Papers with aggressiveness identification
Misogyny and Aggressiveness Tend to Come Together and Together We Address Them (2022.lrec-1)
Copied to clipboard
| Challenge: | Using a binary task to identify whether a tweet is misogynous and aggressive, we compare two approaches to address these problems: one multi-class model that discriminates between all the classes at once; and a cascaded approach where the binary classification is carried out separately. |
| Approach: | They propose a multi-class model that discriminates between all the classes at once and a cascaded approach where the binary classification is carried out separately and then joined together. |
| Outcome: | The proposed models outperform the top submissions to Evalita on the 2020 shared task on automatic misogyny and aggressiveness identification in Italian tweets. |