After many years of stimulating exchanges in the Methods and Research Meetings, we are excited to launch their successor: the DReMSS Sessions. This new series builds on the same spirit of methodological exchange and innovation, but with a refreshed format and broader scope.
The Developments in Research and Methods in the Social Sciences (DReMSS) Platform coordinates and showcases research collaborations between the Faculty of Social and Political Sciences (SSP) at the University of Lausanne and FORS, the Swiss Centre of Expertise in the Social Sciences. A key empirical strand of this joint research programme is centred around survey methods and methodological innovations linked to quantitative social science data collection and analysis.
The DReMSS Sessions bring together researchers to share cutting-edge methodological developments, tackle survey and data analysis challenges, and learn from leading experts in the field.
The sessions take one of three formats:
Twice per semester, researchers affiliated to the DReMSS platform and FORS will present the results of recent methodological research or demonstrate analytic methods using specific datasets in a webinar format, providing an opportunity to showcase our work to a broader, international audience.
Do you need help with survey design or data analysis challenges? Would you like input on the design of methodological research linked to your survey or with analyses? Once a semester, we will meet to discuss specific methodological challenges in our work, providing an opportunity for survey researchers to consult and get feedback on work-in-progress, and to share expertise.
Once a semester, we invite you to join DReMSS members for an in-depth skills refresh with leading experts in methodological developments currently impacting survey practice;
Save the date!
Webinar: Monday, April 20, 2026 | 13:00–14:30, online
Theme: Harnessing Generative AI for questionnaire design, evaluation and testing.
Presenters: Patrick Sturgis, Department of Methodology, London School of Economics and Political Science & Caroline Roberts, Institute of Social Sciences, University of Lausanne
Abstract:
This webinar examines how generative AI can be integrated into the questionnaire design and evaluation process. Rather than treating large language models as ad hoc drafting tools, we discuss structured, workflow-embedded applications that support measurement quality at multiple stages of survey development. Several use cases are discussed, along with findings from validation exercises.
First, we present an occupational coding application that maps open-ended job descriptions to SOC2020 classifications using structured prompts and validation routines, illustrating how AI can support consistent and scalable post-fieldwork coding. We also describe how the tool can be embedded in a dynamic questionnaire design and generate intelligent follow-ups to probe unclassifiable answers. Second, a “Silicon Sampling” generator is presented that simulates heterogeneous respondent personas to stress-test draft questions at scale, identifying ambiguity, response instability, and potential measurement error prior to fielding. Third, an AI-enabled cognitive interviewing tool that operationalises probing protocols to examine comprehension, retrieval, judgement, and response processes in a systematic and reproducible way. Fourth, we present an example of a scalable pipeline for LLM evaluations of draft survey questions using rule-based question evaluation frameworks designed to identify question features that cause response challenges) (in this case, the Question Appraisal System (QAS-99). We share the results of a validation exercise to assess how LLM evaluations using the QAS compare with those of human experts and novices. Finally, we discuss how such tools can be integrated into an agentic workflow to support survey questionnaire development.
Register to get the link to the webinar: https://newsletter.forscenter.ch/newsletter/index.php/lists/ba9900td3g179/subscribe
Calendar
| Session Dates | Planned Sessions |
|---|---|
| Monday 15 September 2025 (13.00–14.00) | Webinar (online) |
| Monday 20 October 2025 (13.00–14.30) | Survey Surgery (room 5621 Géopolis) |
| Monday 17 November 2025 (13.00–14.00) | Webinar (online) |
| Monday 15 December 2025 (13.00–16.00) (postponed) | Expert Workshop (room 5621 Géopolis) |
| Monday 23 February 2026 (13.00–14.00) (postponed) | Webinar (online) |
| Monday 23 March 2026 (14.00–15.30) | Survey Surgery (room 5621 Géopolis) |
| Monday 20 April 2026 (13.00–14.30) | Webinar (online) |
| Monday 18 May 2026 (13.00–16.00) | Expert Workshop (room 5621 Géopolis) |
DReMSS Session Recordings
Missed a session? You can now watch the recordings of past DReMSS Sessions below:
Rethinking Gender Measures in Population Surveys (Roxane Mordasini and Stephanie Steinmetz), September 15, 2025
Fixed-Efects Panel Modelling in Practice (Oliver Lipps and Nicolas Sommet), November 17, 2025
The organisers
Caroline Roberts
Oliver Lipps
Stephanie Steinmetz
Marc Asensio Manjon


