Sentiment Recognition of Online Chinese Micro Movie Reviews Using Multiple Probabilistic Reasoning Model

Online review websites provide an important channel for people to share their opinions. In this paper, we research the sentiment recognition technology on online Chinese micro movie reviews. As the sentiment expressed in Chinese is subtle and the feature space is very sparse, we adopt n-grams to develop sentiment feature space, and then propose an ensemble learning algorithm based on random feature space division method, namely Multiple Probabilistic Reasoning Model (M-PRM), for supervised document level sentiment classification. This algorithm captures discriminative sentiment features and makes full use of them. Comparing with this algorithm, we apply other four machine learning methods: Multinomial NaiveBayes (MNB), Probabilistic Reasoning Model (PRM), Sentiment-word method (SWM) and SVM on two micro movie review datasets. Results show that M-PRM achieves better classification performance than other methods.

[1]  Shanxiao Yang,et al.  Emotion Recognition of EMG Based on Improved L-M BP Neural Network and SVM , 2011, J. Softw..

[2]  Zhi Liu,et al.  Application of Synergetic Neural Network in Online Writeprint Identification , 2011 .

[3]  Michael L. Littman,et al.  Unsupervised Learning of Semantic Orientation from a Hundred-Billion-Word Corpus , 2002, ArXiv.

[4]  Qifa Qu.  Determination of Weights for the Ultimate Cross Efficiency: A Use of Principal Component Analysis Technique , 2012, J. Softw..

[5]  HoTin Kam.  The Random Subspace Method for Constructing Decision Forests , 1998 .

[6]  David D. Lewis,et al.  Naive (Bayes) at Forty: The Independence Assumption in Information Retrieval , 1998, ECML.

[7]  A. McCallum,et al.  Topical N-Grams: Phrase and Topic Discovery, with an Application to Information Retrieval , 2007, Seventh IEEE International Conference on Data Mining (ICDM 2007).

[8]  Chengjun Liu,et al.  Robust coding schemes for indexing and retrieval from large face databases , 2000, IEEE Trans. Image Process..

[9]  Andrew Rosenberg,et al.  Augmenting the kappa statistic to determine interannotator reliability for multiply labeled data points , 2004, HLT-NAACL.

[10]  Hong Yu,et al.  Towards Answering Opinion Questions: Separating Facts from Opinions and Identifying the Polarity of Opinion Sentences , 2003, EMNLP.

[11]  Tin Kam Ho,et al.  The Random Subspace Method for Constructing Decision Forests , 1998, IEEE Trans. Pattern Anal. Mach. Intell..

[12]  Xiaoming Tao,et al.  Classification of Bio-potential Surface Electrode based on FKCM and SVM , 2011, J. Softw..

[13]  Theodora Varvarigou,et al.  Sentiment analysis of social media content using N-Gram graphs , 2011, WSM '11.

[14]  Bo Pang,et al.  Thumbs up? Sentiment Classification using Machine Learning Techniques , 2002, EMNLP.

[15]  Maite Taboada,et al.  Lexicon-Based Methods for Sentiment Analysis , 2011, CL.