van de Guchte, Lennart (2020) Near Real-Time Detection of Misinformation on Online Social Networks. Master's Thesis / Essay, Artificial Intelligence.
|
Text
mAI_2020_van_de_GuchteL.pdf Download (1MB) | Preview |
|
![[img]](https://fse.studenttheses.ub.rug.nl/style/images/fileicons/text.png) |
Text
toestemming.pdf Restricted to Registered users only Download (96kB) |
Abstract
The massive usage of online social networks has amplified the negative effects that misinformation has on society. To counter misinformation, fact-checkers try to verify and debunk news stories. However, due to the speed at which misinformation is disseminated, manual fact-checking often comes too late. Moreover, misinformation influences people’s thoughts, beliefs, and opinions even after it has been corrected. Therefore, to prevent misinformation from being harmful, it is crucial to detect misinformation in real-time, when it begins to spread. Automatic approaches have been proposed that utilize machine learning techniques combined with a variety of features that discriminate misinformation from trusted information. These approaches rely on micro-blog posts that disseminate misinformation on online social networks, such as diffusion patterns, linguistic cues, or user characteristics. The more micro-blog posts become available, the easier it gets to detect misinformation. This makes misinformation detection a time-sensitive task, in which a trade-off is needed between efficiency and effectiveness. In this thesis, we focus on the early detection of misinformation on online social networks, and evaluate the effectiveness of different features.
| Item Type: | Thesis (Master's Thesis / Essay) |
|---|---|
| Supervisor name: | Spenader, J.K. |
| Degree programme: | Artificial Intelligence |
| Thesis type: | Master's Thesis / Essay |
| Language: | English |
| Date Deposited: | 07 Jul 2020 07:12 |
| Last Modified: | 07 Jul 2020 07:12 |
| URI: | https://fse.studenttheses.ub.rug.nl/id/eprint/22489 |
Actions (login required)
 |
View Item |