SOCIAL MEDIA SENTIMENT ANALYSIS FOR BRAND MONITORING

Abstract

Social media (SM) has had a profound effect on the business ecosystem. It provides immense potential for
businesses because consumers habitually log on to it daily and are exposed to companies. Companies depend on
sentiment analysis (SA) to gain a deeper understanding of the consumer mindset. SA can be of assistance so that
you gain insights about new markets, foresee industry trends, and most importantly, understand what didn't go
well with previous product releases to help you improve your existing and future products and services. Obtaining
an accurate and truly useful information from SM sentiment analysis has become a challenging issue in recent
years. In this paper, we propose a web-based brand monitoring system that helps businesses and organizations
monitor public sentiments or opinions about their brand, product or services. SM platform Twitter was used as a
case study, involving the 2016 United States presidential election twitter dataset. The study utilized statistics,
natural language processing, and machine learning to determine the emotional meaning of communications. The
developed system facilitates informed decisions and resolution of public complaints efficiently without the need
for crude analysis (customer surveys, product forms, etc).