Sentiment Analysis of Media Coverage for Strategic Decision-Making using BERT Model

Sentiment analysis of media coverage has emerged as a vital tool for decision making and extracting meaningful sentiments from large/huge volumes of media data from news, public social websites in current digital era. This article focused analyzing sentiment in news, public social media coverage to support strategic decision-making using BERT algorithm. The dataset used as business, public social media politics, and technology is utilized for sentiment classification into three aspects like positive, negative, and neutral categories. The results proved that negative or neutral sentiment dominates media coverage, particularly in political news like media management while business and technology domains are more balanced or positive trends. The BERT algorithm demonstrated high accuracy due to its contextual understanding capabilities and make structured and meaningful format. From a strategic and decision-making perspective, sentiment analysis enabled organizations needs to monitor public perception required more crucial, assess risks, and make proactive decisions. This article provides the importance of AI-driven sentiment analysis strategic decision making in modern business environments.