Audit what a feed amplifies
Measure how different ranking rules change what users see in a controlled social-media feed.
Technical
Bachelor’s · applied project
Final result
Working simulator, three rankers, automated tests and comparison dashboard.
Material to create
400-item controlled feed benchmark
Create neutral proxy content across 8 topics and 20 sources, plus 50 profiles. finalise all labels and generator settings before comparison.
What to do
- Build a replayable feed and compare chronological, engagement-only and diversity-constrained ranking.
How it is tested
Use 400 synthetic items and 50 fixed profiles. Run 10 sessions per profile with fixed seeds; report source concentration, topic diversity, NDCG@10 and invariant-test results.
Before you start
Example tools · Python, pandas, NumPy, scikit-learn, FastAPI, Streamlit or React These are suggestions; equivalent tools are fine.
Access or people · Independent review of the synthetic labels and scenarios.
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 400-item controlled feed benchmark. Make the answer key and pass criteria before testing.
- Build a working version of working simulator, three rankers, automated tests and comparison dashboard.
- 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
Deterministic feed simulator, five rankers, audit dashboard, benchmark and policy trade-off report.
Material to create
1,200-item controlled feed benchmark
Create 1,200 synthetic, non-extremist items across 12 proxy topics and 60 sources. Store item_id, source_id, topic, created_at, relevance, predicted_engagement, quality, risk_proxy and annotator confidence. Create 200 fixed user profiles with topic preferences and exposure history. No live platform accounts or scraped extremist content.
What to do
- Implement five deterministic ranking policies over one versioned item/profile contract with replayable sessions and no live-platform collection.
- Test ranking invariants, stable ties, exposure accounting and audit-trace completeness across fixed seeds and counterfactual policy runs.
- Measure risk exposure, concentration, diversity, benign relevance, calibration and latency at profile level; keep reviewer task effects separate from ranking metrics.
How it is tested
Run every ranker on the same 200 profiles and 20 sessions with fixed seeds. Report risky-exposure@10, source/topic concentration, intra-list diversity, NDCG@10 for benign relevance, calibration and latency. Compare policies with paired profile-level intervals. In a task study, test whether the audit view helps 8 reviewers identify the rule responsible for a harmful exposure pattern.
Before you start
Example tools · Python, pandas, NumPy, scikit-learn, FastAPI, Streamlit or React These are suggestions; equivalent tools are fine.
Access or people · Independent review of the synthetic labels and scenarios; recruit 8 reviewers for the master task study.
Start with these three actions
- Write the schema and generator distributions; independently review 30 items and 10 profiles before generating the fixed benchmark.
- Implement chronological and engagement-only ranking first; add deterministic replay and invariant tests.
- finalise measures, seeds and policy parameters before running the remaining rankers and reviewer study.
Files, questions and sources
Pilot question: Which ranking rules reduce repeated exposure to risky proxy content without destroying useful relevance and diversity?
Literature search: recommender system algorithmic amplification extremism audit exposure diversity risk utility
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 1,200-item controlled feed benchmark.
- Draw the user workflow, data model and system architecture. List the requirements and pass criteria.
- Build a working version of deterministic feed simulator, five rankers, audit dashboard, benchmark and policy trade-off report.
- 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: Design and evaluate a ranking policy that makes exposure risk auditable while preserving relevance and viewpoint/source diversity.
Research result: A reproducible offline audit method and evidence about the trade-offs between engagement, relevance, diversity and risky exposure.
Current project literature
- Causally estimating the effect of YouTube’s recommender system using counterfactual bots (2024) peer-reviewed journal article
Separates recommender effects from user preferences and shows why audit claims need a counterfactual design. - 8–10% of algorithmic recommendations are bad, but… an exploratory risk-utility meta-analysis (2024) peer-reviewed journal article
Frames recommendation design as a measurable risk–utility trade-off rather than a one-sided accuracy problem.
IS theory starting points
- Haroon et al. (2024) — Causally estimating the effect of YouTube’s recommender system — Ground causal claims and distinguish user choice from recommender effects.
