[1]杨玉娟,袁欢欢,王永利.针对评论文本的情感分析方法[J].南京理工大学学报(自然科学版),2019,43(03):280-285.
 Yang Yujuan,Yuan Huanhuan,Wang Yongli.Sentiment analysis method for comment text[J].Journal of Nanjing University of Science and Technology,2019,43(03):280-285.
点击复制

针对评论文本的情感分析方法()
分享到:

《南京理工大学学报》(自然科学版)[ISSN:1005-9830/CN:32-1397/N]

卷:
43卷
期数:
2019年03期
页码:
280-285
栏目:
出版日期:
2019-06-30

文章信息/Info

Title:
Sentiment analysis method for comment text
文章编号:
1005-9830(2019)03-0280-06
作者:
杨玉娟1袁欢欢2王永利2
1.南京图书馆,江苏 南京 210018; 2.南京理工大学 计算机科学与工程学院,江苏 南京 210094
Author(s):
Yang Yujuan1Yuan Huanhuan2Wang Yongli2
1.Nanjing Library,Nanjing 210018,China; 2.School of Computer Science and Engineering,Nanjing University of Science and Technology,Nanjing 210094,China
关键词:
评论文本 情感分析 术语频率-逆文档频率 长期短期记忆 注意力
Keywords:
comment text sentiment analysis term frequency-inverse document frequency long short-term memory attention
分类号:
TP391
摘要:
为了克服传统基于机器学习的情感分析算法依赖手工建立情感词典、需要进行人工干预的缺点,该文提出1种加权word2vec注意力长短记忆网络(WWAL)情感分析模型。突出评论文本中关键词的作用,在word2vec的基础上引入了术语频率-逆文档频率(TFIDF)算法形成词向量,同时在长期短期记忆(LSTM)网络模型中加入了注意力机制。在标准数据集上的实验证明,该文 WWAL模型的查准率、召回率和F1指标等实验衡量指标均优于传统机器学习方法。
Abstract:
A weighted word2vec-attention long short-term memory(WWAL)emotion analysis model is proposed to overcome the shortcomings of traditional machine learning-based sentiment analysis algorithms of relying on manual establishment of emotional dictionary and manual intervention. The role of keywords in the comment text is highlighted. Word vectors based on word2vec are formed by introducing the term frequency-inverse document frequency(TFIDF)algorithm. An attention mechanism is introduced in the long short-term memory(LSTM)networks model. Experimental results on the standard dataset show the WWAL model is better than the traditional machine learning method in terms of precision,recall and F1 indicators.

参考文献/References:

