Approaches for Sentiment Analysis on Twitter: A State-of-Art study

TL;DR

This paper surveys current methods for sentiment analysis on Twitter, highlighting lexical, machine learning, and hybrid approaches, emphasizing Twitter's unique constraints and data accessibility features.

Contribution

It provides a comprehensive overview of state-of-the-art techniques specifically applied to Twitter sentiment analysis, including recent advances and challenges.

Findings

Lexical approaches are effective for simple sentiment detection.

Machine learning models improve accuracy with large datasets.

Hybrid methods combine strengths of lexical and machine learning techniques.

Abstract

Microbloging is an extremely prevalent broadcast medium amidst the Internet fraternity these days. People share their opinions and sentiments about variety of subjects like products, news, institutions, etc., every day on microbloging websites. Sentiment analysis plays a key role in prediction systems, opinion mining systems, etc. Twitter, one of the microbloging platforms allows a limit of 140 characters to its users. This restriction stimulates users to be very concise about their opinion and twitter an ocean of sentiments to analyze. Twitter also provides developer friendly streaming API for data retrieval purpose allowing the analyst to search real time tweets from various users. In this paper, we discuss the state-of-art of the works which are focused on Twitter, the online social network platform, for sentiment analysis. We survey various lexical, machine learning and hybrid approaches for sentiment analysis on Twitter.