Social Media Sentiment Analysis for Opinion Mining

Abstract

The sentiment analysis that digital epidemiology can support faster response and deeper understanding of public health threats than traditional methods is a rapidly growing area. There are numerous social media sentiment analyses over Twitter data, and other similar microblogs face several new challenges due to the typical short length and irregular structure of such content sites available on the internet. Which provides options to users to give feedback about names of diseases and their symptoms. This paper discusses an approach to the health expertise trends and sentiments of users using Twitter, their emotional content as positive, negative, and irrelevant, and an attempt to observe the public’s opinions and identify their issues. In existing top-down approaches, necessary but unknown information, such as disease names and symptoms, is mostly unidentified in social media data until national public health institutes have formalized that disease. In this paper we present a methodology for early detection and analysis of epidemics based on mining Twitter messages. In order to reliably trace messages of patients that actually complain of a disease, we adopt a symptom-driven, rather than disease-driven, keyword analysis. In this paper, various algorithms for sentiment analysis are studied, and challenges and applied machine learning techniques that appear in this field are discussed.