CARTON, S.; MEI, Q.; RESNICK, P. Feature-Based Explanations Don’t Help People Detect Misclassifications of Online Toxicity. Proceedings of the International AAAI Conference on Web and Social Media, [S. l.], v. 14, n. 1, p. 95-106, 2020. Disponível em: https://ojs.aaai.org/index.php/ICWSM/article/view/7282. Acesso em: 26 jun. 2022.