Claim Missing Document
Check
Articles

TikTok-Based Multimodal Input for Vocabulary Development in Writing Nur Habibah Sueb; Sumarta; Kamalia hakim, Putri
English Education: Jurnal Tadris Bahasa Inggris Vol 19 No 1 (2026): English Education: Jurnal Tadris Bahasa Inggris
Publisher : Universitas Islam Negeri Raden Intan Lampung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24042/ee-jtbi.v19i1.32331

Abstract

Vocabulary plays a fundamental role in developing students’ writing skills, yet many English as a Foreign Language (EFL) learners struggle to express ideas due to limited vocabulary knowledge. Although TikTok has increasingly been used as a language learning platform, limited research has explored how its multimodal features support vocabulary development in writing. Therefore, this study aimed to investigate how TikTok-based multimodal input supports students’ vocabulary development in writing at SMK Budi Mulia Karawang. This study employed a qualitative case study involving 24 tenth-grade students. Data were collected through classroom observations, vocabulary worksheets, semi-structured interviews with four students, and analysis of six students’ writing samples. The learning activities involved watching a Rapunzel video from the TikTok account @storytimeon321, identifying and recording unfamiliar vocabulary, and constructing sentences using the newly learned words. Data were analyzed using Braun and Clarke’s (2006) thematic analysis The findings revealed that TikTok-based multimodal input facilitated vocabulary acquisition, recognition, retention, and productive vocabulary use in writing. Visual elements, audio, and captions helped students understand word meanings, improve pronunciation, recognize vocabulary, and retain newly learned words. Furthermore, students demonstrated increased motivation and successfully transferred newly acquired vocabulary into meaningful written sentences. Overall, TikTok-based multimodal learning provides contextualized learning experiences that effectively support vocabulary development and enhance EFL students’ writing skills.
Prompt Engineering to CEFR Alignment: Investigating Generative AI for the Creation of English Listening Assessments Fikri Asih Wigati; Putri Kamalia Hakim; Nia Pujiawati; Maya Rahmawati
Eduvelop: Journal of English Education and Development Vol. 9 No. 1 (2026): Eduvelop: Journal of English Education and Development
Publisher : Universitas Sulawesi Barat

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31605/eduvelop.v9i1.6207

Abstract

Meeting the increasing demand for internationally benchmarked English listening exams is difficult, especially in educational settings with limited resources. In a human–AI collaboration framework, this study investigates the feasibility of using generative artificial intelligence, specifically ChatGPT-4, to support the early development of English listening scripts and test items aligned with the CEFR. Using an exploratory research design, the study generated 20 listening scripts and matching multiple-choice questions across CEFR reference levels A2, B1, B2, and C1 using an iterative prompt engineering technique called Progressive-Hint Prompting (PHP). The produced materials were examined using Text Inspector's descriptive linguistic metrics, which included qualitative assessments of spoken discourse characteristics, topical coverage, and distractor plausibility, as well as lexical profile, readability, and script length. The results show that when guided by structured prompts and ongoing human evaluation, ChatGPT-4 can perform well as a drafting aid. The created scripts demonstrated systematic linguistic variance across CEFR reference levels, particularly in lexical range and text complexity. Nevertheless, several drawbacks were noted, including unequal topical distribution, decreased pragmatic naturalness at higher competence levels, and inconsistent calibration of spoken discourse features. To ensure that distractors were text-based and aligned with assessment criteria, item quality needed to be refined iteratively. These results imply that iterative human-AI interaction, rather than automated generation alone, determines the quality of AI-generated listening materials. The study emphasizes the ongoing importance of professional human oversight while highlighting the potential of generative AI as a resource-efficient support tool for the development of listening assessments. To investigate the efficacy of AI-assisted materials in operational assessment contexts, future research should focus on empirical validation with test takers.