FB2BPMN: An End-to-End Pipeline for Translating Unstructured User Feedback into BPMN Using LLM and Fuzzy Matching
Abstract
Translating unstructured user feedback into Business Process Model and Notation (BPMN) is challenging due to informal language, contextual ambiguity, and the lack of explicit structural cues. We present FB2BPMN, an end-to-end pipeline that combines natural language processing (NLP), large language models (LLMs), and fuzzy string matching to automatically generate BPMN elements from raw feedback. The pipeline comprises four stages: sentence structuring, fact extraction, role-activity mapping, and fuzzy-based semantic alignment. We evaluate FB2BPMN on 125 annotated feedback instances sampled from academic journal management systems. Using expert-authored BPMN as reference, FB2BPMN attains precision 0.97, recall 0.88, and F1 0.91 on element identification and accuracy 0.85 on process flow construction, outperforming a rule-based baseline. Results indicate strong structural and semantic correspondence, showing that FB2BPMN effectively bridges informal feedback and formal process representations.References
K. Grolinger, M. A. M. Capretz, A. Cunha, and S. Tazi, “Integration of business process modeling and Web services: A survey,” Serv. Oriented Comput. Appl., vol. 8, no. 2, pp. 105–128, 2014, doi: 10.1007/s11761-013-0138-2.
T. Skersys, P. Danenas, and R. Butleris, “Extracting SBVR business vocabularies and business rules from UML use case diagrams,” 2018, doi: 10.1016/j.jss.2018.03.061.
V. Kale, “Business Process Modeling and Notation,” Enterp. Process Manag. Syst., no. January, pp. 257–275, 2019, doi: 10.1201/9780429453311-14.
M. Javed and Y. Lin, “iMER: Iterative process of entity relationship and business process model extraction from the requirements,” Inf. Softw. Technol., vol. 135, no. January, p. 106558, 2021, doi: 10.1016/j.infsof.2021.106558.
U. Indahyanti, A. Djunaidy, and D. Siahaan, “Auto-Generating Business Process Model From Heterogeneous Documents : A Comprehensive Literature Survey,” in Proc. 9th Int. Conf. Electrical Engineering, Computer Science and Informatics, 2022, pp. 239–243. doi: https://doi.org/10.23919/EECSI56542.2022.9946460.
I. Tangkawarow, R. Sarno, and D. Siahaan, “ID2SBVR: A Method for Extracting Business Vocabulary and Rules from an Informal Document,” Big Data Cogn. Comput., vol. 6, no. 4, 2022, doi: 10.3390/bdcc6040119.
F. Gilson, M. Galster, and F. Georis, “Generating use case scenarios from user stories,” in Proceedings - 2020 IEEE/ACM International Conference on Software and System Processes, ICSSP 2020, 2020, pp. 31–40. doi: 10.1145/3379177.3388895.
S. Nasiri, A. Adadi, and M. Lahmer, “Automatic generation of business process models from user stories,” Int. J. Electr. Comput. Eng., vol. 13, no. 1, pp. 809–822, 2023, doi: 10.11591/ijece.v13i1.pp809-822.
I. Beerepoot et al., “The biggest business process management problems to solve before we die,” Comput. Ind., vol. 146, no. December 2022, p. 103837, 2023, doi: 10.1016/j.compind.2022.103837.
T. Grisold et al., “The Five Diamond Method for Explorative Business Process Management,” Bus. Inf. Syst. Eng., vol. 64, no. 2, pp. 149–166, 2022, doi: 10.1007/s12599-021-00703-1.
A. Mustansir, K. Shahzad, and M. K. Malik, “Towards automatic business process redesign: an NLP based approach to extract redesign suggestions,” Autom. Softw. Eng., vol. 29, no. 1, 2022, doi: 10.1007/s10515-021-00316-8.
J. Wouters, A. Menkveld, S. Brinkkemper, and F. Dalpiaz, “Crowd-based requirements elicitation via pull feedback: method and case studies,” Requir. Eng., vol. 27, no. 4, pp. 429–455, 2022, doi: 10.1007/s00766-022-00384-6.
I. Fatawi, M. Asy’ari, H. Hunaepi, T. Samsuri, and M. R. Bilad, “Empowering Language Models Through Advanced Prompt Engineering: A Comprehensive Bibliometric Review,” Indones. J. Sci. Technol., vol. 9, no. 2, pp. 441–462, 2024, doi: 10.17509/ijost.v9i2.71481.
A. Mukanova et al., “LLM-Powered Natural Language Text Processing for Ontology Enrichment,” Appl. Sci., vol. 14, no. 13, 2024, doi: 10.3390/app14135860.
