Recommending GitHub Projects by Leveraging Developers' Social Networks and Genetic Algorithm
Bibliographic record
Abstract
In the uncommon and challenging year 2020, face-to-face collaboration is difficult.In particular, in the domain of software, online collaboration becomes more demanding than ever.As the leading platform of open-source software, GitHub, without a doubt, plays a vital role in hosting over 190 million of projects and fostering collaboration among developers.Developers in GitHub continuously seek new opportunities to contribute to new projects.So far, several researchers have used users' historical activities, textual descriptions of projects or starred items to analyze or infer the interests or programming expertise of developers to offer possible project recommendations.While some research utilized social connections to obtain developers' social importance, none of them have implemented such aspects for generating project recommendations.In this research, we use the latest GHTorrent dataset to construct and propose a GitHub project recommendation system by leveraging Parallel Genetic Algorithm and developers' social networks.To the best of our knowledge, this is the first application of Genetic Algorithm in the GitHub project recommendation area.iii I, Lance PoKai Wang, would like to express my sincere gratitude to my fantastic supervisor, Professor Olga Baysal, for her continuous guidance, advice, and friendly discussions throughout my thesis.Her precise insights and constant effort provided me valuable feedback and support, which made this work successful.I also thank Professor Frank Dehne for his advice and guidance on constructing parallel frameworks and also suggesting to work weights-distributed structure.I am also grateful to Adam Spriggs
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 | 0.001 | 0.009 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.005 | 0.003 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 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".