Turning interviews into process models
Turn interview transcripts into process diagrams while showing where each step came from.
Technical
Bachelor’s · applied project
Final result
A process-drafting prototype and documented error types.
Material to create
12 line-numbered scripts across 3 processes
Four role accounts each for leave/equipment/expenses; 2 same-context conflicts per process. Independently finalise step, sequence and conflict keys; separate real conflicts from valid role variants.
What to do
- Build a transcript-to-process draft using an existing model and a fixed prompt.
How it is tested
Use the scripted interviews; check steps/edges against the independent key and record analyst corrections. Plan 4 participant sessions.
Before you start
Example tools · Qwen2.5-7B-Instruct, Python, Pydantic, BPMN 2.0 XML, bpmn-js These are suggestions; equivalent tools are fine.
Access or people · Independent annotator, trainee analysts and inference compute; scripts must be authored.
Research method · Build and test · 6 steps
- Read the starting sources and choose one established implementation method.
- Write the requirements, data fields, system diagram and test cases.
- Prepare 12 line-numbered scripts across 3 processes. Make the answer key and pass criteria before testing.
- Build a working version of a process-drafting prototype and documented error types.
- Run function, integration and failure-case tests. Record each result.
- Run the practical evaluation and list the changes the system still needs.
Download the complete bachelor plan
Download bachelor instructionsMaster’s · research project
Final result
Validated JSON-to-BPMN pipeline, rendered diagrams, provenance links and error analysis.
Material to create
12 line-numbered scripts across 3 processes
Four role accounts each for leave/equipment/expenses; 2 same-context conflicts per process. Independently finalise step, sequence and conflict keys; separate real conflicts from valid role variants.
What to do
- Extract line-numbered scripts into a Pydantic actor/task/gateway/sequence/provenance/conflict schema, export BPMN 2.0 XML and render with bpmn-js.
- Benchmark provenance-constrained versus unconstrained extraction, then hold the fixed draft constant while showing analyst source links on/off.
- Verify JSON/BPMN schemas, token-flow soundness and citation offsets; report element/edge/conflict precision-recall, graph edit distance, corrections and time.
How it is tested
Use 12 line-numbered scripts and an independent dual-modeller gold BPMN. Report task/edge/conflict/citation precision-recall, graph edit distance, JSON/BPMN validity and token-flow soundness. Four trainee analysts inspect fixed drafts with links on/off; record justified corrections and time.
Before you start
Example tools · Qwen2.5-7B-Instruct, Python, Pydantic, BPMN 2.0 XML, bpmn-js These are suggestions; equivalent tools are fine.
Access or people · Independent annotator, 4 trainee analysts and inference compute; scripts must be authored.
Start with these three actions
- Write the three role accounts for one approval process and manually draw a reference diagram. Confirm access to inference compute and record model, software and hardware versions.
- Mark supporting transcript lines and deliberate contradictions before trying the model.
- Run extraction with one fixed prompt and validate the JSON and source references manually.
Files, questions and sources
Pilot question: Do transcript references improve the correctness and reviewability of generated process models?
Literature search: business process modelling interview provenance ambiguity requirements
Empty CSV templates: data-plan.csv · evaluation.csv · literature-matrix.csv
Download starter instructionsResearch method · Design, build and test (DSR) · 7 steps
- Read the newest papers and list the closest existing systems.
- Write down the versions, fields, data split, case assignment, random seeds and correct answers for 12 line-numbered scripts across 3 processes.
- Draw the user workflow, data model and system architecture. List the requirements and pass criteria.
- Build a working version of validated json-to-bpmn pipeline, rendered diagrams, provenance links and error analysis.
- Test every function, connection and failure case. Save the failed tests as well as the passed tests.
- Compare the system with the named alternative. Then run the user task or decision task in the assignment.
- Report the measured result, the failed cases and the design lessons another team can reuse.
Research question and sources
Research question: Investigate how source-linked process drafts handle conflicting stakeholder accounts. Separate syntax, step/edge correctness and analyst correction; compare identical drafts with/without source links and distinguish contradictions from legitimate process variants.
Research result: Design principles for traceable process modelling under conflicting evidence.
Current project literature
- LLM-based Business Process Models Generation from Textual Descriptions (2025) peer-reviewed
Provides a current method and benchmark framing for text-to-process-model generation. - Evaluating Large Language Models in Process Mining (2024) peer-reviewed
Maps current LLM capabilities and limitations in process-analysis tasks.
IS theory starting points
- Berti et al. (2024) — Evaluating LLMs in Process Mining — Separate model syntax, process meaning and usefulness to process analysts.
- Wang & Strong (1996) — Beyond Accuracy — Distinguish accuracy, completeness, representation and fitness for the task.
