Predicting Television Extreme Viewers and Non-viewers A Neural Network Analysis

Authors

  • HAEJUNG PAIK,

    1. Haejung Paik is an assistant professor in the Department of Communication, and Caren Marzban is on the faculty of the Department of Physics, both at the University of Oklahoma.
    Search for more papers by this author
  • CAREN MARZBAN

    1. Haejung Paik is an assistant professor in the Department of Communication, and Caren Marzban is on the faculty of the Department of Physics, both at the University of Oklahoma.
    Search for more papers by this author

  • The authors would like to thank Andrew Heathcote and Joseph Woelfel for their invaluable input. E-mail addresses: hpaik@uoknor.edu and marzban@phyast.nhn.uoknor.edu.

Abstract

In an attempt to better understand the attributes of the “average” viewer, an analysis of the data characterizing television non-viewers and extreme viewers was performed. The data were taken from the 1988, 1989, and 1990 General Social Surveys, conducted by the National Opinion Research Center. The authors performed a neural network analysis and discuss the significance of the findings. For comparison, a discriminant analysis was also performed and is shown to be outperformed by the neural network. Furthermore, the set of demographic variables were identified as the strongest predictor of non-viewers, and the combination of family-related and lifestyle/social-activity-related variables were the strongest attribute of extreme viewers.

Ancillary