Healthy Twitter discussions? Time will tell

TL;DR

This paper investigates the health of online discussions, especially during early COVID-19, using temporal patterns and a novel concept of ephemerality to characterize and potentially label discussion quality without relying on ground truth.

Contribution

It introduces a new approach using temporal dynamics and ephemerality to analyze discussion health in the absence of labeled data, focusing on early COVID-19 debates.

Findings

Unsupervised characterization of discussion types based on volume and timing.

Formalization of ephemerality as an indicator of discussion health.

Discussion of potential for labeling online discourse health using ephemerality.

Abstract

Studying misinformation and how to deal with unhealthy behaviours within online discussions has recently become an important field of research within social studies. With the rapid development of social media, and the increasing amount of available information and sources, rigorous manual analysis of such discourses has become unfeasible. Many approaches tackle the issue by studying the semantic and syntactic properties of discussions following a supervised approach, for example using natural language processing on a dataset labeled for abusive, fake or bot-generated content. Solutions based on the existence of a ground truth are limited to those domains which may have ground truth. However, within the context of misinformation, it may be difficult or even impossible to assign labels to instances. In this context, we consider the use of temporal dynamic patterns as an indicator of discussion health. Working in a domain for which ground truth was unavailable at the time (early COVID-19 pandemic discussions) we explore the characterization of discussions based on the the volume and time of contributions. First we explore the types of discussions in an unsupervised manner, and then characterize these types using the concept of ephemerality, which we formalize. In the end, we discuss the potential use of our ephemerality definition for labeling online discourses based on how desirable, healthy and constructive they are.