Appreciating the Performance of Neuroscience Mining in NeuroIS research: A Case Study on Consumer's Product Perceptions in the Two UI Modes—Dark UI vs. Light UI
Appreciating the Performance of Neuroscience Mining in NeuroIS research: A Case Study on Consumer's Product Perceptions in the Two UI Modes—Dark UI vs. Light UI
Files
Date
2023-01-03
Authors
Costello, Francis
Kim, Min Gyeong
Lee, Kun Chang
Contributor
Advisor
Department
Instructor
Depositor
Speaker
Researcher
Consultant
Interviewer
Annotator
Journal Title
Journal ISSN
Volume Title
Publisher
Volume
Number/Issue
Starting Page
1010
Ending Page
Alternative Title
Abstract
The goal of the current study was to provide information on the potential of neuroscience mining (NSM) for comprehending NeuroIS paradigms. NSM is an interdisciplinary field that combines neuroscience and business mining, which is the application of big data analytics, computational social science, and other fields to business problems. Therefore, NSM makes it possible to apply predictive models to NeuroIS datasets, such as machine learning and deep learning, to find intricate patterns that are hidden by conventional regression-based analysis. We predicted 28 individual EEG power spectra separated brainwave data using a Random Forest (RF) model. Next, we used NSM to precisely predict how consumers would perceive a product online, depending on whether a light or dark user interface (UI) mode was being used. The model was then used to extract more precise results that could not be obtained using more conventional linear-based analytical models using sensitivity analysis. The benefits of using NSM in NeuroIS research are as follows: (1) it can relieve the burden of the three-horned dilemma described by Runkel and McGrath; (2) it can enable more temporal data to be directly analyzed on the target variables; and (3) sensitivity analysis can be performed on a condition/individual basis, strengthening the rigor of findings by reducing sample bias that can be lost in grand averaging of data when analyzed with methods like GLM.
Description
Keywords
Digital Mobile Services for Everyday Life,
consumers' attractiveness/usefulness perception,
eeg,
machine learning,
neuroscience mining,
user interface mode
Citation
Extent
10
Format
Geographic Location
Time Period
Related To
Proceedings of the 56th Hawaii International Conference on System Sciences
Table of Contents
Rights
Attribution-NonCommercial-NoDerivatives 4.0 International
Rights Holder
Local Contexts
Collections
Email libraryada-l@lists.hawaii.edu if you need this content in ADA-compliant format.