‘Who built this crap?’ Developing a Software Engineering Domain Specific Toxicity Detector
Since toxicity during developers’ interactions in open source software (OSS) projects show negative impacts on developers’ relation, a toxicity detector for the Software Engineering (SE) domain is a need. However, prior studies found that contemporary toxicity detection tools failed their reliability with the SE texts by achieving a poor performance. To encounter this challenge, I have developed ToxiCR, a SE-specific toxicity detector that is evaluated with manually labeled 19,571 code review comments. I evaluate ToxiCR with different combinations of ten supervised learning models, five text vectorizers, and eight preprocessing techniques (two of them are SE domain-specific). After applying all possible combinations, I have found that ToxiCR significantly outperformed existing toxicity classifiers with accuracy of 95.8% and an 𝐹1_1 score of 88.9%
Tue 11 OctDisplayed time zone: Eastern Time (US & Canada) change
15:30 - 16:00 | |||
15:30 30mPoster | ASTOR: An Approach to Identify Security Code Reviews Student Research Competition Rajshakhar Paul Wayne State University | ||
15:30 30mPoster | ‘Who built this crap?’ Developing a Software Engineering Domain Specific Toxicity Detector Student Research Competition Jaydeb Sarker Department of Computer Science, Wayne State University Pre-print | ||
15:30 30mPoster | Automatically Fixing Breaking Changes of Data Science Libraries Student Research Competition Hailie Mitchell Carnegie Mellon University | ||
15:30 30mPoster | Execution Path Detection through Dynamic Analysis in Black-Box Testing Environments Student Research Competition Frank Whitworth Wake Forest University | ||
15:30 30mPoster | Automatic Software Timing Attack Evaluation & Mitigation on Clear Hardware Assumption Student Research Competition Prabuddha Chakraborty University of Florida | ||
15:30 30mPoster | Automatically Tagging the “AAA" Pattern in Unit Test Cases Using Machine Learning Models Student Research Competition Chenhao Wei Stevens Institute of Technology, Lu Xiao Stevens Institute of Technology, Tingting Yu University of Cincinnati, Xinyu Chen HSBC Software Development (Guangdong) Limited, Xiao Wang Stevens Institute of Technology, Sunny Wong Envestnet, Abigail Clune AGI | ||
15:30 30mPoster | A Unified Specification Mining Framework for Smart Contracts Student Research Competition Ye Liu Nanyang Technological University | ||
15:30 30mPoster | Identifying Sexism and Misogyny in Pull Request Comments Student Research Competition Sayma Sultana Wayne State University | ||
15:30 30mPoster | Detecting Inconsistencies in If-Condition-Raise Statements Student Research Competition Islem BOUZENIA Software Lab, University of Stuttgart | ||
15:30 30mPoster | Software Evolution Management with Differential Facts Student Research Competition Xiuheng Wu Nanyang Technological University, Singapore | ||
15:30 30mPoster | RESTCluster: Automated Crash Clustering for RESTful API Student Research Competition Yi Liu Nanyang Technological University | ||
