# FreSaDa: A French Satire Data Set for Cross-Domain Satire Detection

arXiv: https://arxiv.org/abs/2104.04828 · HTML: https://mlsanity.com/paper/2104.04828/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 41 references that are in the map.
- First posted on arXiv 10 Apr 2021.

## Builds on (most cited first, 16 of 16)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks](https://mlsanity.com/paper/1908.02265/) (2019)
- [CamemBERT: a Tasty French Language Model](https://mlsanity.com/paper/1911.03894/) (2019)
- [Automatic Detection of Fake News](https://mlsanity.com/paper/1708.07104/) (2017)
- [Baseline Needs More Love: On Simple Word-Embedding-Based Models and Associated Pooling Mechanisms](https://mlsanity.com/paper/1805.09843/) (2018)
- [Combating Fake News: A Survey on Identification and Mitigation Techniques](https://mlsanity.com/paper/1901.06437/) (2019)
- [Automated essay scoring with string kernels and word embeddings](https://mlsanity.com/paper/1804.07954/) (2018)
- [Satirical News Detection and Analysis using Attention Mechanism and Linguistic Features](https://mlsanity.com/paper/1709.01189/) (2017)
- [Adversarial Training for Satire Detection: Controlling for Confounding Variables](https://mlsanity.com/paper/1902.11145/) (2019)
- [Vector of Locally-Aggregated Word Embeddings (VLAWE): A Novel Document-level Representation](https://mlsanity.com/paper/1902.08850/) (2019)
- [A Multi-Modal Method for Satire Detection using Textual and Visual Cues](https://mlsanity.com/paper/2010.06671/) (2020)
- [Fake or Real? A Study of Arabic Satirical Fake News](https://mlsanity.com/paper/2011.00452/) (2020)
- [From Image to Text Classification: A Novel Approach based on Clustering Word Embeddings](https://mlsanity.com/paper/1707.08098/) (2017)
- [UnibucKernel Reloaded: First Place in Arabic Dialect Identification for the Second Year in a Row](https://mlsanity.com/paper/1805.04876/) (2018)

## Built on by (most cited first, 8 of 8)

- [SaRoCo: Detecting Satire in a Novel Romanian Corpus of News Articles](https://mlsanity.com/paper/2105.06456/) (2021)
- [YesBut: A High-Quality Annotated Multimodal Dataset for evaluating Satire Comprehension capability of Vision-Language Models](https://mlsanity.com/paper/2409.13592/) (2024)
- [A Multi-Label Dataset of French Fake News: Human and Machine Insights](https://mlsanity.com/paper/2403.16099/) (2024)
- [Measuring vagueness and subjectivity in texts: from symbolic to neural VAGO](https://mlsanity.com/paper/2309.06132/) (2023)
- [POLygraph: Polish Fake News Dataset](https://mlsanity.com/paper/2407.01393/) (2024)
- [SaRoHead: Detecting Satire in a Multi-Domain Romanian News Headline Dataset](https://mlsanity.com/paper/2504.07612/) (2025)
- [MuSaRoNews: A Multidomain, Multimodal Satire Dataset from Romanian News Articles](https://mlsanity.com/paper/2504.07826/) (2025)
- [SeLeRoSa: Sentence-Level Romanian Satire Detection Dataset](https://mlsanity.com/paper/2509.00893/) (2025)

## Abstract (arXiv)

In this paper, we introduce FreSaDa, a French Satire Data Set, which is composed of 11,570 articles from the news domain. In order to avoid reporting unreasonably high accuracy rates due to the learning of characteristics specific to publication sources, we divided our samples into training, validation and test, such that the training publication sources are distinct from the validation and test publication sources. This gives rise to a cross-domain (cross-source) satire detection task. We employ two classification methods as baselines for our new data set, one based on low-level features (character n-grams) and one based on high-level features (average of CamemBERT word embeddings). As an additional contribution, we present an unsupervised domain adaptation method based on regarding the pairwise similarities (given by the dot product) between the training samples and the validation samples as features. By including these domain-specific features, we attain significant improvements for both character n-grams and CamemBERT embeddings.