Finnish Rumor Detection Dataset and Models

2021-04-16, 2021-04-16
dataset
dataset
Open
Data and models for Finnish rumor detection. The entire dataset is in rumor_dataset.json. Look into dataset_splits.zip for data splits used in the paper (*_test.txt and *_train.txt). The .pt files are the OpenNMT models described in the paper. bert-models.zip has the BERT based models trained with the bert.py (FinBERT) and bert_multi.py (Multilingual BERT) scripts. Cite: Hämäläinen, M., Alnajjar, K., Partanen, N., & Rueter, J. (2021) Never guess what I heard... Rumor Detection in Finnish News: a Dataset and a Baseline. In the Proceedings of the Third Workshop on NLP for Internet Freedom (NLP4IF): Censorship, Disinformation, and Propaganda