Familiarity-Based Collaborative Team Recognition in Academic Social Networks

Collaborative teamwork is key to major scientific discoveries. However, the prevalence of collaboration among researchers makes team recognition increasingly challenging. Previous studies have demonstrated that people are more likely collaborate with individuals they familiar with. In this work, we employ definition familiarity and then propose faMiliarity-based cOllaborative Team recOgnition (MOTO) algorithm recognize collaborative teams. MOTO calculates shortest distance matrix within global network local density each node. Central members initially recognized based on density. Then, recognizes remaining by using metric matrix. Extensive experiments been conducted upon a large-scale dataset. The experimental results show compared baseline methods, can largest number teams possess cohesive structures lower communication costs other methods. utilizes in identify academic line real-world patterns. Based MOTO, research structure performance further analyzed for given time periods. consist from different institutions increases gradually. Such found perform better comparison those whose same institution.