| 361 | 6 | 98 |
| 下载次数 | 被引频次 | 阅读次数 |
针对描述客观事实评论中量化的情感特征片面问题,提出一种基于情感特征的主客观分类方法。将基于情感词典与机器学习结合得到的积极或消极情感权值与概率,作为新的情感特征项与评论文本的语言、属性和信息特征相结合,重新确定影响用户行为的情感特征,从而对评论文本进行主客观分类。实验结果表明,采用支持向量机算法可使基于情感特征的主客观分类效果更佳,准确率为87.20%。
Abstract：A new quantitative sentiment analysis approach based on sentimental dictionaries and machine learning is proposed in this paper to tackle the problem of partiality of quantitative sentimental features of representation for objective facts.The positive and negative emotional weights and probabilities obtained by the combination of emotional dictionary and machine learning are used as new emotional characteristics.These emotional characteristics are combined with the language,attributes and information characteristics of the commentary text to redefine the affective characteristics of the user's behaviour.Experimental results show that the support vector machine(SVM)algorithm can classify the subjective and objective based on emotion characteristics,and the accuracy can reach 87.20%.
[1]PERKINS J.Python Text Processing with NLTK 2.0Cookbook[M/OL].Packt Publishing Limited.2010:1-92[2017-02-15].https://www.amazon.cn/PythonText-Processing-with-NLTK-2-0-Cookbook-LITE-Perkins-Jacob/dp/1849516383.
[2]KASTHURIARACHCHY B H,ZOYSA K D,PREMARATNE H L.A review of domain adaptation for opinion detection and sentiment classification.In Proceedings of the Int’l Conf.on Advances in ICT for Emerging Regions[C/OL]//2012International Conference on Advances in ICT for Emerging Regions(ICTer).Colombo:IEEE,2012:209-213[2017-02-15].http://dx.doi.org/10.1109/ICTer.2012.6423023.
[3]张林,钱冠群,樊卫国.轻型评论的情感分析研究[J/OL].软件学报,2014(12):2790-2807[2017-02-15].DOI:10.13328/j.cnki.jos.004728.http://kns.cnki.net/KCMS/detail/detail.aspx?filename=rjxb201412006&dbname=CJFD&dbcode=CJFQ.
[4]薛益定.中文情感分析研究综述[J/OL].电脑编程技巧与维护,2016(5):22-24[2017-02-15].http://dx.chinadoi.cn/10.3969/j.issn.1006-4052.2016.05.010.
[5]张润,王永滨.机器学习及其算法和发展研究[J/OL].中国传媒大学学报(自然科学版),2016,23(2):10-18[2017-02-15].http://dx.chinadoi.cn/10.3969/j.issn.1673-4793.2016.02.002.
[6]卢兴.基于统计方法的中文短文本情感分析[D/OL].北京:北京理工大学,2016:5-74[2017-02-15].http://cdmd.cnki.com.cn/Article/CDMD-10007-1016717758.htm.
[7]TURNEY P.Thumbs Up or Thumbs Down Semantic Orientation Applied to Unsupervised Classification of Reviews[C/OL].ACL’02 Proceedings of the 40th Annual Meeting on Association for Computational Linguistics.Stroudsburg:ACM,2002:417-424[2017-02-15].https://doi.org/10.3115/1073083.1073153.
[8]朱军,胡文波.贝叶斯机器学习前沿进展综述[J/OL].计算机研究与发展,2015,52(1):16-26[2017-02-15].http://dx.chinadoi.cn/10.7544/issn.1000-1239.2015.20140107.
[9]赵妍妍,秦兵,刘挺.文本情感分析[J/OL].软件学报,2010,21(8):1834-1848[2017-02-15].http://dx.chinadoi.cn/10.3724/SP.J.1001.2010.03832.
[10]李光敏,许新山,张磊.微博中产品意见挖掘研究[J/OL].情报杂志,2014(4):135-138[2017-02-15].http://dx.chinadoi.cn/10.3969/j.issn.1002-1965.2014.04.024.
[11]马力,王芸,杨琳.基于MoodCast模型的用户行为分析与预测[J/OL].电子技术应用,2015,41(11):140-143[2017-02-15].http://dx.chinadoi.cn/10.16157/j.issn.0258-7998.2015.11.039.
[12]郭立力,赵春江.十折交叉检验的支持向量机参数优化算法[J/OL].计算机工程与应用,2009,45(8):55-57[2017-02-15].http://dx.chinadoi.cn/10.3778/j.issn.1002-8331.2009.08.017.
基本信息:
DOI：10.13682/j.issn.2095-6533.2017.04.019
中图分类号:TP391.1
引用信息:
[1]马力,丁蔚,李培,等.基于情感特征的主客观分类研究[J].西安邮电大学学报,2017,22(04):101-104.DOI:10.13682/j.issn.2095-6533.2017.04.019.
基金信息:
陕西省自然科学基础研究计划资助项目(2016JM6085)