1
文献标志码 A