{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,21]],"date-time":"2025-10-21T00:27:32Z","timestamp":1761006452202,"version":"build-2065373602"},"reference-count":50,"publisher":"PeerJ","license":[{"start":{"date-parts":[[2025,10,20]],"date-time":"2025-10-20T00:00:00Z","timestamp":1760918400000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100004055","name":"King Fahd University of Petroleum and Minerals","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100004055","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"abstract":"<jats:p>Software application users often submit numerous enhancement reports (ERs) requesting new features, but only a small fraction are deemed feasible and approved. Recent methods have attempted to automate the identification of feasible ERs, primarily using textual descriptions and traditional machine learning (ML) techniques. This article proposes a deep learning (DL) approach that significantly improves performance by integrating both textual (summary, sentiment) and non-textual metadata (reporter and module statistics) into a unified representation. Textual features are encoded using Bidirectional Encoder Representations from Transformers (BERT), while sentiment is computed using Senti4SD, a tool designed for sentiment analysis in software engineering. Non-textual features are derived from reporter and module histories to provide behavioral context. These features are concatenated and fed into a DL-based binary classifier. Experiments on a publicly available dataset show that the proposed approach substantially outperforms previous methods, improving accuracy from 82.38% to 94.02% and F1-score from 85.03% to 94.26%. The results highlight the effectiveness of combining semantic, affective, and behavioral features in predicting feasible ERs.<\/jats:p>","DOI":"10.7717\/peerj-cs.3290","type":"journal-article","created":{"date-parts":[[2025,10,20]],"date-time":"2025-10-20T08:51:46Z","timestamp":1760950306000},"page":"e3290","source":"Crossref","is-referenced-by-count":0,"title":["Bidirectional encoder representations from transformers (BERT) driven approach for identifying feasible software enhancements"],"prefix":"10.7717","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0237-3025","authenticated-orcid":true,"given":"Qasim","family":"Umer","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"4443","published-online":{"date-parts":[[2025,10,20]]},"reference":[{"key":"10.7717\/peerj-cs.3290\/ref-1","first-page":"167","article-title":"Bug fix-time prediction model using na\u00efve Bayes classifier","author":"Abdelmoez","year":"2012"},{"key":"10.7717\/peerj-cs.3290\/ref-2","first-page":"106","article-title":"SentiCR: a customized sentiment analysis tool for code review interactions","author":"Ahmed","year":"2017"},{"key":"10.7717\/peerj-cs.3290\/ref-3","first-page":"112","article-title":"Bug reports prioritization: which features and classifier to use?","volume":"2","author":"Alenezi","year":"2013"},{"issue":"3","key":"10.7717\/peerj-cs.3290\/ref-4","doi-asserted-by":"publisher","first-page":"111898","DOI":"10.1016\/j.jss.2023.111898","article-title":"BERT based severity prediction of bug reports for the maintenance of mobile applications","volume":"208","author":"Ali","year":"2023","journal-title":"Journal of Systems and Software"},{"key":"10.7717\/peerj-cs.3290\/ref-5","first-page":"183","article-title":"A contextual approach towards more accurate duplicate bug report detection","author":"Alipour","year":"2013"},{"key":"10.7717\/peerj-cs.3290\/ref-6","first-page":"23:304\u201323:318","article-title":"Is it a bug or an enhancement?: a text-based approach to classify change requests","author":"Antoniol","year":"2008"},{"key":"10.7717\/peerj-cs.3290\/ref-7","article-title":"Assisting bug report triage through recommendation. PhD Thesis, University of