Leveraging Sentiment Analysis for Identifying Influential Users in Online Health Communities: A Case Study on the Lung Cancer Survivors Network

The intense impact of social media on individuals' lives is undeniable, where exposure to comments and posts often induces both positive and negative effects. Online health communities serve as supportive spaces where members aid each other. The Lung Cancer Survivors Network, emphasizing peer support, thrives on member contributions. Leveraging sentiment analysis aids in identifying and empowering influencers within these networks, Classification models are constructed after data preprocessing and various vectorization methods namely Term Frequency-Inverse Document Frequency (TF-IDF), bag of words and GloVe embeddings. Classifiers like AdaBoost, Random Forest, Naïve Bayes, Logistic Regression, and Long Short-Term Memory (LSTM) facilitate model creation, with LSTM using GloVe embeddings emerging as the most effective among them.