Predicting Different Types of Subtle Toxicity in Unhealthy Online Conversations

no code implementations • 7 Jun 2021 • Shlok Gilda, Mirela Silva, Luiz Giovanini, Daniela Oliveira

This paper investigates the use of machine learning models for the classification of unhealthy online conversations containing one or more forms of subtler abuse, such as hostility, sarcasm, and generalization.

Sentiment Analysis

People Still Care About Facts: Twitter Users Engage More with Factual Discourse than Misinformation--A Comparison Between COVID and General Narratives on Twitter

no code implementations • 3 Dec 2020 • Mirela Silva, Fabrício Ceschin, Prakash Shrestha, Christopher Brant, Shlok Gilda, Juliana Fernandes, Catia S. Silva, André Grégio, Daniela Oliveira, Luiz Giovanini

We found that (i) factual tweets, regardless of whether COVID-related, were more engaging than misinformation tweets; and (ii) features that most heavily correlated with engagement varied depending on the veracity and content of the tweet.

Misinformation