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
Electronic File Format
MS WORD
Accession Number
CDTG005572
Shelf Location
Archives, The Learning Commons, 12F Henry Sy Sr. Hall
Physical Description
leaves ; 4 3/4 in.
Upload Full Text
wf_no
Recommended Citation
Daniel Stanley, T. (2014). Rating movies using an arousal model. Retrieved from https://animorepository.dlsu.edu.ph/etd_masteral/4621