skip to main content
10.1145/3640310.3674081acmconferencesArticle/Chapter ViewAbstractPublication PagesmodelsConference Proceedingsconference-collections
research-article

Automated Derivation of UML Sequence Diagrams from User Stories: Unleashing the Power of Generative AI vs. a Rule-Based Approach

Published: 22 September 2024 Publication History

Abstract

User stories are informal, non-technical descriptions of features from a user's perspective that guide collaboration and iterative development in Agile projects. However, ambiguities in user stories can lead to miscommunication among stakeholders. Design models, such as UML sequence diagrams, are essential for enhancing communication, clarifying system behavior, and improving the development process. This paper presents an automated approach for generating behavioral models specifically sequence diagrams from natural language requirements expressed as user stories. We also investigate the effectiveness of a Large Language Model (LLM) in using generative AI for this task. By applying our approach and ChatGPT to two benchmark datasets with the same set of user stories, we generated corresponding sequence diagrams for comparison. Expert evaluations in Software Engineering reveal that our approach effectively produces relevant, simplified diagrams for straightforward user stories, whereas the LLM tends to create more complex diagrams that sometimes go beyond the simplicity of the original user stories.

References

[1]
Sabah Al-Fedaghi. 2021. UML sequence diagram: an alternative model. arXiv preprint arXiv:2105.15152 (2021).
[2]
Oscar Castro, Pierrick Bruneau, Jean-Sébastien Sottet, and Dario Torregrossa. 2023. Landscape of High-Performance Python to Develop Data Science and Machine Learning Applications. Comput. Surveys 56, 3 (2023), 1--30.
[3]
Xiaohong Chen, Frédéric Mallet, and Xiaoshan Liu. 2020. Formally Verifying Sequence Diagrams for Safety Critical Systems. In 2020 International Symposium on Theoretical Aspects of Software Engineering (TASE). 217--224. https://doi.org/10.1109/TASE49443.2020.00037
[4]
Mike Cohn. 2004. User stories applied: For agile software development. Addison-Wesley Professional.
[5]
Fabiano Dalpiaz. 2018. Requirements data sets (user stories). Mendeley Data, v1 (2018).
[6]
Fabiano Dalpiaz, Patrizia Gieske, and Arnon Sturm. 2021. On deriving conceptual models from user requirements: An empirical study. Information and Software Technology 131 (03 2021), 106484. https://doi.org/10.1016/j.infsof.2020.106484
[7]
Fabiano Dalpiaz, Ivor Schalk, Sjaak Brinkkemper, Fatma Aydemir, and Garm Lucassen. 2018. Detecting Terminological Ambiguity in User Stories: Tool and Experimentation. Information and Software Technology 110 (12 2018). https://doi.org/10.1016/j.infsof.2018.12.007
[8]
Joost de Winter, Dimitra Dodou, and Peter Wieringa. 2009. Exploratory Factor Analysis With Small Sample Sizes. Multivariate Behavioral Research 44 (04 2009), 147--181. https://doi.org/10.1080/00273170902794206
[9]
ROUABHIA Djaber and HADJADJ Ismail. 2023. AI as a Co-Engineer: A Case Study of ChatGPT in Software Lifecycle. (2023).
[10]
Meryem Elallaoui, Khalid Nafil, and Raja Touahni. 2015. Automatic generation of UML sequence diagrams from user stories in Scrum process. In 2015 10th international conference on intelligent systems: theories and applications (SITA). IEEE, 1--6.
[11]
Fabian Gilson, Matthias Galster, and François Georis. 2020. Generating use case scenarios from user stories. In Proceedings of the international conference on software and system processes. 31--40.
[12]
Gerhard Greeff and Ranjan Ghoshal. 2004. Practical E-manufacturing and supply chain management. Elsevier.
[13]
Abhimanyu Gupta, Geert Poels, and Palash Bera. 2019. Creation of Multiple Conceptual Models from User Stories-A Natural Language Processing Approach. In Advances in Conceptual Modeling: ER 2019 Workshops FAIR, MREBA, EmpER, MoBiD, OntoCom, and ER Doctoral Symposium Papers, Salvador, Brazil, November 4-7, 2019, Proceedings 38. Springer, 47--57.
[14]
Kwai Hing Heung. 2013. A tool for generating UML diagram from source code. (2013). https://plantuml.com/sequence-diagram
[15]
Xinyi Hou, Yanjie Zhao, Yue Liu, Zhou Yang, Kailong Wang, Li Li, Xiapu Luo, David Lo, John Grundy, and Haoyu Wang. 2023. Large language models for software engineering: A systematic literature review. arXiv preprint arXiv:2308.10620 (2023).
[16]
Xinying Hou, Yanjie Zhao, Yue Liu, Zhou Yang, Kailong Wang, Li Li, Xiapu Luo, David Lo, John C. Grundy, and Haoyu Wang. 2023. Large Language Models for Software Engineering: A Systematic Literature Review. ArXiv abs/2308.10620 (2023). https://api.semanticscholar.org/CorpusID:261048648
[17]
Irum Inayat, Siti Salwah Salim, Sabrina Marczak, Maya Daneva, and Shahaboddin Shamshirband. 2015. A systematic literature review on agile requirements engineering practices and challenges. Computers in human behavior 51 (2015), 915--929.
[18]
Ivar Jacobson and James Rumbaugh Grady Booch. 2021. The unified modeling language reference manual. (2021).
[19]
Munima Jahan, Zahra Shakeri Hossein Abad, and Behrouz Far. 2021. Generating sequence diagram from natural language requirements. In 2021 IEEE 29th International Requirements Engineering Conference Workshops (REW). IEEE, 39--48.
[20]
Ian M Kinchin, David B Hay, and Alan Adams. 2000. How a qualitative approach to concept map analysis can be used to aid learning by illustrating patterns of conceptual development. Educational research 42, 1 (2000), 43--57.
[21]
Takwa Kochbati, Shuai Li, Sébastien Gérard, and Chokri Mraidha. 2021. From User Stories to Models: A Machine Learning Empowered Automation. MODELSWARD 10 (2021), 0010197800280040.
[22]
Salih Köse and Fatma Aydemir. 2023. A Framework To Improve User Story Sets Through Collaboration. (01 2023).
