International Journal of Advanced Computing and Communication Systems

Public Sentiment and its Variation Analysis using SentiStrength and Improved Twitter Sentiment Model

Osamah Ali Mohammed Ghaleb and Anna Saro Vijendran, Department of Computer Science,SNR Sons College, Coimbatore, Tamil Nadu, India.

Anna Saro Vijendran, Department of Computer Application, SNR Sons College, Coimbatore, Tamil Nadu, India.

International Journal of Advanced Computing and Communication Systems

Received On :

Revised On :

Accepted On :

Published On :

Volume 05, Issue 02

Page No : 021-028

Abstract

The internet users of the rapidly changing environment utilize social media as the medium of communication for expressing their opinions on social media. It is highly essential to track the sentiments of the people to make wise decisions. The existing approaches only track and model the sentiments. Here, analyses are carried out to find the reasons of sentiment variation The existing LDA based approach involves three main steps 1)Extraction and Pre-processing of tweets 2) Sentiment label assignment 3) Sentiment variation tracking. It utilizes the Senti Strength and Twitter Sentiment for Sentiment label assignment. The proposed system (SSITS) uses Senti Strength and improved Twitter Sentiment for label assignment .The Twitter Sentiment is improved by utilizing Semantic role labeller and Kullback-Leibler divergence classifier.

Keywords

Senti Strength; Twitter Sentiment; LDA; Sentiment Variation; Semantic role labeller; Kullback-Leibler divergence classifier.

Cite this Article

Osamah Ali Mohammed Ghaleb and Anna Saro Vijendran, “Public Sentiment and its Variation Analysis using SentiStrength and Improved Twitter Sentiment Model, ”International Journal of Advanced Computing and Communication Systems, pp. 001-008, July 2018.

Copyright

© 2018 Osamah Ali Mohammed Ghaleb and Anna Saro Vijendran. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.