LLM-Driven Active Learning for Dependency Analysis of Mobile App Requirements Through Contextual Reasoning and Structural Relationships
Source abstract
Abstract
In today’s fast-paced release cycles, mobile app user reviews offer a valuable source for tracking the evolution of user needs. At the core of these needs lies a structure of interdependencies—some enhancements are only relevant in specific usage contexts, while others may conflict when implemented together. Identifying these relationships is essential for anticipating feature interactions, resolving contradictions, and enabling context-aware, user-driven planning. The present work introduces an ontology-enhanced AI framework for predicting whether the requirements mentioned in reviews are interdependent. The core component is a Bidirectional Encoder Representations from Transformers (BERT) classifier retrained within a large-language-model-driven active learning loop that focuses on instances with uncertainty. The framework integrates contextual and structural reasoning; contextual analysis captures the semantic intent and functional role of each requirement, enriching the understanding of user expectations. Structural reasoning relies on a domain-specific ontology that serves as both a knowledge base and an inference layer, guiding the grouping of requirements. The model achieved strong performance on annotated banking app reviews, with a validation F1-score of 0.9565 and an area under the ROC curve (AUC) exceeding 0.97. The study results contribute to supporting developers in prioritizing features based on dependencies and delivering more coherent, conflict-free releases.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Software Engineering Research · Software Engineering Techniques and Practices · Web Data Mining and Analysis
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Software Engineering Department, College of Computer and Information Sciences, King Saud University, Riyadh 11543, Saudi Arabia
Funding
King Saud University, Riyadh, Saudi Arabia
References (46)
Show source-provided references
1. Analysing app reviews for software engineering: A systematic literature review10.1007/s10664-021-10065-7 ↗
2. Ahmad, K., Abdelrazek, M., Arora, C., Baniya, A.A., Bano, M., and Grundy, J. (2023). Requirements Engineering Framework for Human-centered Artificial Intelligence Software Systems. arXiv.10.1016/j.asoc.2023.110455 ↗
3. Ghosh, T.K., Pargaonkar, A., and Eisty, N.U. (2024). Exploring Requirements Elicitation from App Store User Reviews Using Large Language Models. arXiv.
4. Deshpande, G., Arora, C., and Ruhe, G. (2019, January 23–27). Data-Driven Elicitation and Optimization of Dependencies between Requirements. Proceedings of the 2019 IEEE 27th International Requirements Engineering Conference (RE), Jeju Island, Republic of Korea. Available online: https://ieeexplore.ieee.org/document/8920671/.10.1109/RE.2019.00055 ↗
5. Cheng, H., Husen, J.H., Lu, Y., Racharak, T., Ubayashi, N., and Washizaki, H. (2024). Generative AI for Requirements Engineering: A Systematic Literature Review. arXiv.
6. Hemmat, A., Sharbaf, M., Kolahdouz-Rahimi, S., Lano, K., and Tehrani, S.Y. (2025). Research directions for using LLM in software requirement engineering: A systematic review. Front. Comput. Sci., 7.10.3389/fcomp.2025.1519437 ↗
7. Mining and searching app reviews for requirements engineering: Evaluation and replication studies10.1016/j.is.2023.102181 ↗
8. Xu, H., and Xu, G. (2025, July 06). Applying the Bert Algorithm for Software Requirements Classification. Available online: https://www.researchgate.net/profile/Huajie-Xu-2/publication/378696528_Applying_the_Bert_Algorithm_for_Software_Requirements_Classification/links/65e56df8adf2362b636a7961/Applying-the-Bert-Algorithm-for-Software-Requirements-Classification.pdf.