Search Scopus or Web of Science and ACM Digital Library using the topic query, then follow citations to the thesis start date. Record searches and compare methods, data, findings and limitations in literature-matrix.csv. Use that review to confirm or revise the gap and choose a current comparator. The linked papers are starting points.
Search terms: business process modelling interview provenance ambiguity requirements
Non-technical
Bachelor’s · applied project
Final result
A process map, evidence links and a requirements log.
Material to create
6 scripted interviews
Two processes, three role accounts each; insert two conflicting statements per process and preserve a reference map.
What to do
- Create and validate a process map from the scripted stakeholder interviews.
How it is tested
Use established process-modelling notation; keep unresolved contradictions visible and review the map in walkthroughs. Plan 4 participant sessions.
Before you start
Example tools · LibreOffice Writer/Calc, audio recorder with consent; no programming required. These are suggestions; equivalent tools are fine.
Access or people · Recruit students; no diagram generator required.
Research method · Study and improve · 6 steps
- Read the starting sources and write the exact information problem.
- Prepare 6 scripted interviews and a separate answer sheet or coding sheet.
- Run one pilot and fix unclear questions.
- Collect the named evidence with consent.
- Group the findings with the stated categories and check the answer sheet.
- Produce a process map, evidence links and a requirements log. List the three most useful changes.
Download the complete bachelor plan
Download bachelor instructionsMaster’s · research project
Final result
Revised diagrams, provenance-use findings and guidance for documenting disputed steps.
Material to create
6 scripted interviews + 8 IS students
Two processes, three role accounts each; insert two conflicting statements per process and preserve a reference map.
What to do
- Create process diagrams manually from the interview scripts.
- Ask participants to resolve conflicting accounts with and without transcript references.
How it is tested
8 IS students review non-overlapping, identical manual diagrams with references visible or hidden; source scripts remain available in both conditions. Count verified conflicts, false alarms and justified revisions; code whose account is preferred.
Before you start
Example tools · LibreOffice Writer/Calc, audio recorder with consent; no programming required. These are suggestions; equivalent tools are fine.
Access or people · Recruit students; no diagram generator required.
Start with these three actions
- Prepare a pilot with 2 examples from: 6 scripted interviews + 8 IS students. Write the task questions and a reference answer sheet.
- Write a recruitment message, information sheet and consent form for the participants named above. Agree privacy handling with the supervisor before contact.
- Pilot one session after approval; revise unclear questions, finalise the task sets and coding categories, then recruit the planned sample.
Files, questions and sources
Pilot question: How do references influence the way participants resolve conflicting process accounts?
Literature search: business process modelling interview provenance ambiguity requirements qualitative scenario study
Interview prompts
- Which process step is supported by this account?
- Where do the accounts disagree?
- Would you resolve or preserve the disagreement, and why?
Empty CSV templates: study-plan.csv · coding-sheet.csv · literature-matrix.csv
Download starter instructionsResearch method · Study, compare and explain · 7 steps
- Read the newest papers and write one exact research question.
- State which people, cases or documents you will study and what you will compare.
- Write the selection rules, questions and analysis steps for 6 scripted interviews + 8 IS students.
- Run one pilot. Fix unclear questions or categories, then keep the guide unchanged.
- Collect the named interviews, cases or documents with consent.
- Analyse them with the stated comparison or coding method. Keep disagreements and missing data.
- Report the answer, the evidence and the practical output named in the assignment.
Research question and sources
Research question: Explain how novice analysts identify and reconcile scripted contradictions and legitimate role variants. Compare source references visible/hidden and trace each justified map revision to the supplied evidence.
Research result: A guide showing how novice analysts reconcile conflicting statements in the supplied interview scripts.
Current project literature
- LLM-based Business Process Models Generation from Textual Descriptions (2025) peer-reviewed
Provides a current method and benchmark framing for text-to-process-model generation. - Evaluating Large Language Models in Process Mining (2024) peer-reviewed
Maps current LLM capabilities and limitations in process-analysis tasks.
IS theory starting points
- Orlikowski & Gash (1994) — Technological Frames — Compare how roles interpret the purpose, operation and use of the same system.
- Berti et al. (2024) — Evaluating LLMs in Process Mining — Separate model syntax, process meaning and usefulness to process analysts.
Search Scopus or Web of Science and ACM Digital Library using the topic query, then follow citations to the thesis start date. Record searches and compare methods, data, findings and limitations in literature-matrix.csv. Use that review to confirm or revise the gap and choose a current comparator. The linked papers are starting points.
Search terms: business process modelling interview provenance ambiguity requirements qualitative scenario study
Your degree, track and shortlist are saved in this browser.