Analysis and Detection of Information Types of Open Source Software Issue Discussions
Bibliographic record
Abstract
Most modern Issue Tracking Systems (ITSs) for open source software (OSS) projects allow users to add comments to issues. Over time, these comments accumulate into discussion threads embedded with rich information about the software project, which can potentially satisfy the diverse needs of OSS stakeholders. However, discovering and retrieving relevant information from the discussion threads is a challenging task, especially when the discussions are lengthy and the number of issues in ITSs are vast. In this paper, we address this challenge by identifying the information types presented in OSS issue discussions. Through qualitative content analysis of 15 complex issue threads across three projects hosted on GitHub, we uncovered 16 information types and created a labeled corpus containing 4656 sentences. Our investigation of supervised, automated classification techniques indicated that, when prior knowledge about the issue is available, Random Forest can effectively detect most sentence types using conversational features such as the sentence length and its position. When classifying sentences from new issues, Logistic Regression can yield satisfactory performance using textual features for certain information types, while falling short on others. Our work represents a nontrivial first step towards tools and techniques for identifying and obtaining the rich information recorded in the ITSs to support various software engineering activities and to satisfy the diverse needs of OSS stakeholders.
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 machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.006 | 0.044 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.010 | 0.005 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.002 | 0.003 |
| Open science | 0.001 | 0.002 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.001 |
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 source (direct Gemma or distilled Codex), 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".