Time-Series Snapshot Network for Partner Recommendation: A Case Study on OSS

The last decade has witnessed the rapid growth of open-source software (OSS). Still, all contributors may find it difficult to assimilate into OSS community even they are enthusiastic make contributions. We thus suggest that partner recommendation across different roles benefit both users and developers, i.e., once we able successful for those in need, dramatically contribute productivity developers enthusiasm users, further boosting projects’ development. Motivated by this potential, model as link prediction task from email data via network embedding methods. In article, introduce time-series snapshot (TSSN) is a mixture interactions among developers. Based on established TSSN, perform temporal biased walk (TBW) automatically capture structural information network, behavioral similarity between individuals network. Experiments ten Apache sets demonstrate proposed TBW significantly outperforms number advanced random walk-based methods, leading state-of-the-art performance.