The dataset provided can be found on Kaggle at the link. The analysis therefore concerns Cyberbullying tweets divided by bullying category (age, gender, ethnicity, religion..), and the aim is to identify cyberbullying events. To do so some classification tasks have been done, exploiting binary classification, multi-class classification and, finally, classification with BERT algorithm.
martinasus / textanalytics_unipi_2021-22 Goto Github PK
View Code? Open in Web Editor NEWProject for text analytics exam - UniPi