Engaging with AI: An Exploratory Study on Developers' Sharing and Reactions to ChatGPT in GitHub Pull Requests
Bibliographic record
Abstract
ChatGPT, as a representative Foundation Model (FM)-powered tool, has demonstrated significant potential in assisting developers with various software engineering tasks, such as code generation, program repair, and test creation. However, the timing of developers seeking assistance from ChatGPT and their perceptions of ChatGPT-generated content remain underexplored. In this paper, we analyze a dataset comprising 211 developers' shared conversations with ChatGPT within GitHub Pull Requests (PRs). Our study investigates the events in the GitHub PR timeline that precede these shared conversations, the sentiments expressed by developers when sharing these conversations, and the reactions from other developers to PR comments and descriptions that include shared conversations with ChatGPT. Our key findings are: (1) Shared conversations with ChatGPT are posted after seven distinct types of pull request timeline events, with the most frequent being comments added, PR creation, and review requests. (2) Positive sentiment is the most prevalent among developers when sharing these conversations, followed by neutral and negative sentiments. Developer reactions to comments and PR descriptions containing shared conversations are generally sparse; when they do occur, the most common reactions are (thumbs up), (heart), and (eyes). These findings provide new insights into how developers incorporate FM-powered tools into their collaborative software development workflows.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".