Abstract
In a world where complex networks are an increasingly important part of science, it is interesting to question how the new reading of social realities they provide applies to our cultural background and in particular, popular culture. Are authors of successful novels able to reproduce social networks faithful to the ones found in reality? Is there any common trend connecting an author’s oeuvre, or a genre of fiction? Such an analysis could provide new insight on how we, as a culture, perceive human interactions and consume media. The purpose of the work presented in this paper is to define the signature of a novel’s story based on the topological analysis of its social network of characters. For this purpose, an automated tool was built that analyses the dialogs in novels, identifies characters and computes their relationships in a time-dependent manner in order to assess the network’s evolution over the course of the story.
Highlights
The recipe of the Harry Potter saga’s [1,2,3,4,5,6,7] success might reside in part in the very unique way its author has installed a familiar kind of social network in a fantasy world
In order for the reader to be seduced by the story of any novel, the social network narrated in the book must not be too distinct from the ones typically found in real life
Enough, a novel respectful of the social reality of its time constitutes an interesting temporal compression that allows clever text mining and natural language algorithms to more catch the main features of the social network depicted in the novel: its topology, its clustering degree [48] and the way it is being constructed in time
Summary
The recipe of the Harry Potter saga’s [1,2,3,4,5,6,7] success might reside in part in the very unique way its author has installed a familiar kind of social network in a fantasy world. An author tells a story by switching between descriptions of the events occurring during the story (i.e. the narration) and descriptions of the conversations happening between the different characters involved Both are important as they provide information about the characters intervening in the action, but the identification and analysis of the conversations provide a more precise description of the way social links are built through the storytelling. To reach this goal an algorithm composed of four consecutive steps was developed: Pre-processing, Extraction of dialogs and conversations, Characters identification and Network building.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
