STOCK SENTIMENT ANALYSIS FROM NEWS HEADLINES BY USING ENSEMBLE BOOSTING ALGORITHMS

Stock sentiment analysis using machine learning techniques is an active area of research and development. Through these techniques, it is possible to analyze whether news headlines are likely to have a positive or negative sentiment, which is considered a potential factor influencing stock price movements. The analysis in this study is based on factors such as company-related news headlines and their publication dates. This study aims to introduce a stock sentiment analysis methodology based on Ensemble Boosting Algorithms. The dataset used consists of 3,897 unique news headlines from various companies. In addition to Ensemble Boosting Algorithms, widely used classification algorithms were also trained and compared. The results demonstrate that the proposed models achieved successful performance in sentiment classification.