Scholarlink

<p>Personality recognition has emerged as a rapidly expanding research area with significant applications in human–computer interaction, psychological assessment, and social robotics, driven by advances in computational modeling and the increasing availability of linguistic and behavioral data. Despite notable advances, accurately predicting personality traits from text remains challenging due to the opaque nature of deep learning models and their limited explainability across linguistic contexts. In parallel, existing research has largely focused on English-language data, leaving personality prediction underexplored in multilingual settings and morphologically rich, low-resource languages. In this paper, we propose MMoECP, a Multi-Gate Mixture of Experts for Computational Personality Analysis framework that integrates a diverse set of computational models. While previous works have focused on personality prediction, our framework uniquely combines explainable artificial intelligence (AI) techniques, such as LIME and SHAP, with a multi-task learning (MTL) configuration to provide transparent and human-understandable insights into model decisions. We evaluate the proposed framework on five diverse personality analysis datasets, covering both English and Arabic languages. Experimental results demonstrate that MMoECP consistently outperforms traditional multi-label learning (MLL) models, particularly in multilingual and culturally diverse contexts.</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

Multi-Gate Mixture-of-Experts with Explanation for Predictive Computational Personality Analysis

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年5月3日

查看全文
  • Ahmed R. Elmahalawy,
  • Min Wei,
  • Xiaohua Wu,
  • Xiaohui Tao,
  • Lin Li

摘要

Personality recognition has emerged as a rapidly expanding research area with significant applications in human–computer interaction, psychological assessment, and social robotics, driven by advances in computational modeling and the increasing availability of linguistic and behavioral data. Despite notable advances, accurately predicting personality traits from text remains challenging due to the opaque nature of deep learning models and their limited explainability across linguistic contexts. In parallel, existing research has largely focused on English-language data, leaving personality prediction underexplored in multilingual settings and morphologically rich, low-resource languages. In this paper, we propose MMoECP, a Multi-Gate Mixture of Experts for Computational Personality Analysis framework that integrates a diverse set of computational models. While previous works have focused on personality prediction, our framework uniquely combines explainable artificial intelligence (AI) techniques, such as LIME and SHAP, with a multi-task learning (MTL) configuration to provide transparent and human-understandable insights into model decisions. We evaluate the proposed framework on five diverse personality analysis datasets, covering both English and Arabic languages. Experimental results demonstrate that MMoECP consistently outperforms traditional multi-label learning (MLL) models, particularly in multilingual and culturally diverse contexts.