An NLP-Assisted Bayesian Time Series Analysis for Prevalence of Twitter Cyberbullying During the COVID-19 Pandemic
This work addresses the problem of tracking online abuse trends for researchers and policymakers, but it is incremental as it applies existing NLP and Bayesian methods to new pandemic-related data.
The study tackled the problem of measuring cyberbullying prevalence on Twitter during the COVID-19 pandemic by analyzing 1 million tweets from 2019 to 2021, using NLP to classify abusive content and a Bayesian model to adjust for sampling limitations. The results revealed strong weekly and yearly seasonality in hateful speech, with slight differences across years potentially linked to COVID-19.
COVID-19 has brought about many changes in social dynamics. Stay-at-home orders and disruptions in school teaching can influence bullying behavior in-person and online, both of which leading to negative outcomes in victims. To study cyberbullying specifically, 1 million tweets containing keywords associated with abuse were collected from the beginning of 2019 to the end of 2021 with the Twitter API search endpoint. A natural language processing model pre-trained on a Twitter corpus generated probabilities for the tweets being offensive and hateful. To overcome limitations of sampling, data was also collected using the count endpoint. The fraction of tweets from a given daily sample marked as abusive is multiplied to the number reported by the count endpoint. Once these adjusted counts are assembled, a Bayesian autoregressive Poisson model allows one to study the mean trend and lag functions of the data and how they vary over time. The results reveal strong weekly and yearly seasonality in hateful speech but with slight differences across years that may be attributed to COVID-19.