Examining Non-English Foreign Language Education Through Social Media: Discourse and Psychological Analysis Based on Text Mining

Abstract

Based on data from Weibo, the largest social media platform in China, this study employs a composite text mining approach to analyze public discussions about learning non-English foreign languages in recent years, with a focus on the emergence of ChatGPT as a pivotal influence. Through topic modeling and psychological characteristics analysis using the Linguistic Inquiry and Word Count (LIWC) dictionary, this research uncovers key topics and psychological traits associated with discussions on Weibo about non-English foreign language education. Identified topics include Employment, Regrets, Cultural Exchange, and Going Abroad, among others. Analysis of language use reveals significant shifts in psychological characteristics following the rise of ChatGPT, with complex interrelations between these traits and variations across different discussion phases. This study offers valuable insights into Chinese public interest in non-English foreign language education, contributing to the development and refinement of foreign language education in China. It also validates a composite methodology that can be applied to research on language education. The findings provide guidance for optimizing foreign language education in the context of rapidly evolving technology.

Keywords

• Non-English
• foreign language education
• psychological characteristics
• topics
• linguistic inquiry and word count (LIWC)