Community Detection of Screenplay Characters - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2016

Community Detection of Screenplay Characters

Christos Makris
  • Function : Author
  • PersonId : 992346
Pantelis Vikatos
  • Function : Author
  • PersonId : 992417


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.
Fichier principal
Vignette du fichier
430537_1_En_40_Chapter.pdf (451.3 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-01557593 , version 1 (06-07-2017)





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⟩
78 View
298 Download



Gmail Facebook X LinkedIn More