Socialomics of Malaria with Topic Modelling

New avenues for social science study have opened up as social media data has grown increasingly rich and abundant. The new data-driven methodologies based on topic models have provided academics with a new perspective on social phenomena. Because social media information is brief, text-heavy, and unstructured, methodological hurdles emerge for both data analysis and collecting. To identify which deep learning model would best categorise our data, we employ deep learning models such as Convolutional Neural Networks (CNNs), Bidirectional Encoder Representations from Transformers (BERT), and Global Vectors for Word Representation (GloVe). The data for this article comes from Mumbai Malaria posts on Twitter. In contrast to machine learning approaches, these models proved to be highly exact and beneficial in the study of emotions.