Evaluation of Facebook as a Longitudinal Data Source for Parkinson's Disease Insights

Background/Objectives: Parkinson's disease (PD) is a neurodegenerative disorder with a prolonged prodromal phase and progressive symptom burden. Traditional monitoring relies on clinical visits post-diagnosis, limiting the ability to capture early symptoms and real-world disease progression outside structured assessments. Social media provides an alternative source of longitudinal, patient-driven data, offering an opportunity to analyze both pre-diagnostic experiences and later disease manifestations. This study evaluates the feasibility of using Facebook to analyze PD-related discourse and disease timelines. Methods: Participants (N = 60) diagnosed with PD, essential tremor, or atypical parkinsonism, along with caregivers, were recruited. Demographic and clinical data were collected during structured interviews. Participants with Facebook accounts shared their account data. PD-related posts were identified using a Naïve Bayes classifier (recall: 0.86, 95% CI: 0.84-0.88, AUC = 0.94) trained on a ground-truth dataset of 6750 manually labeled posts. Results: Among participants with PD (PwPD), Facebook users were significantly younger but had similar Movement Disorder Society-United Parkinson's Disease Rating Scale scores and disease duration compared to non-users. Among Facebook users with PD, 90% had accounts before diagnosis, enabling retrospective analysis of pre-diagnostic content. PwPD maintained 14 ± 3 years of Facebook history, including 5 ± 6 years pre-diagnosis. On average, 3.6% of all posts shared by PwPD were PD-related, and 1.7% of all posts shared before diagnosis were PD-related. Overall, 69% explicitly referenced PD, and 93% posted about PD-related themes. Conclusions: Facebook is a viable platform for studying PD progression, capturing both early content from the premorbid period and later-stage symptoms. These findings support its potential for disease monitoring at scale.