Publication Type : Conference Paper
Publisher : 2015 International Conference on Computing and Network Communications, CoCoNet 2015
Source : 2015 International Conference on Computing and Network Communications, CoCoNet 2015, Institute of Electrical and Electronics Engineers Inc., p.50-58 (2015)
ISBN : 9781467373098
Keywords : Data mining, Domain Adaptation, Iterative methods, Latent Semantic Analysis, Natural language processing systems, Opinion Oriented Word, Polarity Lexicon, Semantics, Sentiment analysis, Source Domain, Target domain
Campus : Bengaluru
School : Department of Computer Science and Engineering, School of Engineering
Department : Computer Science, Mathematics
Year : 2015
Abstract : Sentiment analysis has emerged as an independent branch of research and attracted many researchers in recent years. Analysis of sentiment deals with expressed opinions. That makes it widely applicable in every part of life and in businesses where opinion counts. Opinions are expressed by the means of opinion oriented words which are part of sentiment analysis resource such as polarity lexicon. Polarity lexicon construction is widely explored by researchers using various supervised and semi-supervised approaches. Semi-supervised approaches are often combined with polarity seed information. A novel semi-supervised approach is proposed to construct polarity lexicon using iterative Latent Semantic Analysis technique from unlabeled multiple source domains corpus. This polarity lexicon is adaptable across multiple target domains. In the process seed words are learned from multiple domain corpus and subsequently adapted to new domains. Significant improvement in accuracy is observed over the baselines. © 2015 IEEE.
Cite this Research Publication : S. Sanagar and Dr. Deepa Gupta, “Adaptation of multi-domain corpus learned seeds and polarity lexicon for sentiment analysis”, in 2015 International Conference on Computing and Network Communications, CoCoNet 2015, 2015, pp. 50-58.