P. Danenas and T. Skersys, “Exploring Natural Language Processing in Model-To-Model Transformations,” IEEE Access, vol. 10, no. November, pp. 116942–116958, 2022, doi: 10.1109/ACCESS.2022.3219455.
S. Prasad, H. Gupta, and A. Ghosh, “Leveraging the Potential of Large Language Models,” Inform., vol. 48, no. 8, pp. 1–16, 2024, doi: 10.31449/inf.v48i8.5635.
R. Sonbol, G. Rebdawi, and N. Ghneim, “A Machine Translation Like Approach to Generate Business Process Model from Textual Description,” SN Comput. Sci., vol. 4, no. 3, pp. 1–16, 2023, doi: 10.1007/s42979-023-01742-z.
J. Köpke and A. Safan, “Introducing the BPMN-Chatbot for Efficient LLM-Based Process Modeling,” 2024. [Online]. Available: https://www.aau.at/en/isys/ics
T. Fehrer, D. A. Fischer, S. J. J. Leemans, M. Röglinger, and M. T. Wynn, “An assisted approach to business process redesign,” Decis. Support Syst., vol. 156, no. July 2021, 2022, doi: 10.1016/j.dss.2022.113749.
P. Delias and G. T. Nguyen, “Prototyping a business process improvement plan. An evidence-based approach,” Inf. Syst., vol. 101, p. 101812, 2021, doi: 10.1016/j.is.2021.101812.
F. Johannsen and H. G. Fill, “Meta Modeling for Business Process Improvement,” 2017, doi: 10.1007/s12599-017-0477-1.
Q. Zeng, J. Liu, C. Zhou, C. Liu, and H. Duan, “A Novel Approach for Business Process Similarity Measure Based on Role Relation Network Mining,” 2020, doi: 10.1109/ACCESS.2020.2983114.
S. Ayari, Y. B. Hlaoui, and L. Ben Ayed, “A specific language for developing business process by refinement based on BPMN 2.0,” Proc. 16th Int. Conf. Softw. Technol. ICSOFT 2021, no. July, pp. 489–496, 2021, doi: 10.5220/0010561404890496.
S. Arshad, I. S. Bajwa, and R. Kazmi, “Generating SBVR-XML Representation of a Controlled Natural Language,” in Communications in Computer and Information Science, 2019, vol. 932, pp. 379–390. doi: 10.1007/978-981-13-6052-7_33.
P. Danenas, T. Skersys, and R. Butleris, “Natural language processing-enhanced extraction of SBVR business vocabularies and business rules from UML use case diagrams,” Data Knowl. Eng., vol. 128, no. June 2019, p. 101822, 2020, doi: 10.1016/j.datak.2020.101822.
B. Estrada-Torres, M. Camargo, M. Dumas, L. García-Bañuelos, I. Mahdy, and M. Yerokhin, “Discovering business process simulation models in the presence of multitasking and availability constraints,” Data Knowl. Eng., vol. 134, no. December 2020, p. 101897, 2021, doi: 10.1016/j.datak.2021.101897.
T. Skersys, P. Danenas, R. Butleris, A. Ostreika, and J. Ceponis, “Extracting sbvr business vocabularies from uml use case models using m2m transformations based on drag-and-drop actions,” Appl. Sci., vol. 11, no. 14, 2021, doi: 10.3390/app11146464.
Q. Zeng, H. Duan, and C. Liu, “Top-Down Process Mining from Multi-Source Running Logs Based on Refinement of Petri Nets,” IEEE Access, vol. 8, pp. 61355–61369, 2020, doi: 10.1109/ACCESS.2020.2984057.
Q. Mo, F. Dai, D. Liu, J. Qin, Z. Xie, and T. Li, “Development of private processes: A refinement approach,” IEEE Access, vol. 7, pp. 31517–31534, 2019, doi: 10.1109/ACCESS.2018.2889715.
E. Bazhenova, F. Zerbato, B. Oliboni, and M. Weske, “From BPMN process models to DMN decision models,” Inf. Syst., vol. 83, pp. 69–88, 2019, doi: 10.1016/j.is.2019.02.001.
J. T. Licardo, N. Tankovic, and D. Etinger, “A Method for Extracting BPMN Models from Textual Descriptions Using Natural Language Processing,” in Procedia Computer Science, 2024, vol. 239, no. January, pp. 483–490. doi: 10.1016/j.procs.2024.06.196.
