Project: Climate Change Misinformation Detection
The challenge of the project is to build a system that detects whether a document contains climate change misinformation. The task is framed as a binary classification problem: a document either contains climate change misinformation or it doesn’t. The caveat of the task is that we only have training documents with positive labels. That is, the training documents provided are articles with climate change misinformation.
The competition has two phases:
Phase 1 - Ongoing Evaluation
At this phase your result will be evaluated based on a subset of the test set. Note that you still need to submit your predictions on the entire test set (all the keys in test-unlabelled.json). In this phase, the performance of your system will be on the Public Leaderboard, the ranking is only for your reference.
Phase 2 - Final Evaluation
The final results will be evaluated on another subset of the test set. You do NOT need to resubmit your results at Phase 2, the submission you choose at Phase 1 will be automatically migrated when Phase 1 ends. The final ranking of your system will be determined based on the Private Leaderboard at this phase.
Please refer to the project specification for details.
In the leaderboard will present 3 evaluation metrics, Precision, Recall and F1 Score. The final ranking will be based on F1 Score.
Start: April 3, 2020, midnight
Description: Public Leaderboard
Start: May 13, 2020, 3 a.m.
Description: Private Leaderboard
May 13, 2020, 3 a.m.
You must be logged in to participate in competitions.Sign In