An NLP-Assisted Bayesian Time Series Analysis for Prevalence of Twitter Cyberbullying During the COVID-19 Pandemic

TL;DR

This study combines NLP and Bayesian time series modeling to analyze the prevalence and seasonality of cyberbullying on Twitter during the COVID-19 pandemic, revealing temporal patterns and potential pandemic effects.

Contribution

It introduces a novel approach integrating NLP-based offensive content detection with Bayesian autoregressive Poisson modeling for social media data analysis.

Findings

Strong weekly and yearly seasonality in hateful speech on Twitter.

Slight differences in cyberbullying trends across years, possibly due to COVID-19.

Method effectively adjusts for sampling limitations in social media data.

Abstract

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.