Vitomir Kovanovi ́c presents research on automating the analysis of cognitive presence in online discussions using machine learning. The Community of Inquiry model identifies three presences (social, cognitive, teaching) but current analysis is labor-intensive. The research aims to develop an automated content analysis system to code messages for cognitive presence phases more efficiently. An SVM classifier was trained on manually coded discussion messages, achieving a Cohen's kappa of 0.42, outperforming an existing neural network approach. Further improving the model to incorporate thread context could help account for stages of discussion and individual students' learning progress.