Burnout risk detectable from GitHub activity signals months ahead
BurnRiSc: Toward Non-Invasive Burnout Screening in Open Source from Public Repository Signals
Computers and SocietyComputation and Language
Summary
Burnout is a serious problem among open source software maintainers who often have too much work and no one to share it with. The authors created BurnRiSc, a way to spot signs of burnout using publicly available GitHub data like how people code and communicate. Their system looks at signals related to feeling exhausted and disengaged, matching scores to each developer's past behavior. In tests with real cases, it could predict burnout disclosures many months before people spoke up. This suggests burnout can be monitored without needing direct surveys or self-reporting.
What this means in practice
- •For open source project managers: Identify early signs of burnout in maintainers to prevent sudden contributor loss by monitoring GitHub activity patterns.
- •For software engineering team leads: Use public repository signals to gauge team member engagement and exhaustion levels over time without intrusive surveys.
Authors
Timofey Sanko, Yuan Tian, Mariam Guizani
Abstract
Burnout is a chronic occupational syndrome, and open source is close to a worst case for it: maintainers absorb unbounded demand with no manager to reallocate work and no organization to notice decline. The cost is not only personal. Burnout precedes withdrawal, and in projects sustained by a handful of maintainers, one departure can break infrastructure that thousands of downstream systems depend on. Yet the field has no way to see it coming: self-report inventories, the only existing measure, miss exactly the contributors most in need of detection and cannot be applied retroactively, so the field cannot even ask how common burnout is or what helps. We present BurnRiSc, a framework that operationalizes the Oldenburg Burnout Inventory's two dimensions, exhaustion and disengagement, as 14 behavioral and linguistic signals computed from GitHub activity and scored against each contributor's own history. The signals aggregate into two weighted dimension scores, with weights learned from labeled cases, and average into a monthly Burnout Risk Score (BRS). In a preliminary evaluation across 68 contributors in ten repositories (ten disclosed burnout cases, twelve comparable-volume collapses, and 46 comparison contributors), sustained BRS elevation precedes 6 of 10 disclosures by 6-15 months, 8 of 10 when adding peak BRS as a second criterion, and 10 of 10 over any prior time frame. We thus present BurnRiSc as evidence that burnout is screenable from public data.