British Columbia","author":"Anvik","year":"2007"},{"key":"10.7717\/peerj-cs.3290\/ref-8","doi-asserted-by":"publisher","first-page":"110245\u2013110259","DOI":"10.1109\/ACCESS.2023.3322101","article-title":"BERT based sentiment analysis for low-resourced languages: a case study of Urdu language","volume":"11","author":"Ashraf","year":"2023","journal-title":"IEEE Access"},{"key":"10.7717\/peerj-cs.3290\/ref-9","doi-asserted-by":"crossref","DOI":"10.1145\/3379177.3388904","article-title":"Action-based recommendation in pull-request development","author":"Azeem","year":"2020"},{"key":"10.7717\/peerj-cs.3290\/ref-10","article-title":"SentiWordNet 3.0: an enhanced lexical resource for sentiment analysis and opinion mining. In: Proceedings of LREC, 10","author":"Baccianella","year":"2010"},{"key":"10.7717\/peerj-cs.3290\/ref-11","first-page":"74","article-title":"Automated duplicate bug report classification using subsequence matching","author":"Banerjee","year":"2012"},{"issue":"3","key":"10.7717\/peerj-cs.3290\/ref-12","doi-asserted-by":"publisher","first-page":"1352","DOI":"10.1007\/s10664-017-9546-9","article-title":"Sentiment polarity detection for software development","volume":"23","author":"Calefato","year":"2018","journal-title":"Empirical Software Engineering"},{"key":"10.7717\/peerj-cs.3290\/ref-13","first-page":"1","article-title":"Determining bug severity using machine learning techniques","author":"Chaturvedi","year":"2012"},{"key":"10.7717\/peerj-cs.3290\/ref-14","doi-asserted-by":"publisher","first-page":"122412\u2013122424","DOI":"10.1109\/access.2021.3108624","article-title":"Convolutional neural network based approval prediction of enhancement reports","volume":"9","author":"Cheng","year":"2021","journal-title":"IEEE Access"},{"issue":"5","key":"10.7717\/peerj-cs.3290\/ref-15","doi-asserted-by":"publisher","first-page":"1315","DOI":"10.26483\/ijarcs.v8i5.3559","article-title":"Neural network based bug priority prediction model using text classification techniques","volume":"8","author":"Choudhary","year":"2017","journal-title":"International Journal of Advanced Research in Computer Science"},{"key":"10.7717\/peerj-cs.3290\/ref-16","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805","article-title":"BERT: pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018"},{"key":"10.7717\/peerj-cs.3290\/ref-17","doi-asserted-by":"crossref","first-page":"709","DOI":"10.1007\/978-3-642-37401-2_69","article-title":"Practical duplicate bug reports detection in a large web-based development community","volume-title":"Web Technologies and Applications","author":"Feng","year":"2013"},{"key":"10.7717\/peerj-cs.3290\/ref-18","first-page":"147","article-title":"Email filtering based on supervised learning and mutual information feature selection","author":"Gad","year":"2015"},{"key":"10.7717\/peerj-cs.3290\/ref-19","doi-asserted-by":"publisher","first-page":"769","DOI":"10.1016\/j.procs.2022.09.132","article-title":"Combining fasttext and glove word embedding for offensive and hate speech text detection","volume":"207","author":"GLO","year":"2022","journal-title":"Procedia Computer Science"},{"key":"10.7717\/peerj-cs.3290\/ref-20","first-page":"285","article-title":"Work practices and challenges in pull-based development: the contributor\u2019s perspective","author":"Gousios","year":"2016"},{"key":"10.7717\/peerj-cs.3290\/ref-21","doi-asserted-by":"publisher","first-page":"358","DOI":"10.1109\/icse.2015.55","article-title":"Work practices and challenges in pull-based development: the integrator\u2019s perspective","volume":"1","author":"Gousios","year":"2015"},{"key":"10.7717\/peerj-cs.3290\/ref-22","first-page":"392","article-title":"It\u2019s not a bug, it\u2019s a feature: how misclassification impacts bug prediction","author":"Herzig","year":"2013"},{"key":"10.7717\/peerj-cs.3290\/ref-23","first-page":"1536","article-title":"DEVA: