Summarizing Developer Chat Conversations

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.

Name thesis:degree_name

Master of Computer Science (M.C.S.)

Level thesis:degree_level

Master's

Discipline thesis:degree_discipline

Computer Science

Grantor dc:publisher

Carleton University

Year dc:date.issued

2022

Author dc:creator

• Prasanna Kumar, Lakshmi

Statement dc:rights

• Copyright © 2022 the author(s). Theses may be used for non-commercial research, educational, or related academic purposes only. Such uses include personal study, research, scholarship, and teaching. Theses may only be shared by linking to Carleton University Institutional Repository and no part may be used without proper attribution to the author. No part may be used for commercial purposes directly or indirectly via a for-profit platform; no adaptation or derivative works are permitted without consent from the copyright owner.

Language dc:language.iso

en

DOI

10.22215/etd/2022-15247

OAI identifier oai:identifier

oai:carleton.scholaris.ca:20.500.14718/41941