From data to insights: Machine learning in thematic analysis of complex health conditions on social media

Social media data has the potential to enable the exploration of public perspectives on health conditions, interventions and policies. However, the resource-intensive nature of qualitative analysis creates a barrier to the timely utilization of social media data. Artificial intelligence can provide innovative ways to reduce the burden by augmenting the data analysis process for researchers. Therefore, the purpose of this research is to explore the feasibility of using Machine Learning (ML) in augmenting thematic analysis of complex health issues data available on social media. First, we performed a human-determined deductive thematic analysis of the 7,177 comments posted by YouTube video viewers on postpartum depression. Then we used the same data to perform machine-assisted analysis using five Natural Language Processing (NLP) classification models with and without class balancing techniques (class weight balance and SMOTE) to balance the unequal number of comments across themes. Our analysis suggested that supervised machine learning may not be optimal for analyzing complex health datasets. However, integrating ML-NLP techniques with thematic analysis can effectively filter out ineligible data, thereby enhancing the efficiency of traditional thematic analysis processes. This integration allows researchers to focus on valuable data, producing meaningful insights and comprehensive analysis while saving time otherwise spent sifting through a large amount of ineligible data. Social media data can offer significant public health insights, and to enhance the use of such data, future research should focus on developing artificial intelligence tools to improve the efficiency of thematic analysis using larger datasets and unsupervised machine learning models for analyzing complex health issues.