[23]
Liwu Li. 2000. Translating use cases to sequence diagrams. In Proceedings ASE 2000. Fifteenth IEEE International Conference on Automated Software Engineering. IEEE, 293--296.
[24]
Yuding Liang and Kenny Zhu. 2018. Automatic generation of text descriptive comments for code blocks. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 32.
[25]
Jun Lin, Han Yu, Zhiqi Shen, and Chunyan Miao. 2014. Using goal net to model user stories in agile software development. In 15th IEEE/ACIS International Conference on Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing (SNPD). IEEE, 1--6.
[26]
Garm Lucassen, Fabiano Dalpiaz, Jan Martijn EM van der Werf, and Sjaak Brinkkemper. 2016. The use and effectiveness of user stories in practice. In Requirements Engineering: Foundation for Software Quality: 22nd International Working Conference, REFSQ 2016, Gothenburg, Sweden, March 14-17, 2016, Proceedings 22. Springer, 205--222.
[27]
Christopher D Manning, Mihai Surdeanu, John Bauer, Jenny Rose Finkel, Steven Bethard, and David McClosky. 2014. The Stanford CoreNLP natural language processing toolkit. In Proceedings of 52nd annual meeting of the association for computational linguistics: system demonstrations. 55--60.
[28]
Samia Nasiri, Yassine Rhazali, and Mohammed Lahmer. 2021. Towards a generation of class diagram from user stories in agile methods. In Advancements in Model-Driven Architecture in Software Engineering. IGI Global, 135--159.
[29]
Samia Nasiri, Yassine Rhazali, Mohammed Lahmer, and Amina Adadi. 2021. From user stories to UML diagrams driven by ontological and production model. International Journal of Advanced Computer Science and Applications 12, 6 (2021).
[30]
Ahmad Iklil Nur, Faris Fasyadin, Imelda Adinda Febriansyah, Muhammad Alvian Yulianto, Ibaneza Griffint Secoria, Amelia Nagatha, Wilona Fadyah Trinaldy, Badrus Zaman, and Indra Kharisma Raharjana. 2023. User scenario 2 seq: Automated system to generate sequence diagram from user stories scenario. In AIP Conference Proceedings, Vol. 2554. AIP Publishing LLC, 040007.
[31]
Ruth ONeill and Alex Russell. 2019. Stop! Grammar time: University students' perceptions of the automated feedback program Grammarly. Australasian Journal of Educational Technology 35, 1 (2019).
[32]
Scott P Overmyer, L Benoit, and R Owen. 2001. Conceptual modeling through linguistic analysis using LIDA. In Proceedings of the 23rd International Conference on Software Engineering. ICSE 2001. IEEE, 401--410.
[33]
Peng Qi, Yuhao Zhang, Yuhui Zhang, Jason Bolton, and Christopher D Manning. 2020. Stanza: A Python natural language processing toolkit for many human languages. arXiv preprint arXiv:2003.07082 (2020).
[34]
Kun Ruan, Xiaohong Chen, and Zhi Jin. 2023. Requirements Modeling Aided by ChatGPT: An Experience in Embedded Systems. In 2023 IEEE 31st International Requirements Engineering Conference Workshops (REW). IEEE, 170--177.
[35]
Fatma Başak Aydemir Salih Göktuğ Köse. 2023. A User Story Dataset for Library and Restaurant Management Systems. Zenodo (2023).
[36]
Eva-Maria Schön, Jörg Thomaschewski, and María José Escalona. 2017. Agile Requirements Engineering: A systematic literature review. Computer standards & interfaces 49 (2017), 79--91.
[37]
Todd Sedano, Paul Ralph, and Cécile Péraire. 2019. The product backlog. In 2019 IEEE/ACM 41st International Conference on Software Engineering (ICSE). IEEE, 200--211.
[38]
JF Smart. 2014. BDD in Action-Behavior-Driven Development for the whole software lifecycle, 2014. Greenwich: Manning Publications (2014).
[39]
Min Song and Tamy Chambers. 2014. Text mining with the Stanford CoreNLP. In Measuring scholarly impact: Methods and practice. Springer, 215--234.
[40]
Kalaivani Subramaniam, Dong Liu, Behrouz Homayoun Far, and Armin Eberlein. 2004. UCDA: Use Case Driven Development Assistant Tool for Class Model Generation. In SEKE, Vol. 7804. Citeseer, 16th.
[41]
Jitendra Singh Thakur and Atul Gupta. 2014. Automatic generation of sequence diagram from use case specification. In Proceedings of the 7th India Software Engineering Conference. 1--6.
[42]
Yao Wan, Zhou Zhao, Min Yang, Guandong Xu, Haochao Ying, Jian Wu, and Philip S Yu. 2018. Improving automatic source code summarization via deep reinforcement learning. In Proceedings of the 33rd ACM/IEEE international conference on automated software engineering. 397--407.
[43]
Simin Wang, Liguo Huang, Amiao Gao, Jidong Ge, Tengfei Zhang, Haitao Feng, Ishna Satyarth, Ming Li, He Zhang, and Vincent Ng. 2022. Machine/deep learning for software engineering: A systematic literature review. IEEE Transactions on Software Engineering 49, 3 (2022), 1188--1231.
[44]
Yves Wautelet, Samedi Heng, Manuel Kolp, and Isabelle Mirbel. 2014. Unifying and extending user story models. In Advanced Information Systems Engineering: 26th International Conference, CAiSE 2014, Thessaloniki, Greece, June 16-20, 2014. Proceedings 26. Springer, 211--225.
[45]
Yves Wautelet, Samedi Heng, Manuel Kolp, Isabelle Mirbel, and Stephan Poelmans. 2016. Building a rationale diagram for evaluating user story sets. In 2016 IEEE Tenth International Conference on Research Challenges in Information Science (RCIS). IEEE, 1--12.
[46]
Stephen A White et al. 2004. Business process modeling notation (bpmn).
[47]
Tianyu Wu, Shizhu He, Jingping Liu, Siqi Sun, Kang Liu, Qing-Long Han, and Yang Tang. 2023. A brief overview of ChatGPT: The history, status quo and potential future development. IEEE/CAA Journal of Automatica Sinica 10, 5 (2023), 1122--1136.
[48]
Tao Yue, Lionel C Briand, and Yvan Labiche. 2010. An automated approach to transform use cases into activity diagrams. In European Conference on Modelling Foundations and Applications. Springer, 337--353.

