Blending citizen science with natural language processing and machine learning - Understanding the experience of living with multiple sclerosis

Aug 4, 2026

Upload by Finn

The emergence of digital technologies enables new research approaches through active collaboration with the public (“citizen science”). Advances in machine learning (ML) and natural language processing (NLP) allow efficient analysis of large-scale text to study individual perspectives. This study blends citizen science with NLP/ML to identify central life-event categories perceived by people with multiple sclerosis (MS) and the associated emotions, then relates findings to standardized individual-level measures.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages23

Reading Time58 min

AccessFree to download

Abstract

Study design and data source

NLP/ML methods and emotion analysis

Topic modeling results

Implications for MS research

source: [https://doi.org/10.48350/185191 | downloaded:](https://doi.org/10.48350/185191 | downloaded:) 7.8.2023 PLOS DIGITAL HEALTH OPEN ACCESS Citation: Haag C, Steinemann N, Chiavi D, Kamm CP, Sieber C, Manjaly Z-M, et al. (2023) Blending citizen science with natural language processing and machine learning: Understanding the experience of living with multiple sclerosis. PLOS Digit Health 2(8): e0000305 . [https://doi.org/](https://doi.org/)[ ](https://doi.org/)[10.1371/journal.pdig.0000305](10.1371/journal.pdig.0000305) Editor: Amara Tariq, Mayo Clinic Arizona, UNITED STATES Received: February 8, 2023 Accepted: June 20, 2023 Published: August 2, 2023 Copyright: © 2023 Haag et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited. Data Availability Statement: We provide the emotion probability scores and anonymized excerpts of the data on OSF: [https://doi.org/10](https://doi.org/10) . 17605/OSF. IO/TJ8M9 . Funding: This research was supported by a grant from the Swiss Multiple Sclerosis Society awarded to the University of Zurich (no grant number; to MAP) . The funders had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript. RESEARCH ARTICLE Blending citizen science with natural language processing and machine learning: Understanding the experience of living with multiple sclerosis Christina Haag1,2, Nina Steinemann2, Deborah Chiavi2, Christian P. Kamm3,4, Chlo´e Sieber1,2, Zina-Mary Manjaly5,6, G´abor Horv´ath2, Vladeta Ajdacic-Gross2, Milo Alan Puhan2, Viktor von Wyl1,2 * 1 Institute for Implementation Science in Health Care, University of Zurich, Switzerland, 2 Epidemiology, Biostatistics and Prevention Institute, University of Zurich, Switzerland, 3 Neurocentre, Lucerne Cantonal Hospital, Lucerne, Switzerland, 4 Department of Neurology, Inselspital, Bern University Hospital, University of Bern, Switzerland, 5 Department of Neurology, Schulthess Klinik, Zurich, Switzerland, 6 Department of Health Sciences and Technology, ETH Zurich, Zurich, Switzerland * [viktor.vonwyl@uzh.ch](viktor.vonwyl@uzh.ch) Abstract The emergence of new digital technologies has enabled a new way of doing research, including active collaboration with the public (‘citizen science’) . Innovation in machine learning (ML) and natural language processing (NLP) has made automatic analysis of largescale text data accessible to study individual perspectives in a convenient and efficient fashion. Here we blend citizen science with innovation in NLP and ML to examine (1) which categories of life events persons with multiple sclerosis (MS) perceived as central for their MS; and (2) associated emotions. We subsequently relate our results to standardized individuallevel measures. Participants (n = 1039) took part in the ’My Life with MS’ study of the Swiss MS Registry which involved telling their story through self-selected life events using text descriptions and a semi-structured questionnaire. We performed topic modeling (‘latent Dirichlet allocation’) to identify high-level topics underlying the text descriptions. Using a pre-trained language model, we performed a fine-grained emotion analysis of the text descriptions. A topic modeling analysis of totally 4293 descriptions revealed eight underlying topics. Five topics are common in clinical research: ‘diagnosis’,‘medication/treatment’,‘relapse/child’,‘rehabilitation/wheelchair’, and ‘injection/symptoms’. However, three topics,‘work’,‘birth/health’, and ‘partnership/MS’ represent domains that are of great relevance for participants but are generally understudied in MS research. While emotions were predominantly negative (sadness, anxiety), emotions linked to the topics ‘birth/health’ and‘partnership/MS’ was also positive (joy) . Designed

FAQs

How does the study combine citizen science with NLP and machine learning?

Participants in the “My Life with MS” study described self-selected life events using text and a semi-structured questionnaire. The researchers then applied topic modeling and pre-trained language models for fine-grained emotion analysis on the text descriptions.

What data and participant sample were used?

A total of 1039 participants took part in the Swiss MS Registry “My Life with MS” project, providing 4293 text descriptions of life events.

What emotional patterns did the researchers observe across topics?

Emotions were predominantly negative (e.g., sadness, anxiety). Emotions linked to the topics “birth/health” and “partnership/MS” were also positive, including joy.

Aug 4, 2026

Upload by Finn