# TaCD: Team-Aware Community Detection Based on Multi-View Modularity

## TL;DR

This paper introduces TaCD, a new community detection algorithm that considers team relationships in social networks to improve community discovery.

## Contribution

The novel TaCD algorithm and the new SCHOLAT dataset with team information are introduced.

## Key findings

- TaCD outperforms existing community detection algorithms on social networks with team information.
- The SCHOLAT dataset is publicly available for testing community detection methods.
- Using multi-view modularity with team and user views improves community detection accuracy.

## Abstract

Community detection in social networks is one of the most important topics of network science. Researchers have developed numerous methods from various perspectives. However, the existing methods often overlook the team information encoded as a special type of user relation in the social network, which plays an important role in community formation and evolution. In this paper, we propose a novel community detection algorithm called Team-aware Community Detection (TaCD). Our model constructs a multi-view network by encoding the user interaction information as the user view and the team information as the team view. To measure the consistency across the two views, we use the Jaccard similarity to establish a cross-view coupling. Based on the constructed 2-view network, we use multi-view modularity to discover team-aware community structure, and solve the optimization problem using the well-known Generalized Louvain approach. Another contribution of this paper is the collection of a new SCHOLAT dataset, which consists of several social networks with team information and is publicly available for testing purposes. Our experimental results on several SCHOLAT networks with team information demonstrate that TaCD outperforms the existing community detection algorithms.