| Name: | Description: | Size: | Format: | |
|---|---|---|---|---|
| 1.95 MB | Adobe PDF |
Advisor(s)
Abstract(s)
Social media platforms enable the rapid dissemination and consumption of information. However, users instantly consume such content regardless of the reliability of the shared data. Consequently, the latter crowdsourcing model is exposed to manipulation. This work contributes with an explainable and online classification method to recognize fake news in real-time. The proposed method combines both unsupervised and supervised Machine Learning approaches with online created lexica. The profiling is built using creator-, content- and context-based features using Natural Language Processing techniques. The explainable classification mechanism displays in a dashboard the features selected for classification and the prediction confidence. The performance of the proposed solution has been validated with real data sets from Twitter and the results attain 80 % accuracy and macro F-measure. This proposal is the first to jointly provide data stream processing, profiling, classification and explainability. Ultimately, the proposed early detection, isolation and explanation of fake news contribute to increase the quality and trustworthiness of social media contents.
Description
Open Access funding provided thanks to the CRUE-CSIC agreement with Springer Nature. This
work was partially supported by: (i) Xunta de Galicia grants ED481B-2021-118 and ED481B-2022-093,
Spain; (ii) Portuguese national funds through FCT – Fundação para a Ciência e a Tecnologia (Portuguese
Foundation for Science and Technology) – as part of project UIDB/50014/2020; and (iii) University of
Vigo/CISUG for open access charge.
Keywords
Artificial intelligence Data stream architecture Machine learning Natural language processing Reliability and transparency Social networking
Citation
de Arriba-Pérez, F., García-Méndez, S., Leal, F. et al. Exposing and explaining fake news on-the-fly. Mach Learn 113, 4615–4637 (2024). https://doi.org/10.1007/s10994-024-06527-w
Publisher
Springer