Machine Learning Detects Pairwise Associations between SOI and BIS/BAS Subscales, making Correlation Analyses Obsolete
![Thumbnail](/bitstream/handle/20.500.14178/1763/Machine%20Learning%20Detects%20Pairwise%20Associations.pdf.jpg?sequence=5&isAllowed=y)
Autor
Prossinger, Hermann
Machová, Kamila
Datum vydání
2022Publikováno v
Human Interaction & Emerging Technologies (IHIET-AI 2022): Artificial Intelligence & Future ApplicationsNakladatel / Místo vydání
AHFE International (USA)ISBN / ISSN
ISBN: 978-1-79238-989-4Metadata
Zobrazit celý záznamTato publikace má vydavatelskou verzi s DOI 10.54941/ahfe100903
Abstrakt
We use AI techniques to statistically rigorously analyze combinations of query responses of two personality-related questionnaires. One questionnaire probes aspects of a participant's character (SOI) and the other avoidance of aversive outcomes together with approaches to goal orientated outcomes (BIS/BAS). We use one-hot encoding, dimension reduction with a neural network (a seven-layer auto-encoder) and two clustering algorithms to detect associations between the twelve combinations of SOI and BIS/BAS groups. We discover that for most combinations more than one association exists. Traditional, fallacious statistical methods cannot find these outcomes.
Klíčová slova
One-hot Encoding, Autoencoder, Neural Networks, DBSCAN Clustering, Spectral Clustering, BIS/BAS, SOI, Heat Maps
Trvalý odkaz
https://hdl.handle.net/20.500.14178/1763Licence
Licence pro užití plného textu výsledku: Creative Commons Uveďte původ 4.0 International