The rapid expansion of digital communication has fueled widespread adoption of social media platforms such as X, Facebook, and Instagram, creating vast data lakes for business organizations. These platforms offer valuable customer insights, enabling companies to refine their market strategies. One industry that stands to benefit significantly from this social media-driven intelligence is telecommunications. This study aims to analyze customer sentiments and identify key discussion topics for a telecommunication company using data from X. Employing natural language processing (NLP) and machine learning (ML) techniques, the research extracted and processed 4117 tweets to classify sentiments and uncover key themes. Five supervised ML models—Naïve Bayes, Support Vector Machine (SVM), Random Forest, Logistic Regression, and Gradient Boost were tested for sentiment classification. The models achieved an average accuracy of 86%, with SVM outperforming the rest at 85%. The F1-score, a measure of precision-recall balance, was 87% for SVM, making it the most effective sentiment classifier. Latent Dirichlet Allocation (LDA) was applied to extract key discussion topics, revealing 15 dominant themes. Key topics included network issues, SIM card inquiries, data and airtime usage, device-related con- cerns, and technical support. These findings highlight the importance of combining sentiment analysis with topic modeling to derive more meaningful business intelligence from social media data.