Jong-Kyu Seo
ABSTRACT
A work of literature shows different characteristics depending on its genre or author. Generally, features of literature can be revealed by linguistic analysis. However, the process of linguistic analysis is complicated and does not have a common standard. In this paper, we numerically calculate the relationship between agents that appear in literature and construct a relational network. The structure of the relational network is determined by the relationships between characters. A network that is composed of characters can be said to be a social network of a virtual world, so many existing social network analysis methods can be applied. We selected more than 20 novels including J.K. Rowling's "Harry Potter" and a traditional novel "Three Kingdoms" for an experiment. We introduce a visualization method for virtual social graphs and some useful analysis. The main contribution of this paper is that our model can be used to reveal the deep structure of a work of fiction using graph topology rather than traditional categories such as short or long novel.
- A. A.-J. Ahmed Hassan and D. Radev. Extracting Signed Social Networks From Text. In Proc. of the TextGraphs Workshop at ACL, pages 6--14, 2012. Google Scholar
Digital Library
- S.-Y. Bong and K.-B. Hwang. Keyphrase extraction in biomedical publications using mesh and intraphrase word co-occurrence information. In Proc. of the ACM DTMBIO, pages 63--66, 2011. Google ScholarDigital Library
- J. Burrows. Textual Analysis. Blackwell Publishing Ltd, 2004.Google Scholar
- D. K. Elson, D. Nicholas, and K. R. McKeown. Extracting Social Networks from Literary Fiction. In Proc. of the Association for Computational Linguistics, pages 141--147, 2012. Google ScholarDigital Library
- C. L. Freeman. The Development of Social Network Analysis: A Study in the Sociology of Science. Empirical Press, 2004.Google Scholar
- Y. Fujii, T. Yoshimura, and T. Ito. Filtering harmful sentences based on three-word co-occurrence. In Proc. of Collaboration, Electronic messaging, Anti-Abuse and Spam, pages 64--72, 2011. Google ScholarDigital Library
- R. Krestel and L. Chen. Using co-occurence of tags and resources to identify spammers. In Proc. of Machine Learning and Principles and Practice of Knowledge Discovery, pages 38--45, 2008.Google Scholar
- D. Liben-Nowell and J. Kleinberg. The link prediction problem for social networks. In Proc. of the twelfth international conference on Information and knowledge management, CIKM '03, pages 556--559, New York, NY, USA, 2003. ACM. Google ScholarDigital Library
- L. Lü and T. Zhou. Link prediction in complex networks: A survey. Physica A: Statistical Mechanics and its Applications, 390(6): 1150--1170, 2011.Google ScholarCross Ref
- K. Park, S. Kim, and H. Cho. Complex system analysis of social networks extracted from literary fictions. In Proc. of the ICMLC, volume 3, pages 107--111, 2013.Google ScholarCross Ref
- J. Rydberg-Cox. Social Networks and the Language of Greek Tragedy. J. of the Chicago Colloquium on Digital Humanities and Computer Science, 1(3): 1--11, 2011.Google Scholar
- J. Seo, G. Park, and H. Cho. Characteristic analysis of social network constructed from literary fiction. In Proc. of the twelfth international conferences on Cyberworlds, 2013. Google ScholarDigital Library
- T. Zhou, L. Lü, and Y.-C. Zhang. Predicting missing links via local information. The European Physical Journal B, 71(4): 623--630, 2009.Google ScholarCross Ref
Index Terms
- A structural analysis of literary fictions with social network framework
Recommendations
Characteristic Analysis of Social Network Constructed from Literary Fiction
CW '13: Proceedings of the 2013 International Conference on CyberworldsA Social network is a useful model to identify hidden structures and meaningful knowledge among social atoms, which have complicated interactions. Until recently, most studies have focused on the real data of social space, including emails, tweets, and ...
To Study the Impact of Social Network Analysis on Social Media Marketing Using Graph Theory
Marketing requires an understanding of relationships and current research has progressed much beyond the simple dyadic relationships to look at how social media networks influence the behavior of customers. Social media's power is fascinating as a ...
Social network analysis of a gamified e-learning course
Social networks and gamification are having an important and growing role in education. Social networks provide unknown communication and connection possibilities while games have the potential to engage students. This paper analyzes the structure of ...
Comments