计算机科学 ›› 2017, Vol. 44 ›› Issue (11): 289-296.doi: 10.11896/j.issn.1002-137X.2017.11.044
池云仙,赵书良,罗燕,赵骏鹏,高琳,李超
CHI Yun-xian, ZHAO Shu-liang, LUO Yan, ZHAO Jun-peng, GAO Lin and LI Chao
摘要： 基于相似性进行文本分类是当前流行的文本处理方法。基于特征隶属度的文本分类相似性度量方法旨在利用特征与文档间的隶属关系度量文档相似性,从而实现文本分类。该方法基于特征与文档的隶属关系,对特征进行全隶属、偏隶属和无隶属词集划分,并基于3种隶属词集定义隶属度函数。全隶属词集隶属于两篇文档,隶属度随权差增大而降低；偏隶属词集仅隶属于其中某一篇文档,隶属度为一个定值；无隶属词集与两篇文档无隶属关系,隶属度为零。在度量相似性时,偏隶属关系高于全隶属关系。由于同类文档词集相近,异类文档词集差异明显,因此,基于特征与文档的隶属度进行相似性度量,可清晰界定词集与类别的隶属关系,提升分类精度。最后,采用数据集20-Newgroups和Reuters-21578对分类有效性进行验证,结果表明基于特征隶属度的相似性度量方法的性能优于目前流行的相似性度量方法。
| [1] SEBASTIANI F.Machine learning in automated text categorization[J].ACM CSUR,2002,4(1):1-47. [2] LIU L,PENG T,ZUO W L,et al.Clustering-Based PU Active Text Clasfication Method [J].Journal of Software,2013,4(11):2571-2583.(in Chinese) 流露,彭涛,左万利,等.一种基于聚类的PU主动文本分类方法[J].软件学报,2013,4(11):2571-2583. [3] XIA R,XU F,ZONG C Q,et al.Dual Sentiment Analysis:Considering Two Sides of One Review [J].IEEE Transactions on Knowledge and Data Engineering,2015,27(8):2120-2133. [4] YU Z,WANG H X,LIN X M,et al.Understanding Short Texts through Semantic Enrichment and Hashing [J].IEEE Transactions on Knowledge and Data Engineering,2016,28(2):566-579. [5] AZAM N,YAO J.Comparison of term frequency and document frequency based feature selection metrics in text categorization[J].Expert Syst.Appl.,2012,9(5):4760-4768. [6] DUAN J,HU Q H,ZHANG L J,et al.Feature Selection for Multi-Label Classification Based on Neighborhood Rough Set [J].Journal of Computer Research and Development,2015,2(1):56-65.(in Chinese) 段洁,胡清华,张灵均,等.基于邻域粗糙集的多标记分类特征选择算法 [J].计算机研究与发展,2015,2(1):56-65. [7] TANG B,KAY S,HE H B.Toward Optimal Feature Selection in Nave Bayes for Text Categorization [J].IEEE Transactions on Knowledge and Data Engineering,2016,28(9):2508-2521. [8] TANG B,HE H B,BAGGENSTOSS P M,et al.A BayesianClassification Approach Using Class-Specific Features for Text Categorization[J].IEEE Transactions Knowledge and Data Engineering,2016,8(6):1602-1606. [9] CHENG V C,LEUNG C H C,LIU J M,et al.Probabilistic Aspect Mining Model for Drug Reviews [J].IEEE Transactions on Knowledge and Data Engineering,2014,6(8):2002-2013. [10] TANG B,HE H ,DING D,et al.A parametric classification rule based on the exponentially embedded family [J].IEEE Transactions on Neural Networks and Learning Systems,2015,6(2):367-377. [11] LIU S H,CHENG X Q, LI F X,et al.TASC:Topic-Adaptive Sentiment Classification on Dynamic Tweets [J].IEEE Transactions on Knowledge and Data Engineering,2015,7(6),1696-1709. [12] SUN K W,LEE C H,WANG J.Multilabel Classification via Co-Evolutionary Multilabel Hypernetwork [J].IEEE Transactions on Knowledge and Data Engineering,2016,8(9):2438-2451. [13] ZHANG T,TANG Y Y,FANG B,et al.Document clustering in correlation similarity measure space[J].IEEE Transactions on Knowledge and Data Engineering,2012,4(6):1002-1013. [14] MORI U,MENDIBURI A,LOZANO J A.Similarity MeasureSelection for Clustering Time Series Databases[J].IEEE Tran-sactions on Knowledge and Data Engineering,2016,28(1):181-195. [15] KANG Y B,HAGHIGH P D,BURSTEIN F.TaxoFinder:AGraph-Based Approach for Taxonomy Learning [J].IEEE Transactions on Knowledge and Data Engineering,2016,28(2):524-536. [16] WANG Q,CUI M Y,LIANG H Z.Semantic-Aware Bloking for Entiy Resolution [J].IEEE Transactions on Knowledge and DataEngineering,2016,28(1):166-180. [17] MCCALLUM A,NIGAM K,et al.A comparison of event mo-dels for naive bayes text classification[C]∥AAAI-98 Workshop on Learning for Text Categorization.1998:41-48. [18] SCHOENHARL T W,MADEY G.Evaluation of measurement techniques for the validation of agent-based simulations against streaming data[C]∥Proc.ICCS.Kraków,Poland,2008:6-15. [19] STREHL A,GHOSH J.Value-based customer grouping fromlarge retail data-sets[C]∥Proc.SPIE.Orlando,FL,USA,2000:33-42. [20] BISWAS S K,MILANFAR P.One Shot Detection with Laplacian Object and Fast Matrix Cosine Similarity [J].IEEE Tran-sactions on Pattern Analysis and Machine Intelligence,2016,38(3):546-562. |
| No related articles found! |
|
||
首页