MALSOME: Detecting and analyzing malicious behaviour in social networks
Description of the granted funding
The rise of social media has changed the way we are using internet, communicate with each other, and obtain information. While the impact of social media has been positive, social media has also created new channels for malicious behaviour: a significant portion of social media users have been subjected to harassing behaviour, and also experienced severe form of cyber bullying. The negative effects of misusing social media have driven the platforms to take actions against malicious content. Due to sheer volume of data, content moderators has to use machine learning tools. The goal of the project is to develop novel methodology for analyzing and detecting more accurately malicious behaviour in social media: we develop tools to discover echo chambers in social media. We also develop means to use temporal network to improving hate speech detection, even when the user tries to actively evade the classifier. Finally we design methods in order to detect fake behaviour in social network.
Show moreStarting year
2021
End year
2025
Granted funding
Other information
Funding decision number
343045
Fields of science
Computer and information sciences
Research fields
Laskennallinen data-analyysi
Identified topics
media, journalism