Jeni Putra
Universitas Pendidikan Indonesia

Published : 2 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 2 Documents
Search

A Comparative Study of Human and AI Assessment in Japanese Sakubun Writing Jeni Putra; Masashi Umemoto; Susi Widianti; Novia Hayati; Muthi Afifah
KIRYOKU Vol 10, No 2 (2026): Kiryoku: Jurnal Studi Kejepangan
Publisher : Applied Foreign Language Study Program, Vocational College, Diponegoro University.

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.14710/kiryoku.v10i2.710-723

Abstract

This study compares the assessment of Japanese sakubun by a native Japanese teacher and two large language model based AI tools, Gemini AI (3.1) and ChatGPT (5.5), and examines the extent to which AI generated scores align with human assessment. The data comprised eight sakubun texts on the theme of meiwaku (inconvenience) written by second year students with approximately JLPT N4 level Japanese proficiency. Each sakubun was assessed using the same rubric covering four dimensions: content, organization, expression, and accuracy, as well as an overall score. The scores were descriptively compared across the three evaluators at both the criterion and overall levels. The results showed that the Japanese teacher assigned the highest average overall score of 16.25, followed by Gemini AI with 14.25 and ChatGPT with 13.75. Of the two AI tools, Gemini AI demonstrated closer overall alignment with the teacher’s assessment. Both AI systems also exhibited a score compression tendency. Higher quality sakubuns were generally evaluated lower than by the teacher, whereas some lower quality sakubuns received relatively higher scores. The most substantial discrepancies were observed in content and expression, indicating that AI assessment was less sensitive to idea development, contextual appropriateness, naturalness of expression, and subtle linguistic nuances. These findings suggest that although Gemini AI and ChatGPT can provide useful supplementary assessment, human evaluator judgment remains essential, particularly for evaluating qualitative and context sensitive aspects of Japanese writing. 
Virtual Linguistic Landscape on Social Media: Brand Image Construction of Japanese Beverages in Japan and Indonesia Muthi Afifah; Sugihartono Sugihartono; Susi Widianti; Jeni Putra; Adinda Nursyaharani; ⁠Michelle Safana
Chi e Journal of Japanese Learning and Teaching Vol. 14 No. 2 (2026): October 2026
Publisher : Universitas Negeri Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15294/chie.v14i2.64298

Abstract

This Study examines how Japanese beverage brands construct brand images through language use on Instagram across Japanese and Indonesian markets. Drawing on the concept of the virtual linguistic landscape (VLL), it investigates how linguistic choices foreground “Japaneseness” and how this emphasis varies across brands and market contexts. The study employs a descriptive qualitative approach, combining thematic analysis of promotional content with an examination of noun frequencies and Japan-related lexical items. Data comprise captions published on the official Japanese and Indonesian Instagram accounts of Pocari Sweat and ITO EN’s Oi Ocha between November 2025 and April 2026. The findings reveal distinct patterns of brand positioning. In Indonesia, Oi Ocha combines its green tea as an authentic Japanese beverage suited to a contemporary lifestyle. Pocari Sweat Indonesia emphasizes hydration and functional benefits through references to local routines and religious observances, with little explicit emphasis on Japanese origin. In Japan, Oi Ocha foregrounds international sports endorsements and Japanese tea identity, whereas Pocari Sweat emphasizes photography, youth, and everyday lifestyles. These findings suggest that Japaneseness functions as a selective branding resource whose prominence varies according to product positioning and market context.