Medfluencer: A Network Representation of Medical Influencers' Identities and Discourse on Social Media

TL;DR

This paper constructs a socio-semantic network of top medical influencers on Twitter during COVID-19, using machine learning and topic modeling to analyze their identities and discourse impact on public health.

Contribution

It introduces a novel network model combining influencer identities and thematic content, utilizing a few-shot classifier and BERTopic for social media health discourse analysis.

Findings

Identified key influencers and their thematic focus areas.

Mapped the influence network on public health discussions.

Provided a reproducible framework for analyzing social media health discourse.

Abstract

In our study, we first constructed a dataset from the tweets of the top 100 medical influencers with the highest Influencer Score during the COVID-19 pandemic. This dataset was then used to construct a socio-semantic network, mapping both their identities and key topics, which are crucial for understanding their impact on public health discourse. To achieve this, we developed a few-shot multi-label classifier to identify influencers and their network actors' identities, employed BERTopic for extracting thematic content, and integrated these components into a network model to analyze their impact on health discourse. To ensure the reproducibility of our results, we have made the code available at https://github.com/ZhijinGuo/Medinfluencer.