- Hoffmann et al. (2024) — 8–10% of algorithmic recommendations are bad, but… — Define measurable risk–utility trade-offs instead of assuming all recommendations are harmful.
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: recommender system algorithmic amplification extremism audit exposure diversity risk utility
Non-technical
Bachelor’s · applied project
Final result
Comparison table, evidence gaps and a plain-language disclosure template.
Dataset
12 public recommender documents from four platforms
Collect one recommender description, one user-control page and one policy/transparency document per platform. finalise date, URL and PDF.
What to do
- Compare what four platforms tell users about why content is recommended and which controls users receive.
How it is tested
Code 12 fixed public documents with an established transparency checklist. Double-code 3 documents and report differences by platform and document type.
Before you start
Example tools · Zotero, LibreOffice Calc, Taguette or NVivo; no programming required. These are suggestions; equivalent tools are fine.
Access or people · No participant recruitment; agree the four platforms and document date with the supervisor.
Research method · Study and improve · 6 steps
- Read the starting sources and write the exact information problem.
- Prepare 12 public recommender documents from four platforms 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 comparison table, evidence gaps and a plain-language disclosure template. List the three most useful changes.
Download the complete bachelor plan
Download bachelor instructionsMaster’s · research project
Final result
A source table for each platform, a platform-by-platform comparison and a disclosure template for recommender audits.
Dataset
24 public platform and DSA documents + 8–10 professional interviews
For six named platforms, collect one recommender description, one terms/policy document, one DSA risk or transparency report and one independent audit/regulator document dated 2024–2027. finalise URLs and PDFs before coding. Interview researchers, prevention professionals or regulators—not young people or platform users.
What to do
- Collect the current recommender descriptions, DSA risk reports and audit summaries from six large platforms.
- Code each document for stated objective, user control, risk measure, youth protection, evidence and external scrutiny.
- Compare the documents with 8–10 professional interviews about what evidence is actually useful for oversight.
How it is tested
Use a predefined document-coding matrix and double-code 20% of documents. Compare stated objectives, risk measures, user controls and evidence across platforms. Use the interviews to test where disclosures support or block an oversight task; retain other explanations and negative cases.
Before you start
Example tools · Zotero, LibreOffice Calc, Taguette or NVivo; no programming required. These are suggestions; equivalent tools are fine.
Access or people · Recruit 8–10 relevant professionals; obtain consent and avoid operationally sensitive case information.
Start with these three actions
- Name the six platforms and four required document types; archive a dated copy of every source.
- Pilot the coding matrix on two platforms and double-code four documents; revise and finalise it.
- Prepare an oversight task and interview guide; recruit only professionals and exclude case-specific operational details.
Files, questions and sources
Pilot question: What information do professionals need to judge whether a recommender risk claim is credible?
Literature search: platform recommender transparency algorithm audit governance youth extremism DSA
Interview prompts
- Which disclosure would let you check a platform’s risk claim?
- What important information is missing or impossible to compare?
- Which control should belong to users, platforms or regulators?
Empty CSV templates: data-plan.csv · evaluation.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 24 public platform and DSA documents + 8–10 professional interviews.
- 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 platform disclosures make recommender risk more or less observable to researchers, regulators and prevention professionals.
Research result: A cross-platform observability framework and evidence-based minimum disclosure requirements for recommender oversight.
Current project literature
- Causally estimating the effect of YouTube’s recommender system using counterfactual bots (2024) peer-reviewed journal article
Separates recommender effects from user preferences and shows why audit claims need a counterfactual design. - 8–10% of algorithmic recommendations are bad, but… an exploratory risk-utility meta-analysis (2024) peer-reviewed journal article
Frames recommendation design as a measurable risk–utility trade-off rather than a one-sided accuracy problem.
IS theory starting points
- Leerssen (2024) — Outside the Black Box — Distinguish transparency from the practical observability needed for oversight.
- Gleiss et al. (2023) — Identifying the patterns of platform regulation — Structure the comparison of regulatory problems and response instruments.
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: platform recommender transparency algorithm audit governance youth extremism DSA
Your degree, track and shortlist are saved in this browser.