9. Deshpande, G., Sheikhi, B., Chakka, S., Zotegouon, D.L., Masahati, M.N., and Ruhe, G. (2021, January 20–24). Is BERT the New Silver Bullet?—An Empirical Investigation of Requirements Dependency Classification. Proceedings of the 2021 IEEE 29th International Requirements Engineering Conference Workshops (REW), Notre Dame, IN, USA. Available online: https://ieeexplore.ieee.org/document/9582338/.10.1109/REW53955.2021.00025 ↗
10. Reimers, N., and Gurevych, I. (2019). Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks. arXiv.10.18653/v1/D19-1410 ↗
11. Automatic Requirement Dependency Extraction Based on Integrated Active Learning Strategies10.1007/s11633-023-1420-1 ↗
12. Wang, X. (2024). Active Learning for NLP with Large Language Models. arXiv.
13. Dalpiaz, F., Dell’Anna, D., Aydemir, F.B., and Cevikol, S. (2019, January 23–27). Requirements Classification with Interpretable Machine Learning and Dependency Parsing. Proceedings of the 2019 IEEE 27th International Requirements Engineering Conference (RE), Jeju Island, Republic of Korea. Available online: https://ieeexplore.ieee.org/document/8920401/.10.1109/RE.2019.00025 ↗
14. Deshpande, G., Motger, Q., Palomares, C., Kamra, I., Biesialska, K., Franch, X., Ruhe, G., and Ho, J. (September, January 31). Requirements Dependency Extraction by Integrating Active Learning with Ontology-Based Retrieval. Proceedings of the 2020 IEEE 28th International Requirements Engineering Conference (RE), Zurich, Switzerland. Available online: https://ieeexplore.ieee.org/document/9218190/.10.1109/RE48521.2020.00020 ↗
15. Guan, H., Xu, H., and Cai, L. (2024). Requirement Dependency Extraction Based on Improved Stacking Ensemble Machine Learning. Mathematics, 12.10.3390/math12091272 ↗
16. Motger, Q., Borrull, R., Palomares, C., and Marco, J. (2019, January 18–21). OpenReq-DD: A Requirements Dependency Detection Tool. Proceedings of the 25th International Conference on Requirements Engineering: Foundation for Software Quality, Essen, Germany.
17. A novel agile ontology engineering methodology for supporting organizations in collaborative ontology development10.1016/j.compind.2023.103979 ↗
18. Domain-specific requirements analysis framework: Ontology-driven approach
19. Mosquera, D., Ruiz, M., and Pastor, O. (2025). Ontology-based NLP tool for tracing software requirements and conceptual models: An empirical study. Requir. Eng., 30.10.1007/s00766-025-00447-4 ↗
20. Hymel, C., and Johnson, H. (2025). Analysis of LLMs vs Human Experts in Requirements Engineering. arXiv.
21. Kholodna, N., Julka, S., Khodadadi, M., Gumus, M.N., and Granitzer, M. (2024). LLMs in the Loop: Leveraging Large Language Model Annotations for Active Learning in Low-Resource Languages. arXiv.10.1007/978-3-031-70381-2_25 ↗
22. The Artificial Intelligence Ontology: LLM-Assisted Construction of AI Concept Hierarchies10.1177/15705838241304103 ↗
23. Kommineni, V.K., König-Ries, B., and Samuel, S. (2024). From human experts to machines: An LLM supported approach to ontology and knowledge graph construction. arXiv.
