Community Detection of Screenplay Characters

Abstract : In this paper, we present a model for automatic community detection of the characters by parsing movie screenplays. In our procedure it is proposed a classification model to predict the casting by categorize each line of the script in a character or not and the co-occurrence of the characters in the same scene constitutes the link between two characters in the social network. We use an existing modularity based community detection algorithm for cutting the created graph in communities. The innovation of our methodology is contained in the extraction of the casting of the screenplay from Wikipedia pages in order to train and build an efficient classifier to identify the characters in a screenplay. The proposed methodology for extracting automatically the social network and communities of screenplay characters can be probably used for enhancing movie recommendations.
Document type :
Conference papers
Complete list of metadatas

Cited literature [8 references]  Display  Hide  Download

https://hal.inria.fr/hal-01557593
Contributor : Hal Ifip <>
Submitted on : Thursday, July 6, 2017 - 1:55:00 PM
Last modification on : Tuesday, December 26, 2017 - 4:40:06 PM
Long-term archiving on : Wednesday, January 24, 2018 - 1:37:50 AM

File

430537_1_En_40_Chapter.pdf
Files produced by the author(s)

Licence


Distributed under a Creative Commons Attribution 4.0 International License

Identifiers

Citation

Christos Makris, Pantelis Vikatos. Community Detection of Screenplay Characters. 12th IFIP International Conference on Artificial Intelligence Applications and Innovations (AIAI), Sep 2016, Thessaloniki, Greece. pp.463-470, ⟨10.1007/978-3-319-44944-9_40⟩. ⟨hal-01557593⟩

Share

Metrics

Record views

93

Files downloads

95