MoodScope An AI-Powered Exploration of Twitter Sentiments Using Frameworks

Sentiment analysis, the computational study of opinions, sentiments, attitudes, and emotionsexpressed in written language, has gained prominence in recent years due to its wide applications andchallenging research problems. This paper focuses on evaluating sentiment analysis using LogisticRegression and Support Vector Machine (SVM) algorithms. The analysis was performed with metricsincluding accuracy (0.941), precision (0.615), recall (0.466), and F1 score (0.530). The dataset comprises319 true positives (TP), 8705 true negatives (TN), 200 false positives (FP), and 365 false negatives (FN).Sentiment analysis has evolved alongside the growth of social media, becoming integral to various fieldsbeyond computer science, including management and social sciences. The paper explores mainstreamsentiment analysis research and recent advancements in modeling comments, discussions, and debates,highlighting the algorithms' effectiveness in capturing nuanced sentiments and opinions.