Automatic Mapping of Social Networks of Actors from Text Corpora: Time Series Analysis

Abstract

To illustrate the WORDij approach to automatic social network identification from large volumes of text, this research mined the social networks among President Clintonpsilas cabinet members (n=24) and also President G.W. Bushpsilas cabinet members (n=45) over each of their two terms based on the members co-occurrence in news stories. The software used a time-slice interval of 30 days for Clinton stories because the average days between Gallup presidential job approval poll ratings was 30 days, resulting in 97 time slices. For Bush the average number of days between polls was 22 days, resulting in a 132-point time series. This synchronized the social networks with presidential job approval ratings. Clinton and Bush had nearly opposite relationships between network centrality and job approval. Automatic network analysis of social actors from textual corpora is feasible and enables testing hypotheses over time.