mlsanityData to 14 Oct 2026

Never guess what I heard... Rumor Detection in Finnish News: a Dataset and a Baseline

arXiv 2106.03389 ↗First posted 7 Jun 2021cs.CLcited by 4

Not on the map. Why?

Abstract (arXiv)

This study presents a new dataset on rumor detection in Finnish language news headlines. We have evaluated two different LSTM based models and two different BERT models, and have found very significant differences in the results. A fine-tuned FinBERT reaches the best overall accuracy of 94.3% and rumor label accuracy of 96.0% of the time. However, a model fine-tuned on Multilingual BERT reaches the best factual label accuracy of 97.2%. Our results suggest that the performance difference is due to a difference in the original training data. Furthermore, we find that a regular LSTM model works better than one trained with a pretrained word2vec model. These findings suggest that more work needs to be done for pretrained models in Finnish language as they have been trained on small and biased corpora.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 12 of its 38 references that are in the map. First posted on arXiv 7 Jun 2021.

Builds on

12 of 38 references.

References · 12

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2019HuggingFace's Transformers: State-of-the-art Natural Language Processingcited by 2,218
  3. 2015Effective Approaches to Attention-based Neural Machine Translationcited by 1,026
  4. 2017OpenNMT: Open-source Toolkit for Neural Machine Translationcited by 251
  5. 2018When and Why are Pre-trained Word Embeddings Useful for Neural Machine Translation?cited by 126
  6. 2019Multilingual is not enough: BERT for Finnishcited by 119
  7. 2021Endangered Languages are not Low-Resourced!cited by 14
  8. 2019A Finnish News Corpus for Named Entity Recognitioncited by 11
  9. 2020A Multi-Modal Method for Satire Detection using Textual and Visual Cuescited by 10
  10. 2019Identifying Nuances in Fake News vs. Satire: Using Semantic and Linguistic Cuescited by 8
  11. 2021When Word Embeddings Become Endangeredcited by 6
  12. 2020Rumor Detection on Twitter Using Multiloss Hierarchical BiLSTM with an Attenuation Factorcited by 3

Built on by

Cited by year

Citing papers per year: 2021: 1; 2022: 3.

4 papers.

  1. 2021Detecting Depression in Thai Blog Posts: a Dataset and a Baselinecited by 6
  2. 2022Multilingual Persuasion Detection: Video Games as an Invaluable Data Source for NLPcited by 4
  3. 2022Automatic Generation of Factual News Headlines in Finnishcited by 1
  4. 2022Harnessing Multilingual Resources to Question Answering in Arabiccited by 0