We present a novel approach - CLAA - for API aspect detection in API reviews that utilizes transformer models trained with a supervised contrastive loss objective function. We evaluate CLAA using performance and impact analysis. For performance analysis, we utilized a benchmark dataset on developer discussions collected from Stack Overflow and compare the results to those obtained using state-of-the-art transformer models. Our experiments show that contrastive learning can significantly improve the performance of transformer models in detecting aspects such as Performance, Security, Usability, and Documentation. For impact analysis, we performed empirical and developer study. On a randomly selected and manually labeled 200 online reviews, CLAA achieved 92% accuracy while the SOTA baseline achieved 81.5%. According to our developer study involving 10 participants, the use of ‘Stack Overflow + CLAA’ resulted in increased accuracy and confidence during API selection. Replication package: https://github.com/disa-lab/Contrastive-Learning-API-Aspect-ASE2023
Wed 13 SepDisplayed time zone: Amsterdam, Berlin, Bern, Rome, Stockholm, Vienna change
10:30 - 12:00 | Program AnalysisResearch Papers / Tool Demonstrations / NIER Track / Journal-first Papers at Room D Chair(s): Domenico Bianculli University of Luxembourg | ||
10:30 12mTalk | An Integrated Program Analysis Framework for Graduate Courses in Programming Languages and Software Engineering Research Papers Prantik Chatterjee Indian Institute Of Technology Kanpur and MathWorks, Pankaj Kumar Kalita IIT Kanpur, Sumit Lahiri Indian Institute Of Technology Kanpur, Sujit Kumar Muduli IIT Kanpur, Vishal Singh Indian Institute of Technology Kanpur, Gourav Takhar Indian Institute of Technology Kanpur, Subhajit Roy IIT Kanpur | ||
10:42 12mTalk | Two Birds with One Stone: Multi-Derivation for Fast Context-Free Language Reachability Analysis Research Papers Chenghang Shi SKLP, Institute of Computing Technology, CAS, Haofeng Li , Yulei Sui University of New South Wales, Sydney, Jie Lu SKLP, Institute of Computing Technology, CAS, Lian Li Institute of Computing Technology at Chinese Academy of Sciences; University of Chinese Academy of Sciences, Jingling Xue UNSW Pre-print File Attached | ||
10:54 12mTalk | NRAgo: Solving SMT(NRA) Formulas with Gradient-based Optimization Tool Demonstrations Minghao Liu Institute of Software at Chinese Academy of Sciences; University of Chinese Academy of Sciences, Kunhang Lv Institute of Software, Chinese Academy of Sciences, Pei Huang Stanford University, Rui Han Institute of Software at Chinese Academy of Sciences; University of Chinese Academy of Sciences, Fuqi Jia Institute of Software at Chinese Academy of Sciences; University of Chinese Academy of Sciences, Yu Zhang Institute of Software, Chinese Academy of Sciences, Feifei Ma Institute of Software at Chinese Academy of Sciences; University of Chinese Academy of Sciences, Jian Zhang Institute of Software at Chinese Academy of Sciences; University of Chinese Academy of Sciences File Attached | ||
11:06 12mTalk | Live Programming for Finite Model Finders NIER Track Allison Sullivan University of Texas at Arlington Pre-print File Attached | ||
11:18 12mTalk | Towards Robustness of Deep Program Processing Models -- Detection, Estimation and Enhancement Journal-first Papers Huangzhao Zhang Peking University, Zhiyi Fu Peking University, Ge Li Peking University, Lei Ma University of Alberta, Zhehao Zhao Peking University, Hua'an Yang Peking University, Yizhe Sun Peking University, Yang Liu Nanyang Technological University, Zhi Jin Peking University Link to publication DOI File Attached | ||
11:30 12mTalk | Precise Data-Driven Approximation for Program Analysis via FuzzingRecorded talk Research Papers Nikhil Parasaram University College London; ConsenSys Diligence, Earl T. Barr University College London; Google DeepMind, Sergey Mechtaev University College London, Marcel Böhme MPI-SP; Monash University Pre-print Media Attached | ||
11:42 12mTalk | Contrastive Learning for API Aspect AnalysisRecorded talk Research Papers G. M. Shahariar Ahsanullah University of Science and Technology, Tahmid Hasan Bangladesh University of Engineering and Technology, Anindya Iqbal Bangladesh University of Engineering and Technology Dhaka, Bangladesh, Gias Uddin York University, Canada Pre-print Media Attached |