Research

Last update: August 2026

My work connects artificial intelligence (AI), software engineering, and computer‑supported cooperative work (CSCW).

Current research themes

01

Human-AI collaboration in software engineering

Effective AI tools should strengthen human judgment, learning, and collaboration—not merely automate tasks.

Selected Findings
  • Project-grounded agents nearly match humans at answering developer questions, but need briefer responses [ICSE’26].
  • Developer–AI tools should offer varied interaction styles while preserving user control and trust [FORGE’25, ICSE’25].
  • Workflow-integrated conversational support reduces challenges for machine-learning end-user programmers [ICSE’24].
  • Code-review bots increase merges but reduce discussion; GitHub Actions introduce tradeoffs [EMSE’22, EMSE’23].
  • Context-appropriate chatbot language improves credibility and user experience [TOCHI’22].
02

Supporting Open Source Software (OSS) communities

Sustainable OSS communities depend on equitable participation, supportive social practices, and a genuine sense of belonging.

Selected Findings
  • OSS newcomers benefit from barrier-aware onboarding, mentors, and suitable tasks [CSCW’15, ICSE’16, EMSE’23, IST’24, CHASE’25].
  • Timely, context-specific interventions help prevent long-term contributor disengagement [EMSE’22, TOSEM’25].
  • Redesigned OSS tools can remove gender-biased barriers for women newcomers [TSE’20].
  • Women’s contributions are accepted at comparable rates, yet social barriers and underrepresentation persist [TOSEM’22].
  • Flexible work, equitable recognition, mentorship, and visible role models improve women’s retention [ICSE SEIS’22].
  • Motivations evolve, and OSS success extends beyond code contributions [ICSE’21, TSE’21].
  • Social connection and intrinsic motivation strengthen belonging in OSS communities [ICSE’23].
  • Interpersonal barriers reduce belonging, especially for gender minorities and disabled contributors [ICSE’25].
03

Computer science and software engineering education

Effective computing education combines evidence-based pedagogy, authentic software projects, structured guidance, and deliberate support for learning with AI.

Selected Findings
  • GenAI helps with low-risk questions, but guidance prevents shallow learning and overreliance [ICSE’24, CUI’25, CSEE&T’25].
  • Gamified scaffolding makes OSS contribution more approachable and engaging [VL/HCC’24, CSEE&T’25].
  • Authentic OSS projects build technical and social skills but require structured guidance [CSEE&T’17, FSE’25].
  • Programming instructors need pedagogical knowledge beyond technical content [ITiCSE’19, FIE’19].
  • Students and instructors perceive programming challenges differently [IEEE LATAM’17].

Research approach

  • Pragmatism Methods tailored to each problem and context, combining quantitative and qualitative approaches when useful.
  • Engineering Real-world problems addressed through purpose-built tools and applications.
  • Innovation New ideas and alternative ways of framing problems.
  • Quality Rigor and quality throughout the research process.
  • Multiple areas Knowledge across domains connected to uncover new problems and opportunities.

Earlier research projects

  • Groupware Workbench: A component-based product line for developing collaborative systems
  • Arquigrafia: a social network for architecture and urbanism
  • Smart Audio City Guide: a mobile application for blind people
  • MetricMiner: a web-based tool for mining software repositories
  • AulaNet: computer supported collaborative learning

View selected publications