Towards a Dataset to Assess Conversational Agent's Efficacy in Mentoring Newcomer Developers

Misan Paul Etchie, Hunter Beach, Katia Felizardo, Igor Steinmacher

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Many Open Source Software (OSS) maintainers experience burnout due to the constant need to support and answer questions posed by newcomer developers. This leads to slower response times, and unanswered questions which discourage newcomers and hinder community growth. Research indicates that conversational agents trained on community data can answer common questions, thus reducing maintainers' work-load. However, conversational agents should only be used if they are useful to newcomers. To help prove a conversational agent can be useful, we manually curated a dataset of questions posted to the JabRef issue tracker and Gitter, submitted by newcomers. This dataset of questions will be invaluable for conducting studies using LLMs to support newcomers. This dataset paper details our collection process, describes the data, and offers reflections on future research.

Original languageEnglish (US)
Title of host publicationProceedings - 2025 IEEE/ACM International Workshop on Bots in Software Engineering, BotSE 2025
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages48-52
Number of pages5
ISBN (Electronic)9798331527082
DOIs
StatePublished - 2025
Event6th IEEE/ACM International Workshop on Bots in Software Engineering, BotSE 2025 - Ottawa, Canada
Duration: Apr 27 2025 → …

Publication series

NameProceedings - 2025 IEEE/ACM International Workshop on Bots in Software Engineering, BotSE 2025

Conference

Conference6th IEEE/ACM International Workshop on Bots in Software Engineering, BotSE 2025
Country/TerritoryCanada
CityOttawa
Period4/27/25 → …

Keywords

  • Dataset
  • Human-Bot Collaboration
  • Newcomers
  • Open Source Software

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Science Applications
  • Software

Fingerprint

Dive into the research topics of 'Towards a Dataset to Assess Conversational Agent's Efficacy in Mentoring Newcomer Developers'. Together they form a unique fingerprint.

Cite this