Repository for the practices of the subject Machine Learning
| Name | Github user |
|---|---|
| Sergio Herreros Fernández | @SergioHerreros |
| Francisco Javier Luna Ortiz | @Lunao01 |
| Carlos Romero Navarro | @KarManiatic |
| Tatsiana Shelepen | @Naschkatzee |
Disinformation is a hazardous and far-reaching phenomenon, capable of causing profound changes in any community’s political, economic, and cultural framework and thus undermining the foundations of societies around the world, either intentionally or through unconscious mistakes. There is no consensus for a standard definition of this phenomenon involving untruthful information. In the Anglo-Saxon world, the most acknowledged classification is the one proposed in Wardle & Derakhshan in 2017, which divides the alteration or manipulation of information into three typologies:
- Misinformation: information that is false or misleading but not intended to cause harm.
- Disinformation: malicious false information, i.e., with a motivation to cause harm.
- Malinformation: information that is truthful but disseminated with the
aim of causing damage.
There are two target variables:
- real - Whether the tweet is real
- fake - Whether the tweet is fale
It is not going to be relevant when applying BERTopic (labels not consdiered in clustering (unsupervised learning).
- The dataset contains as feature the tweets scraped.