The participation of women in Science, Technology, Engineering, and Mathematics (STEM) remains shaped by complex social and structural factors. This study investigates public sentiment regarding the role of technology in supporting women’s participation in STEM through a machine learning–based sentiment analysis. Using 1,533 social media comments, sentiment classification was performed by integrating Support Vector Machine (SVM) and VADER-based automatic labeling, with imbalance handling to improve classification reliability. The results indicate a dominance of positive sentiment (98%), suggesting an optimistic tendency within the analyzed dataset, although this may be influenced by dataset characteristics and methodological bias. Among the evaluated models, a linear-kernel SVM achieved the highest accuracy (98.31%). This study contributes methodologically by demonstrating the effectiveness of integrating lexicon-based labeling with supervised learning for public sentiment analysis on gender equality in STEM, offering empirical insights to inform technology-driven policy interventions.