
软件问答社区的问题删除预测方法
*
蒋竞,苗萌,赵丽娴,张莉
(北京航空航天大学计算机学院,北京100191)
通信作者:张莉,lily@buaa.edu.cn
摘 要:StackOverflow是最受欢迎的软件问答社区之一,用户可以在该网站发布问题并得到其他用户的回答.为
了保证问题质量,网站需要尽快发现并删除低质量或者不符合社区主题的问题.当前,StackOverflow主要采用人
工检查的方式发现需要被删除的问题.然而这种方式往往不能保证问题被及时发现、删除,而且加重了社区管理
员的负担.为了快速发现需要删除的问题,提出了自动化预测问题删除的方法MulPredictor.该方法提取问题的语
义内容特征、语义统计特征和元特征,使用随机森林分类器计算问题会被删除的概率.实验结果表明:与现有方法
DelPredictor和NLPPredictor相比,MulPredictor的准确率在平衡测试集上分别提升了16.34%和12.78%,在随机
测试集上分别提升了12.38%和14.14%.此外,分析了影响问题删除的重要特征,发现代码段、问题的标题和正文
第1段的特征对问题删除有重要的影响.
关键词:问题删除预测;问题质量;问题分类;软件问答社区;StackOverflow
中图法分类号:TP311
中文引用格式:蒋竞,苗萌,赵丽娴,张莉.软件问答社区的问题删除预测方法.软件学报,2022,33(5):1699–1710.http://www.jos.
org.cn/1000-9825/6556.htm
英文引用格式:JiangJ,MiaoM,ZhaoLX,ZhangL.PredictionMethodforQuestionDeletioninSoftwareQuestionandAnswer
Community.RuanJianXueBao/JournalofSoftware,2022,33(5):1699–1710(inChinese).http://www.jos.org.cn/1000-9825/6556.htm
Prediction Method for Question Deletion in Software Question and Answer Community
JIANGJing,MIAOMeng,ZHAOLi-Xian,ZHANGLi
(SchoolofComputerScienceandEngineering,BeihangUniversity,Beijing100191,China)
Abstract:Stack Overflow is one of the most popular software question and answer communities, where users can post questions and
receive answers from others. In order to ensure the quality of questions, the website needs to promptly discover and delete questions with
low quality or not conforming to the community’s theme. Currently, Stack Overflow mainly relies on manual inspection to find questions
that need to be deleted. However, this way usually hardly guarantees to discover and delete questions in time, and increases the burden of
community administrators. In order to quickly find questions that need to be deleted, this study proposes a method to automatically predict
question deletion, which is named MulPredictor. This method extracts the semantic content features, the semantic statistical features and
the meta features of a question, and uses the random forest classifier to calculate the probability that it will be deleted. Experimental
results showed that, compared with existing methods DelPredictor and NLPPredictor, MulPredictor increases the accuracy by 16.34% and
12.78% on balanced test set, and increases the accuracy by 12.38% and 14.14% on random test set. In addition, this study also analyzes
important features in question deletion, and finds that the code segment, the question’s title, and the first paragraph of the question’s body
havethemostsignificantimpactsonquestiondeletion.
Key words:predictionofquestiondeletion;questionquality;questionclassification;softwarequestionandanswercommunity;StackOverflow
*
基金项目:科技创新2030-“新一代人工智能”重大项目(2018AAA0102304);国家自然科学基金(62177003);中央高校基本科研业务费
(YWF-20-BJ-J-1018)
本文由“领域软件工程”专题特约编辑汤恩义副教授、江贺教授、陈俊洁副教授、李必信教授以及唐滨副教授推荐.
收稿时间:2021-08-10;修改时间:2021-10-09;采用时间:2022-01-10;jos在线出版时间:2022-01-28
软件学报ISSN1000-9825,CODENRUXUEW E-mail:jos@iscas.ac.cn
Journal of Software,2022,33(5):1699−1710[doi:10.13328/j.cnki.jos.006556] http://www.jos.org.cn
©中国科学院软件研究所版权所有. Tel:+86-10-62562563
评论