TU Darmstadt / ULB / TUbiblio

Prospect for Knowledge in Survey Data: An Artificial Neural Network Sensitivity Analysis

Weber, Patrick ; Weber, Nicolas ; Goesele, Michael ; Kabst, Rüdiger :
Prospect for Knowledge in Survey Data: An Artificial Neural Network Sensitivity Analysis.
[Online-Edition: http://journals.sagepub.com/doi/10.1177/0894439317725836]
In: Social Science Computer Review ISSN 0894-4393
[Artikel], (2017)

Offizielle URL: http://journals.sagepub.com/doi/10.1177/0894439317725836

Kurzbeschreibung (Abstract)

Policy making depends on good knowledge of the corresponding target audience. To maximize the designated outcome, it is essential to understand the underlying coherences. Machine learning techniques are capable of analyzing data containing behavioral aspects, evaluations, attitudes, and social values. We show how existing machine learning techniques can be used to identify behavioral aspects of human decision-making and to predict human behavior. These techniques allow to extract high resolution decision functions that enable to draw conclusions on human behavior. Our focus is on voter turnout, for which we use data acquired by the European Social Survey on the German national vote. We show how to train an artificial expert and how to extract the behavioral aspects to build optimized policies. Our method achieves an increase in adjusted R² of 102% compared to a classic logistic regression prediction. We further evaluate the performance of our method compared to other machine learning techniques such as support vector machines and random forests. The results show that it is possible to better understand unknown variable relationships.

Typ des Eintrags: Artikel
Erschienen: 2017
Autor(en): Weber, Patrick ; Weber, Nicolas ; Goesele, Michael ; Kabst, Rüdiger
Titel: Prospect for Knowledge in Survey Data: An Artificial Neural Network Sensitivity Analysis
Sprache: Englisch
Kurzbeschreibung (Abstract):

Policy making depends on good knowledge of the corresponding target audience. To maximize the designated outcome, it is essential to understand the underlying coherences. Machine learning techniques are capable of analyzing data containing behavioral aspects, evaluations, attitudes, and social values. We show how existing machine learning techniques can be used to identify behavioral aspects of human decision-making and to predict human behavior. These techniques allow to extract high resolution decision functions that enable to draw conclusions on human behavior. Our focus is on voter turnout, for which we use data acquired by the European Social Survey on the German national vote. We show how to train an artificial expert and how to extract the behavioral aspects to build optimized policies. Our method achieves an increase in adjusted R² of 102% compared to a classic logistic regression prediction. We further evaluate the performance of our method compared to other machine learning techniques such as support vector machines and random forests. The results show that it is possible to better understand unknown variable relationships.

Titel der Zeitschrift, Zeitung oder Schriftenreihe: Social Science Computer Review
Verlag: SAGE Publications Inc
Fachbereich(e)/-gebiet(e): 20 Fachbereich Informatik
20 Fachbereich Informatik > Graphics, Capture and Massively Parallel Computing
Exzellenzinitiative > Graduiertenschulen > Graduate School of Computational Engineering (CE)
Hinterlegungsdatum: 13 Sep 2017 11:38
Offizielle URL: http://journals.sagepub.com/doi/10.1177/0894439317725836
ID-Nummer: doi:10.1177/0894439317725836
Verwandte URLs:
Export:

Optionen (nur für Redakteure)

Eintrag anzeigen Eintrag anzeigen