Cyber-bullying Classification

This is a Kaggle project based on Machine Learning. The objective of the project is to analyse a general tweet statement and determine if it is a cyber-bullying tweet or not. If the tweet relates to a context of bullying, then assign the appropriate class of cyber-bullying.

This is a multi-class classification task which is related to the domain of Natural Language Processing(NLP).

Data:

• Source: Kaggle
• A CSV file that provides more than 47000 tweets labelled according to the class of cyber-bullying.
• There are two columns in the dataset:
  • tweet_text - contains the tweet
  • cyberbullying_type - contains the corresponding cyberbullying class for each tweet (6 classes):
    • age
    • ethnicity
    • gender
    • religion
    • other_cyberbullying
    • not_cyberbullying
• Citation:
  • J. Wang, K. Fu, C.T. Lu, “SOSNet: A Graph Convolutional Network Approach to Fine-Grained Cyberbullying Detection,” Proceedings of the 2020 IEEE International Conference on Big Data (IEEE BigData 2020), December 10-13, 2020.

Note:

These tweets either describe a bullying event or are the offense themselves, therefore explore it to the point where you feel comfortable.

Members:

1. Ashutosh Ojha
2. Sathvick Reddy Narahari
3. Shayla Luong