Scholarlink

<p>This study exploits technological and computational strategies to examine, through a novel methodological framework, motivational dynamics concerning organizational behavior. Drawing on the Reinforcement Sensitivity Theory, a Virtual Reality Organizational Environment (VROE) integrating eye-tracking and decision-making metrics was implemented to differentiate individuals with high and low Behavioral Inhibition (BIS) and Behavioral Activation (BAS) systems. A machine learning (ML) approach was used to analyse data from 68 participants in Spain. The results indicated moderate to high discriminative accuracy for BAS identification, achieving up to 75% predominantly through the analysis of eye-tracking data in form of inclusive and averted gaze patterns. The ML models demonstrated a slight capability for BIS, with an accuracy of 67%. The findings underscore the potential of theory-based applications integrating virtual reality and machine learning to yield motivational insights within organizational settings.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Detecting inhibition and activation tendencies in organizational behavior: a virtual reality and machine learning-based methodological framework

  • 期刊论文

  • 发表日期：

    2025年7月16日

查看全文
  • Sergio C. Torres,
  • Elena Parra-Vargas,
  • Lucía Carrasco-Ribelles,
  • Javier Marín-Morales,
  • Mariano Alcañiz

摘要

This study exploits technological and computational strategies to examine, through a novel methodological framework, motivational dynamics concerning organizational behavior. Drawing on the Reinforcement Sensitivity Theory, a Virtual Reality Organizational Environment (VROE) integrating eye-tracking and decision-making metrics was implemented to differentiate individuals with high and low Behavioral Inhibition (BIS) and Behavioral Activation (BAS) systems. A machine learning (ML) approach was used to analyse data from 68 participants in Spain. The results indicated moderate to high discriminative accuracy for BAS identification, achieving up to 75% predominantly through the analysis of eye-tracking data in form of inclusive and averted gaze patterns. The ML models demonstrated a slight capability for BIS, with an accuracy of 67%. The findings underscore the potential of theory-based applications integrating virtual reality and machine learning to yield motivational insights within organizational settings.