{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,5]],"date-time":"2026-10-05T05:54:29Z","timestamp":1791179669458,"version":"4.1.0"},"reference-count":31,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,10,5]],"date-time":"2026-10-05T00:00:00Z","timestamp":1791158400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Artif. Intell."],"abstract":"<jats:p>Ambiguity in software requirements is a major cause of misinterpretation, design defects, rework, and project delays in software engineering. This study proposes a hybrid semantic\u2013lexical ambiguity detection framework that integrates lexical, structural, and contextual representations for identifying ambiguous software requirement statements. Two benchmark datasets were employed, including a Software Requirements Specification (SRS) dataset and a Functional\u2013Non-Functional Requirements (FR\u2013NFR) dataset. Data pre-processing involved tokenisation, lemmatisation, and noise removal, while Synthetic Minority Oversampling Technique (SMOTE) was applied to address class imbalance within training partitions. Three modeling strategies were evaluated: baseline classifiers using TF\u2013IDF and character n-gram features, semantic models based on Sentence-BERT (SBERT) embeddings, and a hybrid representation combining TF\u2013IDF, character n-grams, and SBERT embeddings. Experimental results indicate that baseline models achieved high precision but comparatively lower recall, limiting their ability to identify ambiguous requirements under class imbalance. The proposed hybrid representation achieved the strongest and most balanced performance across both datasets in practical terms, particularly when combined with Support Vector Machine classification, resulting in improved recall and F1-score, although statistical testing indicated that these gains over the strongest lexical baseline were not significant at the 5% level. By jointly modeling lexical vagueness, structural ambiguity patterns, and contextual semantics, the framework captures both explicit and implicit forms of ambiguity that are frequently overlooked by single-representation approaches. To strengthen experimental validity, five-fold stratified cross-validation, transformer-based baseline comparison using fine-tuned BERT, statistical significance testing, and annotation reliability assessment using Cohen's Kappa coefficient were incorporated. The findings demonstrate that integrating lexical, structural, and semantic representations provides a robust and potentially scalable approach for ambiguity detection in software requirements engineering. The proposed framework contributes to improved requirements quality, reduced risk of misinterpretation, and more reliable automated support for requirements analysis.<\/jats:p>","DOI":"10.3389\/frai.2026.1901190","type":"journal-article","created":{"date-parts":[[2026,10,5]],"date-time":"2026-10-05T05:32:02Z","timestamp":1791178322000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Hybrid semantic-lexical framework for ambiguity detection in software requirements using TF-IDF, character n-grams, and SBERT"],"prefix":"10.3389","volume":"9","author":[{"given":"Fariha","family":"Khalid","sequence":"first","affiliation":[{"name":"Faculty of Computing, Riphah International University","place":["Lahore, Pakistan"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Muhammad","family":"Yaseen","sequence":"additional","affiliation":[{"name":"Faculty of Computing, Riphah International University","place":["Lahore, Pakistan"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Muhammad Awais","family":"Sattar","sequence":"additional","affiliation":[{"name":"Automatic Control, Department of Computer Science, Electrical and Space Engineering, Lule\u00e5 University of Technology","place":["Lule\u00e5, Sweden"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Abdelhamid","family":"Ghoul","sequence":"additional","affiliation":[{"name":"Automatic Control, Department of Computer Science, Electrical and Space Engineering, Lule\u00e5 University of Technology","place":["Lule\u00e5, Sweden"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Aida","family":"Mustapha","sequence":"additional","affiliation":[{"name":"Faculty of Computing","place":["Universiti Malaysia Pahang Al-Sultan Abdullah, Pekan, Malaysia"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,10,5]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2017.05.365","article-title":"Using word embedding and ensemble learning for highly imbalanced data sentiment analysis in short ARABIC text","author":"Al-Azani","year":"2017","journal-title":"Procedia Computer Sci."