Medical Relevancy of Cancer-Related Tweets and Their Relation to Misinformation

Date of Award

2023

Document Type

Thesis

Degree Name

Bachelors

Department

Natural Sciences

First Advisor

Hamid, Fahmida

Keywords

medical tweets, cancer misinformation, misinformation detection, medical relevancy

Area of Concentration

Computer Science with Statistics Secondary Field

Abstract

The purpose of this study was to understand the medical relevancy of cancer-related tweets, and to explore whether they contained misinformation. We created a dataset of 494 tweets and labeled them according to their medical relevancy: medically relevant, not medically relevant, or unrelated to cancer. We then ran logistic regression and support vector machine models on them. We studied the differences between medically relevant and not medically relevant tweets with respect to word choice, and additional differences so found differences between tweets based on medical relevance word choice, and time. Additionally, our exploratory analysis identifies some patterns among misinformation that could be useful for further exploration.

This document is currently not available here.

Share

COinS