Using clarification questions to improve software developers’ Web search

Context: Recent research indicates that Web queries written by software developers are not very successful in retrieving relevant results, performing measurably worse compared to general purpose queries. Most approaches up this point have addressed problem with engineering-specific automated query reformulation techniques, which work without developer involvement but limited the content of original query. In other words, these techniques automatically improve existing can contribute new, previously unmentioned, concepts. Objective: paper, we propose a technique guide manually improving their own search We examine conversational approach follows unsuccessful clarification question aimed at eliciting additional terms, thus providing clear dimension along could be improved. Methods: describe set questions derived from corpus and neural recommending them for newly issued Results: Our evaluation recommendation is accurate, predicting valid 80% time outperforms simple baselines, as well as, state-of-the-art Learning To Rank (LTR) baselines. Conclusion: As shown experimental described capable appropriate considered useful sample ranging novices experienced professionals.