Authoritative sources in a hyperlinked environment
Journal of the ACM (JACM)
Mining the Web for Synonyms: PMI-IR versus LSA on TOEFL
EMCL '01 Proceedings of the 12th European Conference on Machine Learning
Transductive Inference for Text Classification using Support Vector Machines
ICML '99 Proceedings of the Sixteenth International Conference on Machine Learning
A novel refinement approach for text categorization
Proceedings of the 14th ACM international conference on Information and knowledge management
A novel scheme for domain-transfer problem in the context of sentiment analysis
Proceedings of the sixteenth ACM conference on Conference on information and knowledge management
Adapting Naive Bayes to Domain Adaptation for Sentiment Analysis
ECIR '09 Proceedings of the 31th European Conference on IR Research on Advances in Information Retrieval
FeatureEng '05 Proceedings of the ACL Workshop on Feature Engineering for Machine Learning in Natural Language Processing
LexRank: graph-based lexical centrality as salience in text summarization
Journal of Artificial Intelligence Research
Graph ranking for sentiment transfer
ACLShort '09 Proceedings of the ACL-IJCNLP 2009 Conference Short Papers
Automatically extracting polarity-bearing topics for cross-domain sentiment classification
HLT '11 Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies - Volume 1
Transverse subjectivity classification
Proceedings of the First International Workshop on Issues of Sentiment Discovery and Opinion Mining
Hi-index | 0.00 |
Recent years have witnessed a large body of research works on cross-domain sentiment classification problem, where most of the research endeavors were based on a supervised learning strategy which builds models from only the labeled documents or only the labeled sentiment words. Unfortunately, such kind of supervised learning method usually fails to uncover the full knowledge between documents and sentiment words. Taking account of this limitation, in this paper, we propose an iterative reinforcement learning approach for cross-domain sentiment classification by simultaneously utilizing documents and words from both source domain and target domain. Our new method can make full use of the reinforcement between documents and words by fusing four kinds of relationships between documents and words. Experimental results indicate that our new method can improve the performance of cross-domain sentiment classification dramatically.