In recent years there is an unprecedented growth in online communication and collaborative platforms like Slack, Discord, Microsoft Teams,etc. These platforms facilitate communication among developers all over the world and allow distributed software development. Software developers rely on these platforms to discuss their projects and to seek technical help. It is challenging to summarize these chat messages due to their short size, unstructured and colloquial format. This thesis is an attempt to tackle this problem by applying topic modeling techniques to generate discussion summaries. We use a dataset extracted from the Discord chat conversations and evaluate four topic modeling techniques to identify the primary topics discussed. We evaluate different embedding models and study their impact on the performance of the topic modeling technique. We perform an extensive analysis of the topics per month and also study evolution of the topics over a period of one year.