Is AI different for SE?
Year: 2019
Type: report
Abstract: What AI tools are needed for SE? Ideally, we should have simple rules that peek at data, then say "use this tool" or "use that tool".To nd such a rule, we explored 120 dierent data sets addressing numerous problems, including bad smell detection, predicting Github issue close time, bug report analysis, defect prediction and dozens of other non-SE problems.To this data, we apply a SE-based tool that (a) out-performs the state-of-the-art for these SE problems yet (b) fails very badly on standard AI problems.In those results, we can nd a simple rule for when to use/avoid the SE-based tool.SE data is often about infrequent issues, like the occasional defect, or the rarely exploited security violation, or the requirement that holds for one special case.But as we show, standard AI tools work best when the target is relatively more frequent.Also, we can exploit this special properties of SE, to great eect (to rapidly nd better optimizations for SE tasks via a tactic called "dodging", explained in this paper).More generally, this result says we need a new kind of SE research for developing new AI tools that are more suited to SE problems.
Author: Menzies, Tim
Institution: North Carolina State University
Language: English
Subfield: Information Systems
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W7066769758
