In this note we introduce a new methodology that combines tools from social language processing and network analysis to identify socially situated relationships between individuals, even when these relationships are latent or unrecognized. We call this approach social language network analysis (SLNA). We describe the philosophical antecedents of SLNA, the mechanics of preprocessing, processing, and post-processing stages, and the results of applying this approach to a 15month corporate discussion archive. These example results include an explicit mapping of both the perceived expertise hierarchy and the social support / friendship network within this group. Author Keywords social language processing, social network analysis, network structure, communication, content analysis, group. ACM Classification Keywords J.4 Social and Behavioral Sciences: Psychology. General Terms Algorithms, Human Factors, Management, Measurement
Andrew J. Scholand, Yla R. Tausczik, James W. Penn