A Novel Approach for Text Sentimental Analysis in Social Network

Abstract

This study provides an overview and examine the sentimental analysis of twitter data. Sentiment analysis is one of the fastest growing research area in computer science, making it challenging to keep track of all the activities in the area. In this study, we explore the effect of applying sophisticated negation scope detection to twitter sentiment analysis. Sentimental analysis refers to the task of natural language processing to determine whether a piece of text contains some subjective information and what subjective information it expresses, i.e., whether the attitude behind this text is positive, negative or neutral. It detects the sentiment that refers to the specific subject using Natural Language Processing techniques. In this study, we also propose and investigate a method of elementary discourse unit (EDU) level sentiment analysis using discourse features. Following prior work, we hypothesize that when we want to predict the sentiment of a certain EDU, we can use the sentiments of other EDUs, which stand in some discourse relation with the current one. In daily life, our beliefs and perceptions of reality are largely dependent on how other people analyze the world. People mostly share their opinions about different entities like organization, products, services etc. on social media, forums, and blogs. Microblogging sites have millions of people sharing their thoughts daily because of its short and simple manner of expression.