Create a ML model to predict which tweets are alerting about real disaters. An example of a disaster tweet will contain hashtag like #earthquake, #COVID, #pandemic, etc compared to a normal tweet such as "What is up man"
In this project, I have performed data preprocessing, data cleaning such as removing extra space, hashtag, https link,...
Also, I have implemented three different models : simple linear classifier with count vectorizers of words, Logistic Regression with K-fold cross validation and Grid Search CV for best parameters, BERT model.
For the first two models, I got accuracy of 78% and 79.9% respectively. The BERT model is the best one which with some data cleaning has achieved accuary of 82.8%.
mytran2111/NLP_tweet_disaters
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
Create a ML model to predict which tweets are alerting about real disaters
Resources
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published