Open AccessHot question prediction in Stack Overflow
Author(s) -
Zhao Li Xian,
Zhang Li,
Jiang Jing
Publication year - 2021
Publication title -
iet software
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.305
H-Index - 43
eISSN - 1751-8814
pISSN - 1751-8806
DOI - 10.1049/sfw2.12013
Subject(s) - test set , set (abstract data type) , test (biology) , baseline (sea) , computer science , machine learning , hot spot (computer programming) , artificial intelligence , plan (archaeology) , stack (abstract data type) , programming language , history , paleontology , oceanography , archaeology , biology , geology
Stack Overflow is a very popular programming question and answer community. Some questions become hot, and receive high views, which are of widespread concern to developers. Finding hot questions early can give priority to recommend potential hot questions to answers, thereby shortening the response time. Besides, the hot question prediction is also helpful for making advertising plan, planning advertising campaigns and estimating costs. Therefore, it is important to predict hot questions. The authors propose the VSAF method which analyses the V iew amount changes, A nswer amount changes and S core changes soon after questions' creation based on F ully convolutional neural network. The performance of the VSAF method based on a training set and two different test sets has been evaluated. The training set has 1600 hot questions and 1600 cold questions. The random test set has 381 hot questions and 2819 cold questions, while the balanced test set has 400 hot questions and 400 cold questions. The experimental results show that using the balanced test set, VSAF achieves Accuracy, F 1 hot and F 1 cold of 80%, 77.77% and 81.81%, which outperforms the baseline approach by 25.59%, 21.52% and 29.04%, respectively. Using the random test set for evaluation, VSAF achieves Accuracy , F 1 hot and F 1 cold of 84.91%, 53.96% and 90.97%, which outperforms the baseline approach by 31.83%, 84.16% and 19.35%, respectively. The VSAF method significantly outperforms the state‐of‐the‐art approach on hot question prediction.