Detecting Speech Act Types in Developer Question/Answer Conversations During Bug Repair

TL;DR

This study investigates speech act detection in developer bug repair conversations, creating a dataset and training a classifier to improve virtual assistant capabilities in software engineering.

Contribution

It introduces a new annotated dataset of developer conversations and develops an automated method for detecting speech act types in bug repair discussions.

Findings

Achieved 69% precision in speech act detection

Identified 26 speech act types in developer conversations

Collected 2459 annotations across 30 conversations

Abstract

This paper targets the problem of speech act detection in conversations about bug repair. We conduct a "Wizard of Oz" experiment with 30 professional programmers, in which the programmers fix bugs for two hours, and use a simulated virtual assistant for help. Then, we use an open coding manual annotation procedure to identify the speech act types in the conversations. Finally, we train and evaluate a supervised learning algorithm to automatically detect the speech act types in the conversations. In 30 two-hour conversations, we made 2459 annotations and uncovered 26 speech act types. Our automated detection achieved 69% precision and 50% recall. The key application of this work is to advance the state of the art for virtual assistants in software engineering. Virtual assistant technology is growing rapidly, though applications in software engineering are behind those in other areas, largely due to a lack of relevant data and experiments. This paper targets this problem in the area of developer Q/A conversations about bug repair.