Exploiting Structure and Conventions of Movie Scripts for Information Retrieval and Text Mining

Arnav Jhala

    Research output: Journal Article or Conference Article in JournalConference articleResearchpeer-review


    Movie scripts are documents that describe the story, stage direction for actors and camera, and dialogue. Script writers, directors, and cinematographers have standardized the format and language that is used in script writing. Scripts contain a wealth of information about narrative patterns, character direction, blocking, and camera control that can be extracted for various applications in interactive storytelling. In this short paper, we propose the creation of an
    automatically annotated corpus of movie scripts and describe our initial efforts in automating script annotation. We first describe the parts of a movie script that can be automatically annotated and then describe the use of an existing language processing toolkit to automatically annotate specific parts of a movie script.
    Original languageEnglish
    Book seriesLecture Notes in Computer Science
    Pages (from-to)210-213
    Number of pages4
    Publication statusPublished - 2008
    EventFirst Joint International Conference on Interactive Digital Storytelling, ICIDS 2008 - Erfurt, Germany
    Duration: 26 Nov 200829 Nov 2008
    Conference number: 1


    ConferenceFirst Joint International Conference on Interactive Digital Storytelling, ICIDS 2008

    Cite this