There are more multilingual speakers in the world than monolingual ones. Immigration is one of the key factors to bring speakers of different languages in contact with each other. In order to develop relevant policies and recommendations tailored according to the needs of immigrant communities, it is essential to understand the interactions between the users within and across sub-communities. Using a novel method (tensor analysis), we reveal the social network structure of an online multilingual discussion forum which hosts an immigrant community in the Netherlands. In addition to the network structure, we automatically discover and categorize monolingual and bilingual sub-communities and track their formation, evolution and dissolution over a long period of time.