Open Access Open Access  Restricted Access Subscription or Fee Access

Various Techniques of Sentiment Analysis on Twitter Data Set: A Survey

Ankita Abhimanyu Bondre, S. V. Hemanth

Abstract


Abstract

Sentiment analysis is the process of computationally identifying and categorizing opinions expressed in a piece of text, especially in order to determine whether the writer's attitude towards a particular topic, product, etc. is positive, negative, or neutral. Sentiment analysis could be a variety of data processing that measures the inclination of people’s opinions through natural language processing (NLP), linguistics and text analysis, that square measure want to extract and analyze subjective info from the net, largely social media and similar sources. The analyzed knowledge quantifies the overall public's sentiments or reactions toward bound merchandise, folks or ideas and reveals the discourse polarity of the data. Sentiment analysis is additionally called opinion mining which analyzes people’s opinions, sentiments, evaluations, appraisals, attributes and emotions towards entities, admire product services, organizations, people, issues, events, topics etc. This paper gives the survey on various techniques used for doing sentiment analysis i.e. opinion mining. As opinion mining helps us to find what exactly the writer of the content wants to convey about that topic. A lot of research has been already done on this topic using different techniques in the field such as finding scientific topic, sentiment strength detection in short informal text, opinion retrieval from blogs, opinion mining, mining or summarization of customer reviews and in predicting movie sales or movie reviews. The purpose of this paper is to illustrate recent research work done in various fields of sentiment analysis.

Keywords: Sentiment analysis, opinion mining, natural language processing (NLP), text summarization

Cite this Article

Ankita Bondre, Hemanth SV. Various Techniques of Sentiment Analysis on Twitter Data Set: A Survey. Journal of Advanced Database Management & Systems. 2017; 4(2): 27–32p.



Full Text:

PDF

Refbacks

  • There are currently no refbacks.