Date of Award
Master of Science
Knowledge regarding social information is commonly thought to be derived from sources such as interviews and formal relationships. Consequently, social networks can be generated from this information. Recent work has demonstrated that language statistics can explain findings often thought to primarily be explained by external factors. Three studies explored whether language implicitly comprises information that allows for extracting social networks, by testing the hypothesis that individuals who are socially related together are linguistically discussed together, as well as the hypothesis that individuals who are socially related more are linguistically discussed more. Three computational studies were conducted testing the extent to which social networks could be extracted from fiction novels. Semantic relationships revealed that MDS solutions correlated with the actual social network of characters. A human study in which participants estimated social relationships of characters matched the results obtained computationally. The results demonstrated that linguistic information encodes social relationship information.
Dissertation or thesis originally submitted to the local University of Memphis Electronic Theses & dissertation (ETD) Repository.
Hutchinson, Sterling Chelsea, "Language Encodes Social Network Information" (2013). Electronic Theses and Dissertations. 682.