[1] 缪弘,张文强. 基于深度卷积神经网络的视觉SLAM去模糊系统[J]. 中兴通讯技术,2018,24(5):62-66.
Miao Hong,Zhang Wenqiang. Deep convolutional neural network for visual SLAM deblurring[J]. ZTE Technology Journal,2018,24(5):62-66.
[2]Li Minjia,Xie Lun,Wang Zhiliang,et al. Emotion and cognitive reappraisal based on GSR wearable sensor[J]. ZTE Communications,2017,15(S2):18-22.
[3]Mnih V,Heess N,Graves A,et al. Recurrent models of visual attention[J]. Advances in Neural Information Processing Systems,2014,3(6):2204-2212.
[4]Bahdanau D,Cho K,Bengio Y. Neural machine translation by jointly learning to align and translate[DB/OL]. https://arxiv. org/pdf/1409. 0473,2019-05-07.
[5]Rockt?schel T,Grefenstette E,Hermann K M,et al. Reasoning about entailment with neural attention[DB/OL]. https://arxiv. org/pdf/1509. 06664,2019-05-07.
[6]Rush A M,Chopra S,Weston J. A neural attention model for abstractive sentence summarization[DB/OL]. https://arxiv. org/pdf/1509. 00685,2019-05-07.
[7]Hermann K M,KoDcˇiskDy’ T,Grefenstette E,et al. Teaching machines to read and comprehend[DB/OL]. https://arxiv. org/pdf/1506. 03340. pdf,2019-05-07.
[8]Bengio Y,Ducharme R,Vincent P. A neural probabilistic language model[J]. Journal of Machine Learning Research,2003,3(2):1137-1155.
[9]Mnih A,Hinton G E. A scalable hierarchical distributed language model[C]//Proceeding NIPS’08 Proceedings of the 21st International Conference on Neural Information Processing Systems. Vancouver Canada:Curran Associates Inc.,2009:1081-1088.
[10]Mikolov T,Chen K,Corrado G,et al. Efficient estimation of word representations in vector space[DB/OL]. https://arxiv. org/pdf/1301. 3781. pdf,2019-05-07.
[11]Taboada M,Brooke J,Tofiloski M. Lexicon-based methods for sentiment analysis[J]. Computational Linguistics,2011,37(2):267-307.
[12]Bollegala D,Weir D,Carroll J. Using multiple sources to construct a sentiment sensitive thesaurus for cross-domain sentiment classification[C]//Meeting of the Association for Computational Linguistics:Human Language Technologies. Portland,USA:Association for Computational Linguistics,2011:132-141.
[13]李寿山,李逸薇,黄居仁,等. 基于双语信息和标签传播算法的中文情感词典构建方法[J]. 中文信息学报,2013,27(6):75-82.
Li Shoushan,Li Yiwei,Huang Juren,et al. Chinese emotional dictionary construction method based on bilingual information and label propagation algorithm[J]. Journal of Chinese Information Processing,2013,27(6):75-82.
[14]王文,王树锋,李洪华. 基于文本语义和表情倾向的微博情感分析方法[J]. 南京理工大学学报,2014,38(6):733-738.
Wang Wen,Wang Shufeng,Li Honghua. A method of Weibo emotion analysis based on text semantics and expression tendency[J]. Journal of Nanjing University of Science and Technology,2014,38(6):733-738.
[15]梁军,柴玉梅,原慧斌,等. 基于深度学习的微博情感分析[J]. 中文信息学报,2014,28(5):155-161.
Liang Jun,Chai Yumei,Yuan Huibin,et al. Sentiment analysis of Weibo based on deep learning[J]. Journal of Chinese Information Processing,2014,28(5):155-161.
[16]Kim Y. Convolutional neural networks for sentence classification[C]//Conference on Empirical Methods in Natural Language Processing(EMNLP 2014). Doha,Qatar:Association for Computational Linguistics,2014:1746-1751.
[17]Kingma D P,Ba J. Adam:A method for stochastic optimization[DB/OL]. https://arxiv. org/pdf/1412. 6980v8. pdf,2019-05-07.

相似文献/References:

[1]王 文,王树锋,李洪华.基于文本语义和表情倾向的微博情感分析方法[J].南京理工大学学报(自然科学版),2014,38(06):733.
 Wang Wen,Wang Shufeng,Li Honghua.Microblogging sentiment analysis method based on text semantics and expression tendentiousness[J].Journal of Nanjing University of Science and Technology,2014,38(03):733.

备注/Memo

备注/Memo:
收稿日期:2018-08-16 修回日期:2018-12-14
基金项目:国家自然科学基金(61170035; 61272420; 81674099; 61502233); 中央高校基本科研业务费专项资金(30918012204; 30918015103); 南京市科技计划项目(201805036); “十三五”装备领域基金(61403120501)
作者简介:杨玉娟(1981-),女,副研究馆员,主要研究方向:情报检索、自然语言处理等,E-mail:njlib_yang@126.com; 通讯作者:王永利(1974-),男,博士,教授,主要研究方向:海量数据分析、自然语言处理等,E-mail:yongliwang@njust.edu.cn。
引文格式:杨玉娟,袁欢欢,王永利. 针对评论文本的情感分析方法[J]. 南京理工大学学报,2019,43(3):280-285.
投稿网址:http://zrxuebao.njust.edu.cn
更新日期/Last Update: 2019-06-30