A Novel Method of Network Text Analysis
This paper describes a novel method of network text analysis, one that involves a new approach to 1) the selection of words from a text, 2) the aggregation of those words into higher-order concepts, 3) the kind of the relationship that establishes statements from pairs of concepts and 4) the extraction of meaning from the text network formed by these statements. After describing the method, I apply it to a sample of the seven most recent winners of the Academy Award for Best Original Screenplay―Little Miss Sunshine, Juno, Milk, The Hurt Locker, The King’s Speech, Midnight in Paris, and Django Unchained. Consistent with prior research, I demonstrate that structure encodes meaning. Specifically, it is shown that statements associated with a text network’s least constrained nodes are consistent with themes in the films’ synopses found on Wikipedia, the International Movie Database, and Rotten Tomatoes.