S. Sholiq, R. Sarno, and E. S. Astuti, “Generating BPMN diagram from textual requirements,” J. King Saud Univ. - Comput. Inf. Sci., vol. 34, no. 10, pp. 10079–10093, 2022, doi: 10.1016/j.jksuci.2022.10.007.
S. Sholiq, M. A. Yaqin, A. P. Subriadi, and B. Setiawan, “Generation of business process modeling notation diagrams from textual functional requirements in Indonesian,” Int. J. Electr. Comput. Eng., vol. 15, no. 3, pp. 2938–2950, 2025, doi: 10.11591/ijece.v15i3.pp2938-2950.
X. Han et al., “A-BPS: Automatic Business Process Discovery Service using Ordered Neurons LSTM,” Proc. - 2020 IEEE 13th Int. Conf. Web Serv. ICWS 2020, vol. 1, pp. 428–432, 2020, doi: 10.1109/ICWS49710.2020.00063.
A. Mustansir, K. Shahzad, and M. K. Malik, “Sentiment Analysis of User Feedback on Business Processes,” in Proceedings - 2021 36th IEEE/ACM International Conference on Automated Software Engineering Workshops, ASEW 2021, 2021, pp. 204–210. doi: https://doi.org/10.1109/ASEW52652.2021.00048.
S. Ahmed and K. Shahzad, “Augmenting Business Process Model Elements With End-User Feedback,” IEEE Access, vol. 10, no. October, pp. 115635–115651, 2022, doi: 10.1109/ACCESS.2022.3216418.
K. Baïna, M. El Hamlaoui, and H. Kabbaj, “Business Process Modelling Augmented: Model Driven transformation of User Stories to Processes,” ACM Int. Conf. Proceeding Ser., pp. 215–220, 2020, doi: 10.1145/3419604.3419793.
S. Ahmed and A. Mustansir, “Mapping Textual Feedback to Process Model Elements,” Proc. - 2020 35th IEEE/ACM Int. Conf. Autom. Softw. Eng. Work. ASEW 2020, pp. 131–137, 2020, doi: 10.1145/3417113.3423376.
S. Nasiri, Y. Rhazali, M. Lahmer, and N. Chenfour, “Towards a Generation of Class Diagram from User Stories in Agile Methods,” in Procedia Computer Science, 2020, vol. 170, pp. 831–837. doi: 10.1016/j.procs.2020.03.148.
P. Danenas and T. Skersys, “Exploring Natural Language Processing in Model-To-Model Transformations,” 2022, doi: 10.1109/ACCESS.2022.3219455.
D. C. Wynn and A. M. Maier, “Feedback systems in the design and development process,” Res. Eng. Des., vol. 33, no. 3, pp. 273–306, 2022, doi: 10.1007/s00163-022-00386-z.
L. Yan et al., “Practical and ethical challenges of large language models in education: A systematic scoping review,” Br. J. Educ. Technol., vol. 55, no. 1, pp. 90–112, 2024, doi: 10.1111/bjet.13370.
H. Waheed, S. U. Hassan, N. R. Aljohani, J. Hardman, S. Alelyani, and R. Nawaz, “Predicting academic performance of students from VLE big data using deep learning models,” Comput. Human Behav., vol. 104, 2020, doi: 10.1016/j.chb.2019.106189.
A. Praveen Kumar, A. Nayak, K. Manjula Shenoy, R. J. Manoj, and A. Priyadarshi, “Pattern-Based Syntactic Simplification of Compound and Complex Sentences,” IEEE Access, vol. 10, pp. 53290–53306, 2022, doi: 10.1109/ACCESS.2022.3174846.
P. Danenas, T. Skersys, and R. Butleris, “Natural language processing-enhanced extraction of SBVR business vocabularies and business rules from UML use case diagrams,” 2020, doi: 10.1016/j.datak.2020.101822.
S. Van Woensel, W.; Motie, “NLP4PBM: A systematic review on process extraction using natural language processing with rule based, machine and deep learning methods,” Enterp. Inf. Syst., 2024, [Online]. Available: https://doi.org/10.1080/17517575.2024.2417404
DOI:
https://doi.org/10.31449/inf.v50i8.12087Downloads
Published
How to Cite
Issue
Section
License
Authors retain copyright in their work. By submitting to and publishing with Informatica, authors grant the publisher (Slovene Society Informatika) the non-exclusive right to publish, reproduce, and distribute the article and to identify itself as the original publisher.
All articles are published under the Creative Commons Attribution license CC BY 3.0. Under this license, others may share and adapt the work for any purpose, provided appropriate credit is given and changes (if any) are indicated.
Authors may deposit and share the submitted version, accepted manuscript, and published version, provided the original publication in Informatica is properly cited.
