期刊文献+

基于主动学习的新媒体政务互动内容情感挖掘研究 被引量:3

Research on Emotion Mining of Government Affairs Interactive Content in New Media Based on Active Learning
原文传递
导出
摘要 [目的/意义]新媒体平台逐渐成为政民交互的重要载体,准确把握新媒体政务互动内容中的情感倾向,有助于提升政府舆情把握能力与社会治理能力。[方法/过程]在BERT文本语义表示基础上,将主动学习策略与BiLSTM模型集成,进行新媒体政务互动内容情感倾向分析,以提升模型对互动内容情感数据的有效利用。[结果/结论]针对“法律法规草案公开征求意见类”微博互动内容的实验表明,将主动学习引入BERT-BiLSTM模型后,模型的准确率、召回率及F值提升,新媒体政务互动内容情感呈现效果较好。文章所提模型科学可行,能够在减少数据依赖的情况下,提升情感挖掘的效率。 [Purpose/significance] New media platform has gradually become an important carrier of the interaction between the government and the people.Accurately grasping the emotional tendency of government affairs interactive content in new media helps to improve the government’s ability of public opinion grasping and social governance.[Method/process] This paper integrates active learning strategy with BiLSTM model on the basis of BERT text semantic representation for sentiment tendency analysis of government affairs interactive content,in order to improve the effective use of interactive content sentiment data.[Result/conclusion] Experiment on government affairs interactive content of “draft laws and regulations for public consultation” in Sina Microblog shows that after active learning is introduced into BERT-BilSTM model,the accuracy rate,recall rate and F value of the model are improved,and the emotion of government affairs interactive content can be better presented.The proposed model in this paper is scientifically feasible and can improve the efficiency of sentiment mining with less data dependence.
作者 郑翔 胡吉明 Zheng Xiang
出处 《情报理论与实践》 CSSCI 北大核心 2022年第4期177-183,共7页 Information Studies:Theory & Application
基金 国家自然科学基金面上项目“基于深度学习的政务新媒体互动内容摘要自动生成与情感分析模型研究”的成果,项目编号:71874125。
关键词 新媒体 政务互动内容 情感挖掘 主动学习 new media government affairs interactive content emotional mining active learning
  • 相关文献

参考文献18

二级参考文献231

  • 1段平.如何撰写科技论文英文信息型摘要[J].大学英语,2000(12):51-52. 被引量:3
  • 2陈涛,谢阳群.文本分类中的特征降维方法综述[J].情报学报,2005,24(6):690-695. 被引量:79
  • 3朱嫣岚,闵锦,周雅倩,黄萱菁,吴立德.基于HowNet的词汇语义倾向计算[J].中文信息学报,2006,20(1):14-20. 被引量:326
  • 4张谊生.论现代汉语的范围副词[J].上海师范大学学报:哲学社会科学版.2001(1).
  • 5中国互联网络信息中心.第36次中国互联网络发展状况统计报告[R/OL].[2015-06-01].http://www.cnnic.net.cn/h1.wfzyj/hlwxzbg,/.
  • 6Turney P D. Thumbs up or thumbs down? Semantic orientation ap- plied to unsupervised classification of reviews[ C ]//Proceedings of the 40th Annual Meeting on Association for Computational Linguis- tics. Philadelphia: Association for Computational Linguistics, 2002 : 417 - 424.
  • 7Pang Bn, Lee L, Vaithyanathan S. Thumbs up? Sentiment classifi- cation using machine learning techniques [ C ]//Proceedings of the ACL- 02 Conference on Empirical Methods in Natural Language Processing - Volume 10. Philadelphia: Association for Computation- al Linguistics, 2002 : 79 - 86.
  • 8Cui Hang, Mittal V, Datar M. Comparative experiments on senti- ment classification for online product reviews [ C ]//Proceedings of the 21 st National Conference on Artificial Intelligence. Boston : As- sociation for the Advancement of Artificial Intelligence, 2006.
  • 9Mao Yi, Lebanon G. Isotonic conditional random fields and local sentiment flow[ C 1//Proceedings of the Conference on Advances in Neural Information Processing Systems. Vancouver: Neural Informa- tion Processing Systems Foundation,2006 : 961 - 968.
  • 10Wei Wei, Gulla J A. Sentiment learning on product reviews via sen- timent ontology tree [ C ]//Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics. Uppsal_a:Associa- tion for Computational Linguistics,2010.

共引文献486

同被引文献47

引证文献3

二级引证文献8

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部