},{"key":"B2","doi-asserted-by":"publisher","DOI":"10.1109\/ICSME55016.2022.00020","article-title":"\u201cEvaluation of Context-Aware Language Models and Experts for Effort Estimation of Software Maintenance Issues,\u201d","year":"2022","journal-title":"2022 IEEE International Conference on Software Maintenance and Evolution (ICSME)"},{"key":"B3","doi-asserted-by":"publisher","DOI":"10.1155\/2021\/6696695","author":"Aqsa","year":"2021","journal-title":"Requirement Engineering Challenges in Agile Software"},{"key":"B4","doi-asserted-by":"publisher","DOI":"10.51519\/journalisi.v5i3.539","author":"Bahtiar","year":"2023","journal-title":"Comparison of Na\u00efve Bayes and Logistic Regression in Sentiment Analysis on Marketplace Reviews Using Rating-Based"},{"key":"B5","doi-asserted-by":"publisher","first-page":"44","DOI":"10.1162\/artl_a_00336","article-title":"The impossibility of automating ambiguity","volume":"27","author":"Birhane","year":"2021","journal-title":"Artif. Life"},{"key":"B6","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-44673-7_12","author":"Evgeniou","year":"2001","journal-title":"Support Vector Machines: Theory and Applications."},{"key":"B7","doi-asserted-by":"publisher","DOI":"10.1145\/3510003.3510157","article-title":"\u201cAutomated handling of anaphoric ambiguity in requirements: a multi-solution study,\u201d","author":"Ezzini","year":"2022","journal-title":"Proceedings of the 44th international conference on software engineering"},{"key":"B8","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE43902.2021.00133","article-title":"\u201cUsing domain-specific corpora for improved handling of ambiguity in requirements,\u201d","author":"Ezzini","year":"2021","journal-title":"2021 IEEE\/ACM 43rd international conference on software engineering (ICSE)"},{"key":"B9","doi-asserted-by":"publisher","first-page":"559","DOI":"10.1007\/s10515-019-00261-7","article-title":"An NLP approach for cross-domain ambiguity detection in requirements engineering","volume":"26","author":"Ferrar","year":"2019","journal-title":"Automat. Softw. Eng."},{"key":"B10","doi-asserted-by":"publisher","DOI":"10.1145\/3674805.3686692","article-title":"\u201cAn exploratory mixed-methods study on general data protection regulation (GDPR) compliance in open-source software,\u201d","author":"Franke","year":"2024","journal-title":"Proceedings of the 18th ACM\/IEEE international symposium on empirical software engineering and measurement"},{"key":"B11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-14192-8_20","article-title":"\u201cAmbiguity detection: towards a tool explaining ambiguity sources,\u201d","author":"Gleich","year":"2010","journal-title":"Requirements Engineering: Foundation for Software Quality"},{"key":"B12","doi-asserted-by":"publisher","first-page":"39","DOI":"10.1007\/s11219-020-09523-0","article-title":"\u201cChallenges concerning test case specifications in automotive software testing: assessment of frequency and criticality,\u201d Software Quality Journal, vol","volume":"1","author":"Juhnke","year":"2021","journal-title":"29, no"},{"key":"B13","doi-asserted-by":"publisher","first-page":"108699","DOI":"10.1016\/j.compeleceng.2023.108699","article-title":"Improving BERT model for requirements classification by bidirectional LSTM-CNN deep model","volume":"108","author":"Kaur","year":"2023","journal-title":"Computers and Electrical Eng."