Twitter and Emotions: Exploring Sentiment Detection

Human emotions are often discerned through tone, facial expressions, and gestures via face-to-face interactions. However, the question arises: Can sentiment be accurately identified from unstructured text on social networks? In this study, we demonstrate that it is indeed possible. We applied four machine learning methods—Deep Learning, Decision Trees, Naive Bayes, and Support Vector Machines—in two classification scenarios: cross-validation and training/test sets enhanced by a meta-classifier. Our goal was to identify which combination of classification scenario, learning method, and preprocessing performs best in sentiment analysis. To validate our approach, we used a manually labeled corpus, forming three datasets of different sizes with varying preprocessing techniques. The results underscore the viability and effectiveness of the proposed approach and provide implications for various fields (product development, marketing, political analysis, customer service education, linguistic education).