Affiliation:
1. Kalinga Institute of Industrial Technology (Deemed), Bhubaneswar, India
Abstract
Opinion mining and sentiment analysis help in extracting valuable information from the huge user data generated in the form of opinions and reviews from the customers and comments. Such a huge increase in data available on the electronic or social media has also increased interest in this field. Sentiment analysis helps in extraction of opinions of others (writer or speaker) from a given source (text) using different methods and techniques like NLP, text mining, and linguistic computation and classifying them into positive, negative, and neutral opinions. Decision making for both consumers as well as the seller becomes much easier with such type of classification. This chapter consists of survey report on different elements of sentiment analysis, its applications, and challenges involved. The chapter studies and compares some of the techniques used to evaluate the item's reputation using sentiment analysis. A number of tools and features for sentiment analysis are also included in this chapter that can later help to perform better sentiment analysis of data.
Reference88 articles.
1. Intelligent feature selection for opinion classification.;A.Abbasi;Technology (Elmsford, N.Y.),2003
2. Sentiment analysis in multiple languages: Feature selection for opinion classification in web forums.;A.Abbasi;ACM Transactions on Information Systems,2008
3. Abdelwahab, O., Bahgat, M., Lowrance, C. J., & Elmaghraby, A. (2015, December). Effect of training set size on SVM and Naive Bayes for Twitter sentiment analysis. In 2015 IEEE international symposium on signal processing and information technology (ISSPIT) (pp. 46-51). IEEE.
4. Agrawal, R., Rajagopalan, S., Srikant, R., & Xu, Y. (2003, May). Mining newsgroups using networks arising from social behavior. In Proceedings of the 12th international conference on World Wide Web (pp. 529-535). Academic Press.
5. Towards using visual attributes to infer image sentiment of social events.;U.Ahsan;2017 International Joint Conference on Neural Networks (IJCNN),2017