Panteion University of Social and Political Sciences
Εφαρμογές ασαφούς λογικής στη μέτρηση των στάσεων
Abstract
dc:descriptionThe object of this doctoral thesis is Fuzzy Logic and Artificial Neural Networks, domains of Artificial Intelligence, and their extension in Likert scales. Likert scales (or subscales) are usually constructed by summing up the items when the assessment of their psychometric properties has resulted in showing that the scale is both reliable and valid. This doctoral thesis presents a methodology for developing a fuzzy set theory solution to combine Likert items into a single overall scale (or subscales). The proposed methodology puts together information produced by construct validity assessment, statistical analysis and experts’ knowledge produced during theory development, in a fuzzy inference system to develop a more accurate attitude measurement. Moreover, this thesis presents a methodology for developing individuals’ profiles based on fuzzy Likert scale scores using percentile norms. The aim is the determination whether the normative or fuzzy data after their transformation using the percentile norms will better reflect the relative levels of the underlying attitude. Finally a neuro-fuzzy system is proposed that classifies the respondents into levels of the underlying attitude considering a number of crucial factors thereby reducing the uncertainty. The evaluation of the methodologies presented are tested on a Likert scale that was used in a large-scale sample survey for measuring xenophobia in Northern Greece conducted under the auspices of the National Centre for Social Research with scientifically responsible Prof. Michalopoulou. The methodologies can be applied with minor modifications to other data sets.
Degree
thesis:*- Grantor dc:publisher
- Panteion University of Social and Political Sciences
- Year dc:date
- 2018
Author and committee
dc:creator, dc:contributor.*- Authors dc:creator
-
- Kazani, Angeliki
- Καζάνη, Αγγελική
Subjects
dc:subject × 26- Κλίμακες Likert
- Τεχνητή νοημοσύνη
- Ασαφής λογική
- Ασαφή Συστήματα Συλλογιστικής
- Ασαφείς κανόνες
- Συναρτήσεις συμμετοχής
- Αξιοπιστία
- Παραγοντική ανάλυση
- Ανάλυση των «Προφίλ»
- Νευρωνικά δίκτυα
- Νεύρο-ασαφή συστήματα
- Likert scales
- Artificial intelligence
- Fuzzy set theory
- Fuzzy inference systems
- Fuzzy rules
- Membership functions
- Reliability
- Exploratory factor analysis
- Profile analysis
- Neural networks
- Neuro-fuzzy systems
- Κοινωνικές Επιστήμες
- Πολιτικές Επιστήμες
- Social Sciences
- Political Science
Rights
- Language dc:language
- gre
Identifiers
dc:identifier.*- Identifier
- 10.12681/eadd/44256