南京大学学报(自然科学版) ›› 2016, Vol. 52 ›› Issue (1): 175–183.

• • 上一篇    下一篇

归纳式迁移学习在跨领域情感倾向性分析中的应用

孟佳娜*, 赵丹丹, 于玉海, 孙世昶   

  • 出版日期:2016-01-27 发布日期:2016-01-27
  • 作者简介:(大连民族大学计算机科学与工程学院, 大连116600)
  • 基金资助:
    基金项目:国家自然科学基金(61202254),中央高校自主科研基金(DC201502030202,DC201502030405)
    收稿日期:2015-06-15
    *通讯联系人,E-mail:mengjn@dlnu.edu.cn

Application of inductive transfer learning in cross-domain sentiment analysis

Meng Jiana*, Zhao Dandan, Yu Yuhai, Sun Shichang   

  • Online:2016-01-27 Published:2016-01-27
  • About author:(School of Computer Science and Engineering, Dalian Nationalities University, Dalian, 116600, China)

摘要: 在跨领域情感倾向性分析中,提出一种基于归纳式迁移学习的图模型,通过图模型建立源领域和目标领域数据之间的关联,使得源领域的数据通过图模型学习目标领域数据在特征和实例上的特点。同时,利用归纳式迁移学习方法使用少量的目标领域的已标注数据进行训练,从而提高了情感分类器在目标领域的分类准确率。在标准数据集上进行了实验,实验结果表明该方法是有效的。

Abstract: To solve the sentiment analysis problems, traditional supervised learning methods and semi-supervised learning methods are based on the assumption that the training data and the testing data come from the identical distribution. It generates the cross-domain sentiment analysis problems when the assumption is not satisfied in some cases. In this paper, aiming at the problems of cross-domain sentiment analysis, a graph model is proposed based on the inductive transfer learning. The relevance of the source domain and the target domain data is modified, such that the source domain data can learn the characteristic at the point of the feature and the instance of the target domain data by the graph model. Simultaneously, the accuracy of sentiment classifiers in the target domain can be improved by using few target domain labeled data by the inductive transfer learning method. Experiments studies are carried out on the standard data, and the results show the efficiency of the proposed approach.

[1]Pang B, Lee L, Shivakumar V. Thumbs up? Sentiment classification using machine learning techniques. In: Proceedings of the Conference on Empirical Methods in Natural Language Processing. Philadelphia, PA, USA, 2002:79–86.
[2]Rao D, Ravichandran D. Semi-supervised Polarity Lexicon Induction. In: Proceedings of 12th Conference of the European Chapter of the Association for Computational Linguistics. 2009: 675–682.
[3]徐琳宏,林鸿飞,潘  宇. 情感词汇本体的构造. 情报学报,2008,(27):180-185.
[4]赵妍妍,秦  兵,车万翔等. 基于句法路径的情感评价单元识别. 软件学报. 2011, (22): 887?898.
[5]王素格, 李德玉, 魏英杰. 基于赋权粗糙隶属度的文本情感分类方法. 计算机研究与发展, 2011,48(5):855-861.
[6]姚天眆, 程希文, 徐飞玉等. 文本意见挖掘综述. 中文信息学报, 2008, 22(3): 71-80.
[7]俞亚君, 霍  静, 史颖欢等. SSXCS:半监督学习分类系统. 南京大学学报(自然科学), 2013,49(5):611-618.
[8]Pan S, Yang Q. A survey on transfer learning. IEEE Transactions on Knowledge and Data Engineering, 2009, (22): 1345-1359.
[9]Cao X B, Wang Z, Yan P K, et al. Transfer learning for pedestrian detection. Neurocomputing, 2013,100:51-57
[10]Zhuo H H, Yang Q. Action-model acquisition for planning via transfer learning. Artificial Intelligence,2014,212:80-103
[11]Dai W Y, Yang Q, Xue G R, et al. Self-taught clustering. In: Proceedings of the 25th International Conference of Machine Learning. Helsinki, Finland, ACM, 2008:200–207.
[12]Meng J N, Lin H F, Li Y P. Knowledge transfer based on feature representation mapping for text classification. Expert Systems with Applications, 2011 (38): 10562–10567.
[13]Meng J N, Lin H F, Yu Y H. Adaptive transfer learning for spam filtering. Journal of Computational Information Systems, 2010(6):4581-4589.
[14]Blitzer J, Dredze M, Pereira F. Biographies, bollywood, boomboxes and blenders: Domain adaptation for sentiment classification. In: Proceedings of the 45th Annual Meeting of the Association of Computational Linguistics. Prague, Czech Republic, 2007.
[15]Blitzer J, McDonald R, Pereira F. Domain adaptation with structural correspondence learning. In: Proceedings of Conference on Empirical Methods in Natural Language. Sydney, Australia, 2006.
[16]吴  琼,刘  悦,沈华伟等.面向跨领域情感分类的统一框架.计算机研究与发展,2013,50 (8):1683–1689.
[17]Pan S, Ni X C, Sun J T ,et al. Cross-domain sentiment classification via spectral feature alignment. In: Proceedings of the 19th International Conference on World Wide Web. New York, USA: ACM Press, 2010.
[18]魏现辉,张绍武,杨  亮等. 基于加权SimRank 的跨领域文本情感倾向性分析. 模式识别与人工智能,2013,26(11):1004-1009.
[19]孟佳娜. 迁移学习在文本分类中的应用研究. 博士学位论文. 大连: 大连理工大学, 2011.
[20]Dai W Y, Yang Q Y, Xue G R, et al. Boosting for transfer learning. In: Proceedings of the 24th International Conference on Machine Learning. Corvallis, OR, USA, 2007:193–200.
[21]Wu P C, Dietterich T G.. Improving SVM accuracy by training on auxiliary data sources. In: Proceedings of the 21st International Conference on Machine Learning. Morgan Kaufmann, 2004: 871–878.
[22]Shi Y, Lan Z Z, Liu W, et al. Extending semi-supervised learning methods for inductive transfer learning. In: Proceedings of the 9th IEEE International Conference on Data Mining. Miami, Florida, USA, 2009: 483–492.
[23]Arnold A, Nallapati R, Cohen W W. A comparative study of methods for transductive transfer learning. In: Proceedings of the 7th IEEE International Conference on Data Mining Workshops. Omaha, Nebraska, USA: IEEE Computer Society, 2007: 77–82.
[24]Meng J N, Sun S C. Transductive transfer learning based on KL-divergence. International Journal of Innovative Computing, Information and Control,2014, 10(1):303-313.
[25]宋海霞, 严  馨, 余正涛等.基于自适应聚类的虚假评论检测, 南京大学学报(自然科学), 2013,49(4):433-438.
No related articles found!
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!