sensing emotions in the valence arousal space in software engineering text","author":"Islam","year":"2018a"},{"issue":"7","key":"10.7717\/peerj-cs.3290\/ref-24","doi-asserted-by":"publisher","first-page":"125","DOI":"10.1016\/j.jss.2018.08.030","article-title":"SentiStrength-SE: exploiting domain specificity for improved sentiment analysis in software engineering text","volume":"145","author":"Islam","year":"2018b","journal-title":"Journal of Systems and Software"},{"key":"10.7717\/peerj-cs.3290\/ref-25","first-page":"132","article-title":"Filtering spam in Weibo using ensemble imbalanced classification and knowledge expansion","author":"Jin","year":"2015"},{"issue":"1","key":"10.7717\/peerj-cs.3290\/ref-26","doi-asserted-by":"publisher","first-page":"226","DOI":"10.4304\/jait.1.1.4-20","article-title":"A review of machine learning algorithms for text-documents classification","volume":"1","author":"Khan","year":"2010","journal-title":"Journal of Advances in Information Technology"},{"key":"10.7717\/peerj-cs.3290\/ref-27","first-page":"1","article-title":"Predicting the severity of a reported bug","author":"Lamkanfi","year":"2010"},{"key":"10.7717\/peerj-cs.3290\/ref-28","first-page":"308","article-title":"Improving the accuracy of duplicate bug report detection using textual similarity measures","author":"Lazar","year":"2014"},{"issue":"Supplement C","key":"10.7717\/peerj-cs.3290\/ref-29","doi-asserted-by":"publisher","first-page":"223","DOI":"10.1016\/j.jss.2016.02.022","article-title":"Enhancements for duplication detection in bug reports with manifold correlation features","volume":"121","author":"Lin","year":"2016","journal-title":"Journal of Systems and Software"},{"key":"10.7717\/peerj-cs.3290\/ref-30","first-page":"94","article-title":"Sentiment analysis for software engineering: how far can we go?","author":"Lin","year":"2018"},{"issue":"6","key":"10.7717\/peerj-cs.3290\/ref-31","doi-asserted-by":"publisher","first-page":"15037","DOI":"10.1109\/access.2024.3357661","article-title":"Utilizing ensemble learning for detecting multi-modal fake news","volume":"12","author":"Luqman","year":"2024","journal-title":"IEEE Access"},{"key":"10.7717\/peerj-cs.3290\/ref-32","first-page":"346","article-title":"Automated severity assessment of software defect reports","author":"Menzies","year":"2008"},{"key":"10.7717\/peerj-cs.3290\/ref-33","article-title":"Efficient estimation of word representations in vector space","author":"Mikolov","year":"2013","journal-title":"International Conference on Learning Representations"},{"issue":"2","key":"10.7717\/peerj-cs.3290\/ref-34","doi-asserted-by":"publisher","first-page":"621","DOI":"10.1016\/j.eswa.2012.07.059","article-title":"Document-level sentiment classification: an empirical comparison between SVM and ANN","volume":"40","author":"Moraes","year":"2013","journal-title":"Expert Systems with Applications"},{"issue":"2","key":"10.7717\/peerj-cs.3290\/ref-35","doi-asserted-by":"publisher","first-page":"347","DOI":"10.1007\/s10515-017-0229-y","article-title":"Automatic approval prediction for software enhancement requests","volume":"25","author":"Nizamani","year":"2017","journal-title":"Automated Software Engineering"},{"key":"10.7717\/peerj-cs.3290\/ref-36","first-page":"1","article-title":"Summarization techniques for code, change, testing, and user feedback (invited paper)","author":"Panichella","year":"2018"},{"key":"10.7717\/peerj-cs.3290\/ref-37","first-page":"269","article-title":"Towards an improvement of bug severity classification","author":"Roy","year":"2014"},{"issue":"1","key":"10.7717\/peerj-cs.3290\/ref-38","doi-asserted-by":"publisher","first-page":"437","DOI":"10.1016\/j.eswa.2011.07.034","article-title":"Enhanced topic-based vector space model for semantics-aware spam filtering","volume":"39","author":"Santos","year":"2012","journal-title":"Expert