metadata

library_name: transformers
tags:
  - text-classification
  - hate-speech

Model Card for Model ID

This model is fine-tuned on top of distill bert base uncased for hatespeech. Its purpose is to predict whether a given text contains hate speech or not. Class Label are 1 for hatspeech and 0 for not.

Model Details

Model Description

Important info This model works with binary classification and doesn't consider multilabel clssification. It detects it's either a hatespeech or not.

Developed by: Ayush Dhoundiyal
Language(s) (NLP): English
Finetuned from model: Bert Base Uncased

Model Sources [optional]

Paper: https://github.com/ayushdh96/Natural-Language-Processing/blob/main/Ayush_Dhoundiyal_Project_Report.pdf [More Information Needed]

Training Details

Training Data

Pre-processing invloved basic steps like lemmtizing, stemming of words. Removing stop words and lowercasing the text to be classified. It's requested to perform these steps for good results.

Evaluation

The model provides the accuracy of 0.96, precision of 0.97. recall of 0.97 and f1 score of 0.97.