Skip to content

Structural and configurational analyses of GenAI-mediated informal digital learning of Chinese, multicultural personality traits, and willingness to communicate: evidence from plurilingual international students in China

Oct 2026 · Journal of Multilingual and Multicultural Development · 1 citation · 68 references
EFL/ESL Teaching and Learning

Abstract

This study examines how plurilingual international students’ generative AI-mediated informal digital learning of Chinese (GenAI-IDLC) interacts with dimensions of multicultural personality to predict their second language willingness to communicate (L2 WTC). Survey responses were collected from 387 plurilingual international students learning Chinese in China and analyzed using structural equation modeling (SEM) and fuzzy-set qualitative comparative analysis (fsQCA) approaches. SEM results demonstrated that learners’ GenAI-IDLC was significantly and positively associated with cultural empathy, open-mindedness, social initiative, flexibility, and L2 WTC, but not emotional stability. Moreover, international students’ flexibility was significantly and positively associated with their L2 WTC, whereas their cultural empathy, open-mindedness, emotional stability, and social initiative were not significantly associated with their L2 WTC. The association between GenAI-IDLC and L2 WTC was partially mediated by flexibility. The fsQCA further identified four configurations in which different combinations of GenAI-IDLC and multicultural personality were linked to high L2 WTC. By integrating SEM with fsQCA, the study advances our understanding of the multiple and complex pathways underlying L2 WTC in the GenAI-mediated informal Chinese learning context. The results offer a basis for implications for language educators and universities seeking to facilitate cross-cultural communication through GenAI technologies.

View source

Similar papers

#artificial intelligence Conference Open access Apr 2020

ECCOLA - a Method for Implementing Ethically Aligned AI Systems

The method, ECCOLA, is presented, which aims at making the high-level AI ethics principles more practical, making it possible for developers to more easily implement them in practice.

Ville Vakkuri, Kai-Kristian Kemell, P. Abrahamsson · 64 citations · ⚡6
#computer vision Review Apr 2024

AI-powered Code Review with LLMs: Early Results

The goal is to not only refine the accuracy of the LLM-based tool but also to underscore its potential in streamlining the software development lifecycle through proactive code improvement and education.

Z. Rasheed, Malik Abdul Sami, Muhammad Waseem et al. · 62 citations · ⚡3
#computer vision Open access Mar 2024

LLM-based agents for automating the enhancement of user story quality: An early report

The use of large language models to automatically improve the user story quality in Austrian Post Group IT agile teams is explored, with a reference model for an Autonomous LLM-based Agent System developed and implemented at the company.

Zheying Zhang, M. Rayhan, Tomas Herda et al. · 48 citations · ⚡4
#computer vision Review Mar 2024

System for systematic literature review using multiple AI agents: Concept and an empirical evaluation

This paper introduces a novel multi-AI-agent system designed to fully automate SLRs, and demonstrates how it substantially reduces the time and effort traditionally required for SLRs while maintaining comprehensiveness and precision.

Abdul Malik Sami, Z. Rasheed, Kai-Kristian Kemell et al. · 44 citations · ⚡2
#computer vision Feb 2024

Can Large Language Models Serve as Data Analysts? A Multi-Agent Assisted Approach for Qualitative Data Analysis

The proposed LLM-based multi-agent system automates qualitative data analysis process, creating opportunities for researchers and practitioners, and future improvements focus on enhancing multilingual performance and integrating continuous expert feedback.

Z. Rasheed, Muhammad Waseem, Aakash Ahmad et al. · 41 citations

Related blog posts

Microsoft Research Blog Oct 7, 2026

Agent Lightning v1.0: A 3,500-Line Lightweight Agentic RL Framework for Training Agents with Real Harnesses

Training AI agents with reinforcement learning can be challenging because their tools, context, and decision-making are managed by complex frameworks. Agent Lightning connects existing agents to RL training, making it easier to improve them without rebuilding them. The post Agent Lightning v1.0: A 3,500-Line Lightweight Agentic RL Framework for Training Agents with Real Harnesses appeared first on Microsoft Research.

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.