Berlin 2012 – scientific programme
Parts | Days | Selection | Search | Updates | Downloads | Help
SOE: Fachverband Physik sozio-ökonomischer Systeme
SOE 13: Communication and Language
SOE 13.7: Talk
Wednesday, March 28, 2012, 15:30–15:45, H 0110
Using social network analysis to explore narrative structure — •Andrzej Jarynowski1,2, Stephanie Boland1,3, Elva Robinson1, Richard Walsh1, Dan Franks1, and John Forrestor1 — 1YCCSA, University of York, UK — 2Smoluchowski Insitute of Physics, Jagiellonian University, Cracow, Poland — 3English, University of Exeter, UK
Network theory is useful when it comes to studying nature from a systems perspective, and social network analysis has been already applied to human societies. We want to make a cross-disciplinary leap, and use the tools of network theory to understand and explore narrative structure in literary fiction, a still under-utilized approach. However, the systems in fiction are sensitive on reader's subjectivity and attention must to be paid to different methods of extracting networks. The project aims to investigate the different ways social interactions are "read" in texts by comparing networks produced by automated algorithms-natural language processing (NLP) with those created by surveying more subjective human responses. Conversation networks from fiction have been already extracted by scientists, but the more general framework surrounding these interactions was missing. We propose several NLP methods for detecting interactions, and test them against a range of human perceptions. In doing so, we uncovered some limitations of using network analysis to test literary theory (e.g. interaction, which correspond to the plot, do not form climax).