Towards an NLP-Based Topic Characterization of Social Relations

The unstructured text content of online communication artifacts is a salient source of information about social relationships. We investigate the utility of keywords extracted from the message body as a representation of the relationship´s characteristics, which are reflected by the conversation topics to a certain extent. Keyword extraction is performed using standard natural language processing methods. Communication data and human assessments of the extracted keywords are obtained from Facebook users via a custom application. The overall positive quality assessment provides evidence that the keywords indeed convey relevant information about the relationship. This kind of representation may be of value for various computational tasks from the domain of social computing.