24. Dependency-aware software release planning through mining user preferences10.1007/s00500-019-04630-y ↗
25. Effective Requirement Engineering Process Model in Software Engineering10.11648/j.se.20200801.11 ↗
26. Letsholo, K.J. (2024). Early-Stage Requirements Transformation Approaches: A Systematic Review. arXiv.
27. Kolahdouz-Rahimi, S., Lano, K., and Lin, C. (2023, January 19–21). Requirement Formalisation Using Natural Language Processing and Machine Learning: A Systematic Review. Proceedings of the 11th International Conference on Model-Based Software and Systems Engineering, Lisbon, Portugal. Available online: https://www.scitepress.org/DigitalLibrary/Link.aspx?doi=10.5220/0011789700003402.10.5220/0011789700003402 ↗
28. User Reviews Classification in Play Store Applications Using Deep Learning: An Empirical Study. Diqiu Kexue - Zhongguo Dizhi Daxue Xuebao/Earth Science
29. Data Dependencies Extended for Variety and Veracity: A Family Tree10.1109/TKDE.2020.3046443 ↗
30. Asyrofi, R., Siahaan, D.O., and Priyadi, Y. (2020, January 10–11). Extraction Dependency Based on Evolutionary Requirement Using Natural Language Processing. Proceedings of the 2020 3rd International Seminar on Research of Information Technology and Intelligent Systems (ISRITI), Yogyakarta, Indonesia. Available online: https://ieeexplore.ieee.org/document/9315489/.10.1109/ISRITI51436.2020.9315489 ↗
31. Samer, R., Stettinger, M., Atas, M., Felfernig, A., Ruhe, G., and Deshpande, G. (2019, January 4–6). New Approaches to the Identification of Dependencies between Requirements. Proceedings of the 2019 IEEE 31st International Conference on Tools with Artificial Intelligence (ICTAI), Portland, OR, USA. Available online: https://ieeexplore.ieee.org/document/8995268/.10.1109/ICTAI.2019.00-91 ↗
32. Atas, M., Samer, R., and Felfernig, A. (2018, January 3–6). Automated Identification of Type-Specific Dependencies between Requirements. Proceedings of the 2018 IEEE/WIC/ACM International Conference on Web Intelligence (WI), Santiago. Available online: https://ieeexplore.ieee.org/document/8609673/.10.1109/WI.2018.00-10 ↗
33. Automated Requirement Dependency Analysis for Complex Technical Systems10.1017/pds.2022.189 ↗
34. Zhi, Y., Li, T., and Yang, Z. (2021, January 22–26). Extracting features from app descriptions based on POS and dependency. Proceedings of the 36th Annual ACM Symposium on Applied Computing, Virtual Event, Republic of Korea. Available online: https://dl.acm.org/doi/10.1145/3412841.3442120.10.1145/3412841.3442120 ↗
35. Ontology-Based Automatic Reasoning and NLP for Tracing Software Requirements into Models with the OntoTrace Tool
36. Large Language Models for Software Engineering: A Systematic Literature Review10.1145/3695988 ↗
37. Tikayat Ray, A., Cole, B.F., Pinon Fischer, O.J., Bhat, A.P., White, R.T., and Mavris, D.N. (2023). Agile Methodology for the Standardization of Engineering Requirements Using Large Language Models. Systems, 11.10.20944/preprints202305.1325.v1 ↗
38. Mitigating exposure bias in large language model distillation: An imitation learning approach10.1007/s00521-025-11162-0 ↗
39. Almoqren, N., and Alrashoud, M. (2025, January 13–15). A Smart Framework for Optimizing User Feedback Prioritization in Application Development. Proceedings of the 2024 International Conference on IT Innovation and Knowledge Discovery (ITIKD), Manama, Bahrain. Available online: https://ieeexplore.ieee.org/document/11004934/.10.1109/ITIKD63574.2025.11004934 ↗
40. Ronanki, K., Berger, C., and Horkoff, J. (2023). Investigating ChatGPT’s Potential to Assist in Requirements Elicitation Processes. arXiv.10.1109/SEAA60479.2023.00061 ↗
41. Software Requirements Classification: From Bag-of-Words to Transformer
42. A novel and precise approach for similarity-based link prediction in diverse networks10.1007/s13278-023-01160-2 ↗
43. Network analysis with the aid of the path length matrix10.1007/s11075-023-01577-y ↗
44. GOntoSim: A semantic similarity measure based on LCA and common descendants10.1038/s41598-022-07624-3 ↗
45. Fischbach, J., Frattini, J., and Vogelsang, A. (2021). CiRA: A Tool for the Automatic Detection of Causal Relationships in Requirements Artifacts. arXiv.10.1007/978-3-030-73128-1_2 ↗
46. Tahvili, S., Hatvani, L., Felderer, M., Afzal, W., and Bohlin, M. (2019, January 4–9). Automated Functional Dependency Detection Between Test Cases Using Doc2Vec and Clustering. Proceedings of the 2019 IEEE International Conference on Artificial Intelligence Testing (AITest), Newark, CA, USA. Available online: https://ieeexplore.ieee.org/document/8718215/.10.1109/AITest.2019.00-13 ↗