},{"key":"B14","year":""},{"key":"B15","doi-asserted-by":"publisher","first-page":"103000","DOI":"10.1016\/j.ipm.2022.103000","article-title":"Lexical ambiguity detection in professional discourse","volume":"59","author":"Liu","year":"2022","journal-title":"Inf. Process. Manag"},{"key":"B16","doi-asserted-by":"publisher","first-page":"63579","DOI":"10.1109\/ACCESS.2023.3287326","article-title":"A novel approach to improve software defect prediction accuracy using machine learning","volume":"11","author":"Mehmood","year":"2023","journal-title":"IEEE Access"},{"key":"B17","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/LGRS.2021.3115110","article-title":"Optimization for arbitrary-oriented object detection via representation invariance loss","volume":"19","author":"Ming","year":"2022","journal-title":"IEEE Geosci. Remote Sensing Letters"},{"key":"B18","doi-asserted-by":"publisher","DOI":"10.1109\/CAIDA51941.2021.9425236","article-title":"\u201cComparative Analysis for Predicting Non-Functional Requirements using Supervised Machine Learning,\u201d","author":"Mir Khatian","year":"2021","journal-title":"2021 1st International Conference on Artificial Intelligence and Data Analytics (CAIDA)"},{"key":"B19","doi-asserted-by":"publisher","DOI":"10.1145\/3528588.3528651","article-title":"\u201cIdentification of intra-domain ambiguity using transformer-based machine learning,\u201d","author":"Moharil","year":"2022","journal-title":"Proceedings of the 1st international workshop on natural language-based software engineering"},{"key":"B20","doi-asserted-by":"publisher","DOI":"10.1145\/3195538.3195545","article-title":"\u201cAmbiguous software requirement specification detection: an automated approach,\u201d","year":"2018","journal-title":"Proceedings of the 5th international workshop on requirements engineering and testing"},{"key":"B21","doi-asserted-by":"publisher","first-page":"108972","DOI":"10.1016\/j.engappai.2024.108972","volume":"136","author":"Peretz","year":"2024"},{"key":"B22","doi-asserted-by":"publisher","first-page":"114197","DOI":"10.1016\/j.knosys.2025.114197","article-title":"Labeling issues through semantic patterns in open-source Agile practices","volume":"328","year":"2025","journal-title":"Knowl. Based. Syst"},{"key":"B23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1410","author":"Reimers","year":"2019","journal-title":"Sentence-BERT: sentence embeddings using Siamese BERT-networks"},{"key":"B24","doi-asserted-by":"publisher","DOI":"10.1109\/INFOMAN.2019.8714682","article-title":"\u201cAutomatic detection of ambiguous software requirements: an insight,\u201d","author":"Riaz","year":"2019","journal-title":"2019 5th international conference on information management (ICIM)"},{"key":"B25","unstructured":"Sonali\n              S. S. T.\n            \n          \n          FR-NFR dataset.\n          \n          2024"},{"key":"B26","doi-asserted-by":"publisher","first-page":"62811","DOI":"10.1109\/ACCESS.2022.3182372","article-title":"\u201cThe Use of NLP-Based Text Representation Techniques to Support Requirement Engineering Tasks: A Systematic Mapping Review,\u201d","volume":"10","author":"Sonbol","year":"2022","journal-title":"IEEE Access"},{"key":"B27","unstructured":"Vaibhav\n              S.\n            \n          \n          \n          2023"},{"key":"B28","doi-asserted-by":"publisher","first-page":"695","DOI":"10.1109\/TSE.2024.3361033","volume":"50","author":"Veizaga","year":"2024","journal-title":"IEEE Transactions on Software Eng."},{"key":"B29","doi-asserted-by":"publisher","year":"2018","DOI":"10.1109\/WSCE.2018.8690536"},{"key":"B30","doi-asserted-by":"publisher","first-page":"11127","DOI":"10.3390\/app132011127","article-title":"Developing an advanced software requirements classification model using BERT: an empirical evaluation study on newly generated Turkish data","volume":"13","author":"Yucalar","year":"2023","journal-title":"Appl. Sci."},{"key":"B31","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3444689","article-title":"Natural language processing for requirements engineering: a systematic mapping study","volume":"54","author":"Zhao","year":"2021","journal-title":"ACM Comput. Surv"}],"container-title":["Frontiers in Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2026.1901190\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,5]],"date-time":"2026-10-05T05:32:03Z","timestamp":1791178323000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2026.1901190\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10,5]]},"references-count":31,"alternative-id":["10.3389\/frai.2026.1901190"],"URL":"https:\/\/doi.org\/10.3389\/frai.2026.1901190","relation":{},"ISSN":["2624-8212"],"issn-type":[{"value":"2624-8212","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,10,5]]},"article-number":"1901190"}}