Basic Review of Different Strategies for Sentiment Analysis in Online Social Networks
Siva Kumar Pathuri1, N. Anbazhagan2
1Siva Kumar Pathuri, Department of Computer Science Engineering, KLEF, Vaddeswaram, AP, India.
2Dr. N. Anbazhagan, Department of Math’s, Alagappa University, Karaikudi, (Tamil Nadu), India.

Manuscript received on 08 April 2019 | Revised Manuscript received on 17 May 2019 | Manuscript published on 30 May 2019 | PP: 3392-3396 | Volume-8 Issue-1, May 2019 | Retrieval Number: A3268058119/19©BEIESP
Open Access | Ethics and Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)

Abstract: TThe growth of different online networks such as MySpace, Twitter, LinkedIn and Face book have been increased in recent years, high amount of data outsource via social media into data sources. This huge amount of data analyzed for research on different types of real time applications. So that analysis of sentiment and mining user opinion is one of aggressive concept to explore meaning of outsourced data. While different types of approaches are implemented to identifying sentiment and opinion in social networks like pattern based classification with respect to parts of speech, emotions and batch model learning while analyzing huge amount of data. In this paper we give brief description of different machine learning approaches to describe utilize sentiment of huge amount data in social networks. We give survey of different approaches with respect to sentiment exploration from online social network. Also describe comparative analysis of different methods used for analysis of sentiment and mining of user opinion in online social networks.
Index Terms: Sentiment Analysis, Twitter, Online Social Networks, Stream Detection, Information Retrieval, Data – Processing, Concept Based Approaches and Machine Learning.

Scope of the Article: Machine Learning.