Eun Ji Choi
Korea University · 社会科学
研究室紹介
Professor Eun Ji Choi's research lab specializes in applied linguistics, multimodal communication, and AI-driven educational technology, with a focus on enhancing language learning and digital instruction. The lab investigates cross-cultural academic communication, particularly the oral and written performance of international students in Korean academic contexts, while also advancing multimodal fake news detection through innovative vision-language models. A central theme is the development of flexible, AI-powered digital materials for Korean language education, integrating adaptive technologies and multimodal data processing. The lab bridges language education, artificial intelligence, and computational linguistics to create responsive, learner-centered solutions.
Research Overview
Research Output Trend
Figures are computed from collected data and may differ slightly.
Selected Papers
5Eun-ji ChoiMyungsook Jung. 2007. 10. 30. A Survey of Perceptions on Foreign Students' Academic Oral Presentation in Korean language. Bilingual Research 35, 303-332. This study conducted the survey regarding the perception on academic oral presentation in Korean language performed by foreign university or graduate students. 56 Koreans as the audience of academic oral presentation of foreign students and 28 foreign students who have performed the presentation more than twice participated in this s
This study investigates the types of writing tasks in main subject of Business administration. There are the most foreign students in the department of Business administration. And it is needed to conduct the research on the characteristics and aspects in that field. Especially it is worthy of notice that there would be differences in types of writing tasks between various study field. In these reasons, investigating was conducted to classify the types of writing tasks and estimate weight on tho
Detecting fake news has received a lot of attention. Many previous methods concatenate independently encoded unimodal data, ignoring the benefits of integrated multimodal information. Also, the absence of specialized feature extraction for text and images further limits these methods. This paper introduces an end-to-end model called TT-BLIP that applies the bootstrapping language-image pretraining for unified visionlanguage understanding and generation (BLIP) for three types for images, and bidi
This study explores development strategies for AI digital Korean materials aimed at ensuring flexibility. Language instructional materials development must account for the diverse characteristics of learners and the varied environments of educational fields. While developers have continuously strived to ensure this flexibility, paper-based materials have been constrained by a lack of adaptable methods and limited ease in module implementation. To address these limitations, this study proposes a
Multimodal Fake News Detection has received increasing attention recently. Existing methods rely on independently encoded unimodal data and overlook the advantages of capturing intra-modality relationships and integrating inter-modal similarities using advanced techniques. To address these issues, Cross-Modal Tri-Transformer and Metric Learning for Multimodal Fake News Detection (CroMe) is proposed. CroMe utilizes Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Lan