Recommendations

Comments

Information & Contributors

Information

Published In

cover image ACM Conferences
MODELS '24: Proceedings of the ACM/IEEE 27th International Conference on Model Driven Engineering Languages and Systems
September 2024
311 pages
ISBN:9798400705045
DOI:10.1145/3640310
Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected].

Sponsors

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 22 September 2024

Permissions

Request permissions for this article.

Check for updates

Author Tags

  1. Generative Model
  2. Large Language Model
  3. Model Generation
  4. Natural Language Processing
  5. Rule-based approach
  6. Sequence Diagram
  7. User Story

Qualifiers

  • Research-article
  • Research
  • Refereed limited

Conference

MODELS '24
Sponsor:

Acceptance Rates

MODELS '24 Paper Acceptance Rate 26 of 124 submissions, 21%;
Overall Acceptance Rate 144 of 506 submissions, 28%

Contributors

Other Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

  • 0
    Total Citations
  • 334
    Total Downloads
  • Downloads (Last 12 months)334
  • Downloads (Last 6 weeks)70
Reflects downloads up to 03 Mar 2025

Other Metrics

Citations

View Options

Login options

View options

PDF

View or Download as a PDF file.

PDF

eReader

View online with eReader.

eReader

Figures

Tables

Media

Share

Share

Share this Publication link

Share on social media