Health Informatics

1. Opinion Mining: Covid Vaccine Sentiment Analysis by Geographic Regions

We explore the sentiments surrounding Covid-19 vaccine adoption on Twitter. We focus on key regions of the US, particularly urban areas. We utilize machine learning models such as logistic regression, Support Vector Machines, and Naive Bayes to provide baseline models. Furthermore, we develop fine-tuned transformer-based language models that provide a classification of sentiments with high accuracy.

2. Understanding topic discussions on asthma web forums

This research involves the use of NLP techniques such as unsupervised machine learning and topic modeling techniques to understand how people living with asthma employ public discussion forums. Also, we explore the correlation between predictions such such as the degree of pollen prevalence during a specific season and the frequency of forum discussions. The goal is to understand and use this information to create tools that can better cater to the needs of asthma patients.

3. Graph representation learning for chronic disease prediction in underrepresented populations

This research aims to develop graph-based models that can help uncover insights in patient clinical data in underrepresented groups.