Categories
Pages
-

DBIS

Overlapping Community Detection for Botnet analysis on Twitter

April 8th, 2022

The study of (social) structures in real-world networks is known as (social) network analysis. Nodes and linkages make up networks. Communities are subnetworks in which nodes have more connections to nodes within the subnetwork than to nodes outside the subnetwork. The difficulty of detecting nodes in networks that belong to more than one sub-network is known as overlapping community detection. The goal of this work is to extend our existing bot detection framework to include community detection functionality.

Thesis Type Bachelor
Student Tom Ahshoff
Status Running
Supervisor(s) Ralf Klamma
Advisor(s) Michal Slupczynski
In our currently running project MILKI-PSY, we focus on multimodal immersive mentoring to facilitate Self Regulated Learning (SRL).
To support mentors with the tools they need to provide adaptive and personalized tutoring, a set of learning services was developed and is currently under development. These services utilize our flagship peer-to-peer community platform las2peer.

 

Unfortunately, malicious social bots are continually threatening the online ecosystem, spreading malware, phishing links, or spam, and manipulating user behavior on social networks. For example, in Syria, a social bot filled Twitter with hashtags linked to the Syrian civil war with unrelated topics, diverting people’ attention away from the war. Furthermore, social bots have lately been accused of misrepresenting online debates regarding key political elections in Western nations, notably the Brexit referendum in the United Kingdom. Twitter, for example, has been particularly badly affected, since bots account for an astonishingly huge proportion of its users. Detecting and eliminating dangerous social bots from online social networks is so critical.
In previous work, we implemented a bot detection framework based on Artificial Immune System algorithms to provide researchers with a possibility to better understand the behavior of these bots and their goals.

 

The goal of this thesis is to extend the existing bot detection framework with an overlapping community detection mechanism for botnet analysis.

If you are interested in this thesis, a related topic or have additional questions, please do not hesitate to send a message to slupczynski@dbis.rwth-aachen.de
Please apply with a meaningful CV and a recent transcript of your academic performance.

Potentially relevant literature:

Prerequisites:
  • Web Technologies
  • Java