Rhythmpathy: A study on rhythms influence on emotion

Date of Publication

2010

Document Type

Bachelor's Thesis

Degree Name

Bachelor of Science in Computer Science

College

College of Computer Studies

Department/Unit

Computer Science

Thesis Adviser

Jocelynn Cu

Defense Panel Member

Merlin Suarez
Rhia Trogo

Abstract/Summary

This study seeks to determine the influence of rhythm on a listeners emotions in order to serve as grounds for the future development of algorithms for multiple emotion label classification. A collection of 100 instrumental music pieces in wave audio format (.wav) was acquired from audio Cds and downloaded from the internet. A 30 second segment was taken from each piece, with the restriction that the tempo was unvarying throughout the segment, making up the music corpus used in this research. Sets of song segments were presented ordered incrementally based on tempo to human subjects, who provided emotion labels via self reporting for each sample based on their own personal emotions. With the use of MARSYAS, 18 rhythmic features were extracted from the beat histogram of each segment. Using WEKA's classifier subset evaluation, the optimal subset of rhythmic features for classifying in general as well as specific to each emotion was determined for each classifier.

Abstract Format

html

Language

English

Format

Print

Accession Number

TU18469

Shelf Location

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

Physical Description

1v. various foliations : illustrations ; 28 cm.

This document is currently not available here.

Share

COinS