Search

BACKGROUND The increasing availability of "real-world" data in the form of written text holds promise for deepening our understanding of societal and health-related challenges. Textual data constitute a rich source of information, allowing the capture of lived experiences through a broad range of different sources of information (eg, content and emotional tone). Interviews are the "gold standard" for gaining qualitative insights into individual experiences and perspectives. However, conducting interviews on a large scale is not always feasible, and standardized quantitative assessment suitable for large-scale application may miss important information. Surveys that include open-text assessments can combine the advantages of both methods and are well suited for the application of natural language processing (NLP) methods. While innovations in NLP have made large-scale text analysis more accessible, the analysis of real-world textual data is still complex and requires several consecutive steps. OBJECTIVE We developed and subsequently examined the utility and scientific value of an NLP pipeline for extracting real-world experiences from textual data to provide guidance for applied researchers. METHODS We applied the NLP pipeline to large-scale textual data collected by the Swiss Multiple Sclerosis (MS) registry. Such textual data constitute an ideal use case for the study of real-world text data. Specifically, we examined 639 text reports on the experienced impact of the first COVID-19 lockdown from the perspectives of persons with MS. The pipeline has been implemented in Python and complemented by analyses of the "Linguistic Inquiry and Word Count" software. It consists of the following 5 interconnected analysis steps: (1) text preprocessing; (2) sentiment analysis; (3) descriptive text analysis; (4) unsupervised learning-topic modeling; and (5) results interpretation and validation. RESULTS A topic modeling analysis identified the following 4 distinct groups based on

BACKGROUND Informal and formal volunteering engagement is a proxy for social integration and may have beneficial effects for physical and mental well-being in persons with multiple sclerosis (pwMS). As literature on the topic among the pwMS is lacking, this study aimed to determine frequency and type of volunteering performed by pwMS and to identify factors associated with volunteering. METHODS Cross-sectional, self-reported data of 615 pwMS participating in the Swiss Multiple Sclerosis Registry were analyzed using descriptive statistics to determine frequency and type of volunteering engagement. Univariable and multivariable generalized linear models with binomial distribution and log link function were used to identify factors associated with volunteering. Age, sex, employment status and gait disability were added to the multivariable model as fixed confounders. Sociodemographic, health-, work- and daily activity-related factors were included in the analysis. RESULTS About one third (29.4%) of participants reported engagement in volunteering activities, most often through charities (16.02%) and cultural organizations (14.36%). In the multivariable model, participants who had a university degree were more likely to volunteer than those with lower level of education (RR = 1.48 95% CI [1.14; 1.91]). The ability to pursue daily activities (as measured by the EQ-5D subscale) was strongly associated with participation in volunteering among pwMS. Compared with pwMS who had no or only slight limitations in daily activities, those with severe problems were markedly less likely to engage in volunteering (RR = 0.41, 95% CI [0.21; 0.80]) . Finally, pwMS who reported caring for and supporting their family (i.e., being a homemaker) were more likely to engage in volunteering activities than those who did not (RR = 1.52, 95% CI [1.15; 2.01]). CONCLUSION Nearly one in three pwMS engaged in diverse volunteering activities. Having a university degree, being less limited in daily act