计算机科学 ›› 2026, Vol. 53 ›› Issue (1): 262-270.doi: 10.11896/jsjkx.250100070
贾经冬, 侯鑫, 王哲, 黄坚
JIA Jingdong, HOU Xin, WANG Zhe, HUANG Jian
摘要： 为有效促进App功能迭代,现有大量研究通过挖掘用户评论来改善或增加新功能以促进版本更新,但忽视了从用户评论中识别应该消退的功能。针对此问题,提出了用户数据驱动的App消退功能分析方法。首先从应用市场采集用户评论,构建关键字模板过滤出含消退功能的评论,应用语法范式从中挖掘功能短语,并训练分类器识别功能短语以提取出待研究的消退功能,从而构建消退功能数据集。根据版本更新日志和用户评论回溯找到消退功能的生命周期。然后进行消退功能生命周期的用户评论分析。基于文本情感分析,提出字数权重阈值法对虚假评分进行检测和更正,运用BERT进行评论文本分类,提出BERTopic-Corex主题模型产生主题词,结合之前的分析结果和评论字数识别出关键用户评论,实现了从用户评论中有效分析和识别消退功能。实验结果和实例证明了所提方法的可行性和有效性。
中图分类号:
| [1]DABROWSKI J,LETIER E,PERINI A,et al.Analysing App reviews for software engineering:a systematic literature review[J].Empirical Software Engineering,2022,27(2):43. [2]XIAO J M,CHEN S Z,FENG Z Y,et al.Anautomatic analysis of user revews method for App evolution and maintenance[J].Chinese Journal of Computers,2020,43(11):2184-2202. [3]WANG Y,ZHENG L W,ZHANG Y Y,et al.Softwarerequirements mining method for chinese App user review data[J].Computer Science,2020,47(12):56-64. [4]HU T Y,JIANG Y.Mining of user’s comments reflecting usage feedback for App software[J].Journal of Software,2019,30(10):3168-3185. [5]YAO Y M,JIANG W Y,WANG Y L,et al.Non-functional requirements analysis based on application reviews in the Android App market[J].Information Resources Management Journal,2022,35(2):1-17. [6]JHA N,MAHMOUD A.Mining non-functional requirementsfrom App store reviews[J].Empirical Software Engineering,2019,24(5):1-37. [7]FU S H,XUE K K,YANG M Y,et al.An exploratory study on users’ resestance to mobile App updates:Using netnography and fsQCA[J].Technological Forecasting and Social Change,2023,191(6):122479. [8]HUNGER T,ARNOLD M,PESTINGER R.Risks and requirements in sustainable App development-a review[J].Sustainability,2023,15(8):7018. [9]DE LIMA V M A,DE ARAUJO A F,MARCACINI R M.Temporal dynamics of requirements engineering from mobile App reviews[J].PeerJ Computer Science,2022,8(2):e874. [10]NAYEBI M,KUZNETSOV K,CHEN P.Anatomy of functionality deletion:an exploratory study on mobile Apps[C]//International Conference on Mining Software Repositories(MSR).2018:243-253. [11]MAALEJ W,KERTANOVIC Z,NABIL H,et al.On the automatic classification of App reviews[J].Requirements Enginee-ring,2016,21:311-331. [12]BISWAS M,ANISH P R,GHAISAS S.Interpretable Appre-view classification with tansformers[C]//International Requirements Engineering Conference Workshops(RE).2024:26-34. [13]AL KILANI N,TAILAKH R,HANANI A.Automatic classification of Apps reviews for requirement engineering:exploring the customers need from healthcare Applications[C]//International Conference on Social Networks Analysis,Management and Security(SNAMS).2019:541-548. [14]MEMON Z A,MUNAWAR N,KAMAL M.App store mining for feature extraction:analyzing user reviews[J].Acta Scientiarum Technology,2023,46(1):e62867. [15]SUPRAYOGI E,BUDI I,MAHENDRA R.Information Extraction for Mobile Application User Review[C]//International Conference on Advanced Computer Science and Information Systems(ICACSIS).2018:343-348. [16]TANG X Z,TIAN H Y,KONG P F,et al.App review driven collaborative bug finding[J].Empirical Software Engineering,2024,29(5):124. [17]KEERTIPATI S,SAVARIMUTHU B T R,LICORISH S A.Approaches for prioritizing feature improvements extracted from App reviews[C]//International Conference on Evaluation and Assessment in Software Engineering(EASE).2016:1-6. [18]CHEN N,LIN J,HOI S C H,et al.AR-miner:mining informative reviews for developers from mobile App marketplace[C]//International Conference on Software Engineering(ICSE).2014:767-778. [19]PALOMBA F,SALZA P,CIURUMELEA A,et al.Recommending and localizing change requests for mobile Apps based on user reviews[C]//International Conference on Software Enginee-ring(ICSE).,2017:106-117. [20]GAO C Y,ZENG J C,LO D,et al.Understanding in-App advertising issues based on large scale App review analysis[J].Information and Software Technology,2022,142(1):106741. [21]GAO H C,GUO C K,BAI G D,et al.Sharing runtime permission issues for developers based on similar-App review mining[J].Journal of Systems and Software,2022,184(1):111118. [22]SARRO F,AI-SUBAIHIN A A,HARMAN M,et al.Featurelifecycles as they spread,migrate,remain,and die in App stores[C]//International Requirements Engineering Conference(RE).2015:76-85. [23]MURPHY-HILL E,ZIMMERMANN T,BIRD C,et al.The design of bug fixes[C]//International Conference on Software Engineering.IEEE,2013:332-341. [24]GUZMAN E,OLIVEIRA L,STEINER Y,et al.User feedback in the App store:a cross-cultural study[C]//International Conference on Software Engineering.2018:13-22. [25]MALGAONKAR S,LICORISH S A,SAVARIMUTHU B TR.Prioritizinguser concerns in App reviews:a study of requests for new features enhancements and bug fixes[J].Information and Software Technology,2022,142(1):106798. [26]NAYEBI M,KUZNETSOV K,ZELLER A,et al.Recommending and release planning of user-driven functionality deletion for mobile apps[J].Requirements Engineering,2024,29:459-480. [27]GU X,KIM S.What parts of your Apps are loved by users?[C]//International Conference on Automated Software Engineering(ASE).2015:760-770. [28]WU H Y,DENG W J,NIU X T,et al.Identifying key features from App user reviews[C]//International Conference on Software Engineering(ICSE).2021:922-932. [29]MARTENS D,MAALEJ W.Towards understanding and detecting fake reviews in App stores[J].Empirical Software Engineering,2019,24(6):3316-3355. [30]HE D J,PAN M H,HONG K,et al.Fakereview detection based on pu learning and behavior density[J].IEEE Network,2020,34(4):298-303. [31]WANG X H,ZHANG T,TAN Y H,et al.How to effectively mine App reviews concerning software ecosystem?A survey of review characteristics[J].Journal of Systems and Software,2024,213(1):112040. [32]GROOTENDORST M.BERTopic:neural topic modeling with a class-based TF-IDF procedure[J].arXiv:2203.05794,2022. [33]GALLAGHER R J,REING K,KALE D,et al.Anchored correlation explanation:Topic modeling with minimal domain know-ledge[J].Transactions of the Association for Computational Linguistics,2017,5(5):529-542. |
|
||
首页