Sentiment Analysis on Social Media
There are challenges in developing accurate sentiment analysis models for all languages, but there are applications in understanding public perception of eco-friendly transformation and air quality, predicting box office success, and analyzing public sentiment during global events such as pandemics.
Abstract
Sentiment analysis is a technique that uses machine learning, natural language processing, and computational linguistics to understand people’s feelings and opinions on social media. With the growth of social media users, there is an abundance of information shared in various forms including text, photos, audio and video. Sentiment analysis divides this information into positive, negative or neutral sentiment and has been divided into three levels: sentence, document and features. There are two main methods of sentiment analysis: machine learning and lexicon-based approaches. Sentiment analysis has applications in understanding public perception of eco-friendly transformation and air quality, predicting box office success, and analyzing public sentiment during global events such as pandemics. However, there are challenges in developing accurate sentiment analysis models for all languages.