I Feel Offended, Don’t Be Abusive! Implicit/Explicit Messages in Offensive and Abusive Language

By Tommaso Caselli, Valerio Basile, Jelena Mitrović, Inga Kartoziya, Michael Granitzer. 2020

180 citations recorded by the source corpus.

Subfields: Natural Language Processing, Safety, Robustness & Interpretability

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Natural Language Processing

In Safety, Robustness & Interpretability

Citations in the corpus

Anticipating Safety Issues in E2E Conversational AI: Framework and Tooling (2021, background): “In addition to overtly offensive language, several works highlight the importance of including more subtle forms of abuse, such as implicit abuse and micro-aggressions (e.g., Jurgens et al., 2019; Caselli et al., 2020; Han & Tsvetkov, 2020).”
Recipes for Safety in Open-domain Chatbots (2020, background): “Caselli et al. (2020) annotate the explicitness of the abuse, a distinction which might prove an important determinant of how easy it is to detect.”
Learning from the Worst: Dynamically Generated Datasets to Improve Online Hate Detection (2021, background): “as sarcasm, irony, adjectival nominalization and rhetorical questions are particularly likely to be misclassified (Caselli et al., 2020; Vidgen et al., 2019a).”
Latent Hatred: A Benchmark for Understanding Implicit Hate Speech (2021, background): “Because this speech lacks clear lexical signals, hate groups can evade keyword-based detection systems (Waseem et al., 2017; Wiegand et al., 2019), and even the most advanced architectures may suffer if they have not been trained on implicitly abusive messages (Caselli et al., 2020).”
Resources and benchmark corpora for hate speech detection: a systematic review (2020, background): “…which inspired the multi-layer annotation scheme proposed for the dataset of the OffensEval2019 shared task (Zampieri et al. 2019b) and other works, including the target-aware annotation in Basile et al. (2019) and the implicit-explicit distinction in the annotation of Caselli et al. (2020).”
SafetyKit: First Aid for Measuring Safety in Open-domain Conversational Systems (2022, background): “In addition to overtly offensive language, several works highlight the importance of including more subtle forms of abuse, such as implicit abuse and micro-aggressions (e.g., Jurgens et al., 2019; Caselli et al., 2020; Han and Tsvetkov, 2020).”