Turning interviews into process models
Personal proposal by Per-Arne Andersen
S5 · Spring 2027
https://thesis.uya.no/proposals/from-conversation-to-process/

Turn interview transcripts into process diagrams while showing where each step came from.

TECHNICAL
- Use Qwen2.5-7B-Instruct to extract steps into JSON with transcript-line references.
- Render a process diagram and flag conflicting order or missing responsibility.

DATA (planned)
12 line-numbered scripts across 3 processes
Four role accounts each for leave/equipment/expenses; 2 same-context conflicts per process. Independently freeze step, sequence and conflict keys; separate real conflicts from valid role variants.
Qwen2.5-7B-Instruct: https://huggingface.co/Qwen/Qwen2.5-7B-Instruct
Transformers generation settings: https://huggingface.co/docs/transformers/main_classes/text_generation

METHOD
Same Qwen extraction instructions with/without source-reference requirements. Score step/edge precision–recall, support and conflict errors; assess citation accuracy only when citations exist. Four trainee analysts inspect diagrams and specify stakeholder follow-up.

OUTPUT
Diagram generator, transcripts and error analysis.

BACHELOR
Task: Build a transcript-to-process draft using an existing model and a fixed prompt.
Data: 12 line-numbered scripts across 3 processes (planned)
Four role accounts each for leave/equipment/expenses; 2 same-context conflicts per process. Independently freeze step, sequence and conflict keys; separate real conflicts from valid role variants.
Requires: Independent annotator, trainee analysts and inference compute; scripts must be authored.
Method: Use the scripted interviews; check steps/edges against the independent key and record analyst corrections. Plan 4 participant sessions.
Output: A process-drafting prototype and documented error types.
Use relevant literature to justify the established approach; a new research contribution is not the aim of this proposal.

MASTER
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.
Intended contribution: Design principles for traceable process modelling under conflicting evidence.

STARTING PAPERS
Berti et al. (2024) — Evaluating LLMs in Process Mining: https://arxiv.org/abs/2403.06749
Separate model syntax, process meaning and usefulness to process analysts.
Wang & Strong (1996) — Beyond Accuracy: https://www.tandfonline.com/doi/abs/10.1080/07421222.1996.11518099
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.

START HERE
Tools: Qwen2.5-7B-Instruct, Python, JSON, Mermaid
1. 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.
2. Mark supporting transcript lines and deliberate contradictions before trying the model.
3. Run extraction with one fixed prompt and validate the JSON and source references manually.
Literature search: business process modelling interview provenance ambiguity requirements
Study controls:
- Use actor/action/sequence JSON and unresolved-conflict flags; do not force a single story when accounts disagree.
- Report results by the 3 processes; 12 scripts or many individual steps are not independent processes.
- Pin greedy decoding and the complete inference setup.
- For generation, use do_sample=False and num_beams=1; record model/tokenizer revisions, runtime, quantisation, prompt and output limit. Keep failed outputs.
- Before collecting participant data, agree consent, storage and withdrawal handling with the supervisor. Use participant codes, not names, in study files.
- For the master’s study, use the research task above to define the factors and comparisons in this pilot plan. Preregister one primary outcome and feasible scope after the literature review; do not add every possible model or interface variant.

REQUIRES
Independent annotator, 4 trainee analysts and inference compute; scripts must be authored.

--------------------

NON-TECHNICAL
- Create process diagrams manually from the interview scripts.
- Ask participants to resolve conflicting accounts with and without transcript references.

DATA (planned)
6 scripted interviews + 8 IS students
Two processes, three role accounts each; insert two conflicting statements per process and preserve a reference map.


METHOD
8 IS students review disjoint, 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.

OUTPUT
Revised diagrams and guidance for documenting disputed steps.

BACHELOR
Task: Create and validate a process map from the scripted stakeholder interviews.
Data: 6 scripted interviews (planned)
Two processes, three role accounts each; insert two conflicting statements per process and preserve a reference map.
Requires: Recruit students; no diagram generator required.
Method: Use established process-modelling notation; keep unresolved contradictions visible and review the map in walkthroughs. Plan 4 participant sessions.
Output: A process map, evidence links and a requirements log.
Use relevant literature to justify the established approach; a new research contribution is not the aim of this proposal.

MASTER
Explain why stakeholders disagree about the same process. Use technological frames to contrast legitimate role-specific variants with factual contradictions; trace how each interpretation changes the proposed process map.
Intended contribution: An explanatory account of process-model disagreement and requirements reconciliation.

STARTING PAPERS
Orlikowski & Gash (1994) — Technological Frames: https://dl.acm.org/doi/10.1145/196734.196745
Compare how roles interpret the purpose, operation and use of the same system.
Berti et al. (2024) — Evaluating LLMs in Process Mining: https://arxiv.org/abs/2403.06749
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.

START HERE
Tools: LibreOffice Writer/Calc, audio recorder with consent; no programming required.
1. Prepare a pilot with 2 examples from: 6 scripted interviews + 8 IS students. Write the task questions and a reference answer sheet.
2. Write a recruitment message, information sheet and consent form for the participants named above. Agree privacy handling with the supervisor before contact.
3. Pilot one session after approval; revise unclear questions, freeze the task sets and coding categories, then recruit the planned sample.
Literature search: business process modelling interview provenance ambiguity requirements qualitative scenario study
Study controls:
- No model running or diagram generator is required. Prepare the reference diagram and answer key independently before participant review.
- Before collecting participant data, agree consent, storage and withdrawal handling with the supervisor. Use participant codes, not names, in study files.
- Pilot separately, then freeze the questions and coding plan. Check objective answer keys independently; keep an audit trail of coding, including disagreements.
- For comparisons, counterbalance order and case assignment; do not show a person both versions of one case. Report participant-level findings, not repeated tasks as independent people.

REQUIRES
Recruit students; no diagram generator required.

Bachelor: apply established methods and evaluate a practical solution or study. Master: position a research question in current scientific literature, investigate a mechanism or unresolved problem, and explain the contribution. Final scope is agreed with me.
Study sizes are proposed; participant recruitment and planned materials are not already arranged.