Rating movies using an arousal model

Date of Publication

2014

Document Type

Master's Thesis

Degree Name

Master of Science in Computer Science

College

College of Computer Studies

Department/Unit

Computer Science

Thesis Adviser

Solomon See

Defense Panel Chair

Rafael Cabredo

Defense Panel Member

Briane Samson

Abstract/Summary

Based on theories on how to structure and pace the intensity of movies, this research explores the idea of looking for patterns in the intensity of movies and to see whether or not there are indeed patterns that can be useful in rating movies. The measurement is done through arousal curves. The arousal curve, which is basically excitement over time, is used to estimate the intensity of a movie over time and it is derived from film grammars which directors use to highlight certain scenes or elicit certain emotional responses. These data are used to build a Hidden Markov Model classifier to predict a rating of a movie. Basing only on structure, the model can correctly predict the rating of a movie 70% of the time however, there are elements that affect rating that cannot be captured by structure alone. This research shows that there is a potential for structure to be used as a means to differentiate decent movies from bad movies.

Abstract Format

html

Language

English

Format

Electronic

Accession Number

CDTG005572

Shelf Location

Archives, The Learning Commons, 12F Henry Sy Sr. Hall

Physical Description

leaves ; 4 3/4 in.

This document is currently not available here.

Share

COinS