Systems with Applications"},{"key":"10.7717\/peerj-cs.3290\/ref-39","first-page":"441","article-title":"TakeLab: Systems for measuring semantic text similarity","author":"\u0160ari\u0107","year":"2012"},{"issue":"Supplement C","key":"10.7717\/peerj-cs.3290\/ref-40","doi-asserted-by":"publisher","first-page":"632","DOI":"10.1016\/j.procs.2015.10.059","article-title":"A novel way of assessing software bug severity using dictionary of critical terms","volume":"70","author":"Sharma","year":"2015","journal-title":"Procedia Computer Science"},{"key":"10.7717\/peerj-cs.3290\/ref-41","first-page":"871","article-title":"DupFinder: integrated tool support for duplicate bug report detection","author":"Thung","year":"2014"},{"key":"10.7717\/peerj-cs.3290\/ref-42","first-page":"215","article-title":"Information retrieval based nearest neighbor classification for fine-grained bug severity prediction","author":"Tian","year":"2012"},{"issue":"5","key":"10.7717\/peerj-cs.3290\/ref-43","doi-asserted-by":"publisher","first-page":"1354","DOI":"10.1007\/s10664-014-9331-y","article-title":"Automated prediction of bug report priority using multi-factor analysis","volume":"20","author":"Tian","year":"2015","journal-title":"Empirical Software Engineering"},{"key":"10.7717\/peerj-cs.3290\/ref-44","first-page":"385","article-title":"Improved duplicate bug report identification","author":"Tian","year":"2012"},{"issue":"10","key":"10.7717\/peerj-cs.3290\/ref-45","doi-asserted-by":"publisher","first-page":"57","DOI":"10.1016\/j.jss.2019.05.026","article-title":"Sentiment based approval prediction for enhancement reports","volume":"155","author":"Umer","year":"2019","journal-title":"Journal of Systems and Software"},{"key":"10.7717\/peerj-cs.3290\/ref-46","first-page":"357","article-title":"Automatically prioritizing pull requests","author":"Veen","year":"2015"},{"key":"10.7717\/peerj-cs.3290\/ref-47","article-title":"A comparative study for email classification","author":"Youn","year":"2006"},{"key":"10.7717\/peerj-cs.3290\/ref-48","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2303.07196","article-title":"A comprehensive empirical evaluation of existing word embedding approaches","author":"Zaland","year":"2023"},{"issue":"10","key":"10.7717\/peerj-cs.3290\/ref-49","doi-asserted-by":"publisher","first-page":"22","DOI":"10.1016\/j.knosys.2014.03.015","article-title":"Binary {PSO} with mutation operator for feature selection using decision tree applied to spam detection","volume":"64","author":"Zhang","year":"2014","journal-title":"Knowledge-Based Systems"},{"issue":"12","key":"10.7717\/peerj-cs.3290\/ref-50","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/tse.2020.2967383","article-title":"User review-based change file localization for mobile applications","volume":"47","author":"Zhou","year":"2020","journal-title":"IEEE Transactions on Software Engineering"}],"container-title":["PeerJ Computer Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/peerj.com\/articles\/cs-3290.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/peerj.com\/articles\/cs-3290.xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/peerj.com\/articles\/cs-3290.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/peerj.com\/articles\/cs-3290.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,20]],"date-time":"2025-10-20T08:51:50Z","timestamp":1760950310000},"score":1,"resource":{"primary":{"URL":"https:\/\/peerj.com\/articles\/cs-3290"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,20]]},"references-count":50,"alternative-id":["10.7717\/peerj-cs.3290"],"URL":"https:\/\/doi.org\/10.7717\/peerj-cs.3290","archive":["CLOCKSS","LOCKSS","Portico"],"relation":{},"ISSN":["2376-5992"],"issn-type":[{"value":"2376-5992","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,20]]},"article-number":"e3290"}}