Human communication is often executed in the form of a narrative, an accountof connected events composed of characters, actions, and settings. A coherentnarrative structure is therefore a requisite for a well-formulated narrative --be it fictional or nonfictional -- for informative and effective communication,opening up the possibility of a deeper understanding of a narrative by studyingits structural properties. In this paper we present a network-based frameworkfor modeling and analyzing the structure of a narrative, which is furtherexpanded by incorporating methods from computational linguistics to utilize thenarrative text. Modeling a narrative as a dynamically unfolding system, wecharacterize its progression via the growth patterns of the character network,and use sentiment analysis and topic modeling to represent the actual contentof the narrative in the form of interaction maps between characters withassociated sentiment values and keywords. This is a network framework advancedbeyond the simple occurrence-based one most often used until now, allowing oneto utilize the unique characteristics of a given narrative to a high degree.Given the ubiquity and importance of narratives, such advanced network-basedrepresentation and analysis framework may lead to a more systematic modelingand understanding of narratives for social interactions, expression of humansentiments, and communication.
展开▼
