Distilbert and LSTM are two deep learning models that can be used to analyze large datasets for identifying and analyzing tweets containing hateful or derogatory speech. These models can also be used to detect hate speech in any kind of text sequence, not just limited to tweets. In this project, we attempted to use the concatenation of two datasets to evaluate the performance of Distilbert and LSTM in detecting such anomalies. Our results showed a high validation accuracy rate of 93% for Distilbert and 94% for LSTM, demonstrating the effectiveness of both models in detecting hate speech in tweets and other types of text sequences.
-
Notifications
You must be signed in to change notification settings - Fork 0
Distilbert and LSTM can identify hate speech in various text sequences. In our project, we combined datasets to evaluate their performance on validation set and achieved 93% accuracy with Distilbert and 94% with LSTM.
Mohsen-29/Distilbert-and-LSTM-to-detect-hate-speech-on-Twitter
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Folders and files
Name | Name | Last commit message | Last commit date | |
---|---|---|---|---|
Repository files navigation
About
Distilbert and LSTM can identify hate speech in various text sequences. In our project, we combined datasets to evaluate their performance on validation set and achieved 93% accuracy with Distilbert and 94% with LSTM.
Topics
Resources
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published