To whomever that came across this repo,
Hello, this is my personal project on clickbait detection using the dataset from the Clickbait-Challenge at https://www.clickbait-challenge.org/.
The dataset is fairly large and not uploaded here. Please obtain the data from https://www.clickbait-challenge.org/. Rename the truth/instance files from the 2495 dataset as truth1.json and instance1.json. Rename the truth/instance files from the 19538 dataset as truth2.json and instance2.json. Place all dataset files under data/raw. Run the preprocessing file and a merged and processed data will spawn into data/prepped.
The models for detecting clickbaitaits are in their respectively named files.
Thanks!
Sean Xie