Software analytics has been the subject of considerable recent attention but is yet to receive significant industry traction. One of the key reasons is that software practitioners are reluctant to trust predictions produced by the analytics machinery without understanding the rationale for those predictions. While complex models such as deep learning and ensemble methods improve predictive performance, they have limited explainability. In this paper, we argue that making software analytics models explainable to software practitioners is as important as achieving accurate predictions. Explainability should therefore be a key measure for evaluating software analytics models. We envision that explainability will be a key driver for developing software analytics models that are useful in practice. We outline a research roadmap for this space, building on social science, explainable artificial intelligence and software engineering.
Wed 30 MayDisplayed time zone: Amsterdam, Berlin, Bern, Rome, Stockholm, Vienna change
16:00 - 17:30 | Mining, Verifying, and LearningNIER - New Ideas and Emerging Results at E3 room Chair(s): Mukul Prasad Fujitsu Laboratories of America | ||
16:00 15mTalk | Mining Container Image Repositories---MSR for Software Configurations and Beyond NIER - New Ideas and Emerging Results Tianyin Xu University of Illinois at Urbana-Champaign, Darko Marinov University of Illinois at Urbana-Champaign Pre-print | ||
16:15 15mTalk | Explainable Software Analytics NIER - New Ideas and Emerging Results Pre-print | ||
16:30 15mTalk | Generalizing Specific-Instance Interpolation Proofs with SyGuS NIER - New Ideas and Emerging Results | ||
16:45 15mTalk | Efficient Parametric Model Checking Using Domain-Specific Modelling Patterns NIER - New Ideas and Emerging Results | ||
17:00 15mTalk | Deep Learning UI Design Patterns of Mobile Apps NIER - New Ideas and Emerging Results | ||
17:15 15mShort-paper | Code Review Comments: Language matters NIER - New Ideas and Emerging Results Vasiliki Efstathiou Athens University of Economics and Business, Diomidis Spinellis Athens University of Economics and Business DOI Pre-print |