Scholarlink

<p>Survey data often lacks explicit labeling, making it difficult to apply advanced machine learning techniques for predictive analysis. The study proposes an approach to systematically converting and binarizing survey data, addressing the lack of labeled data in text-based surveys. The survey dataset contains responses from 309 male fertility patients in Malaysia, collected over a one year period from November 2021 to October 2022. The survey data includes information on demographic, occupational stress, job satisfaction, and job performance. A comprehensive comparison is conducted between the traditional normalization method and the proposed method by utilizing eight machine learning and five large language models. Our proposed method demonstrates superior performance with an accuracy improvement of 9.68% for machine learning models and 16.67% for large language models. The findings identify work-time balance, work-energy balance, and colleague support as key predictors of job satisfaction using Local interpretable Model-agnostic Explanations. Top two sentiment analyzers were employed together with three generative AI models to validate the superiority of the proposed method. The study’s implications extend to HR practices and organizational decision-making, providing targeted strategies for enhancing employee satisfaction and engagement.</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

A Novel Approach to Label Generation in Text-Based Survey Data for Predictive Modeling of Job Satisfaction with Explainable and Generative AI

  • 期刊论文

  • 发表日期：

    2025年10月15日

查看全文
  • Jannat Sultana,
  • Rashedur M. Rahman

摘要

Survey data often lacks explicit labeling, making it difficult to apply advanced machine learning techniques for predictive analysis. The study proposes an approach to systematically converting and binarizing survey data, addressing the lack of labeled data in text-based surveys. The survey dataset contains responses from 309 male fertility patients in Malaysia, collected over a one year period from November 2021 to October 2022. The survey data includes information on demographic, occupational stress, job satisfaction, and job performance. A comprehensive comparison is conducted between the traditional normalization method and the proposed method by utilizing eight machine learning and five large language models. Our proposed method demonstrates superior performance with an accuracy improvement of 9.68% for machine learning models and 16.67% for large language models. The findings identify work-time balance, work-energy balance, and colleague support as key predictors of job satisfaction using Local interpretable Model-agnostic Explanations. Top two sentiment analyzers were employed together with three generative AI models to validate the superiority of the proposed method. The study’s implications extend to HR practices and organizational decision-making, providing targeted strategies for enhancing employee satisfaction and engagement.