Extraction of multilayered social networks from activity data

Area of Science:

• Social Network Analysis
• Information Science
• Computer Science

Background:

• Web-based systems generate vast user interaction data, offering opportunities to map social networks.
• Extracting these networks is complex due to the volume and variety of connections.
• User interactions are mediated by objects (e.g., emails, forum posts), forming the basis for relationship identification.

Purpose of the Study:

• To propose a new method for creating multilayered social networks.
• To address the challenge of hierarchical object structures in social network extraction.
• To enable the identification and analysis of new layers and relationships within these networks.

Main Methods:

• Utilizing user activity data from web-based systems.
• Developing a method to handle hierarchical relationships between communication objects.
• Implementing a flattening and preprocessing procedure for network construction.

Main Results:

• A novel approach for building multilayered social networks was developed.
• The method effectively incorporates hierarchical object structures.
• New layers and relationships within the social network can be identified and analyzed.

Conclusions:

• The proposed method enhances social network analysis by accounting for object hierarchies.
• It provides a more comprehensive understanding of complex user interactions in web-based environments.
• This approach facilitates deeper insights into the structure and dynamics of online social networks.