Description

Disease outbreaks consist of the observation of more than 3 local cases of a disease. For example, according to CDC in the US measles was eliminated in 2000, but came back in 28 States and killed 110,000 people in 2017.

In this work, we aim to analyze social media (to begin with, Twitter) to map how vaccination hesitancy influences epidemiological outbreaks. Our goal is to examine if negative sentiment related to vaccination precedes declaration of symptoms. We also intend to use external datasets, such as metabiota, that consist of start and end of outbreaks.

Our pipeline is as follow:

Collect datasets:

prior knowledge from the literature, resources, datasets

Create analysis:

Build Twitter/Youtube API to scan comments and Tweets for negative sentiments about vaccination Build a dictionary of symptoms to match in tweets to extract disease outbreaks

Prior work

Paper from Sune Lehmann group:

Algorithmic Detection and Analysis of Vaccine-Denialist Sentiment Clusters in Social Networks

by Bjarke Mønsted and Sune Lehmann

https://arxiv.org/pdf/1905.12908.pdf

Figure 1: The top 10 most linked to domains by strongly antivaxx and provaxx profiles. Bar length shows percentage of the total number of links shared by profiles in the given category and hence do not sum to 100. For each domain, the red bars going right represent antivaxxers and blue bars going left provaxxers. Antivaxxers rely heavily on links to Youtube, and the page ’natural news’, which promulgates pseudoscience and sells products related to health and nutrition. Provaxxers link to a wide array of news and science sites, which is why a lower overall percentage of their links are contained in the top 10

Measure of outbreaks

Main network picture in logo from https://www.wired.com/2015/06/antivaxxers-influencing-legislation/.