All Academic, Inc. Research Logo

Info/CitationFAQResearchAll Academic Inc.
Document

Visual Representation and the Prediction of Emotion
Unformatted Document Text:  17 Exploratory factor analysis was conducted in order to verify that two dependent variables: negative affect and positive affect, could be created out of the thirteen individual emotion questions. Using principal component analysis with varimax rotation, two clear factors emerged, one representing positive affect and one representing negative affect. Both scales were reliable. The negative scale had a Chronbach’s alpha of .94 and the positive scale a Chronbach's alpha of .88 after removing "it was interesting" and "it was funny" because of their lower factor loadings. The two scales were negatively correlated, but with a small Pearson’s correlation of -.2. Therefore, it was determined that they could be used independently. Several variables required recoding in order to be used in the regression analysis. Income was divided into three levels (high, medium and low) and recoded as dummy variables. The orientation variables were divided into four levels (back, side, 45 degree angle, and head-on), and recoded as dummy variables. Sex, race, political party and political ideology were also made into dummy variables. We divided the race variable into white, African-American, Asian, and “other races.” The other races variable represents Latino and Indian people. The dummy variables for political party were Democrat, Republican, Independent, or other party, and the variables for political ideology were Liberal, Moderate, and Conservative. It was necessary to use dummy variables for a number of the content variables as well. For example, because they were not appropriately linear, each of the variables measuring the orientation of the camera to the subjects had to be

Authors: Sherr, Susan.
first   previous   Page 17 of 29   next   last



background image
17
Exploratory factor analysis was conducted in order to verify that two
dependent variables: negative affect and positive affect, could be created out of
the thirteen individual emotion questions. Using principal component analysis
with varimax rotation, two clear factors emerged, one representing positive affect
and one representing negative affect.
Both scales were reliable. The negative scale had a Chronbach’s alpha of
.94 and the positive scale a Chronbach's alpha of .88 after removing "it was
interesting" and "it was funny" because of their lower factor loadings. The two
scales were negatively correlated, but with a small Pearson’s correlation of -.2.
Therefore, it was determined that they could be used independently.
Several variables required recoding in order to be used in the regression
analysis. Income was divided into three levels (high, medium and low) and
recoded as dummy variables. The orientation variables were divided into four
levels (back, side, 45 degree angle, and head-on), and recoded as dummy
variables. Sex, race, political party and political ideology were also made into
dummy variables. We divided the race variable into white, African-American,
Asian, and “other races.” The other races variable represents Latino and Indian
people. The dummy variables for political party were Democrat, Republican,
Independent, or other party, and the variables for political ideology were Liberal,
Moderate, and Conservative.
It was necessary to use dummy variables for a number of the content
variables as well. For example, because they were not appropriately linear, each
of the variables measuring the orientation of the camera to the subjects had to be


Convention
All Academic Convention can solve the abstract management needs for any association's annual meeting.
Submission - Custom fields, multiple submission types, tracks, audio visual, multiple upload formats, automatic conversion to pdf.
Review - Peer Review, Bulk reviewer assignment, bulk emails, ranking, z-score statistics, and multiple worksheets!
Reports - Many standard and custom reports generated while you wait. Print programs with participant indexes, event grids, and more!
Scheduling - Flexible and convenient grid scheduling within rooms and buildings. Conflict checking and advanced filtering.
Communication - Bulk email tools to help your administrators send reminders and responses. Use form letters, a message center, and much more!
Management - Search tools, duplicate people management, editing tools, submission transfers, many tools to manage a variety of conference management headaches!
Click here for more information.

first   previous   Page 17 of 29   next   last

©2012 All Academic, Inc.