Claim Missing Document
Check
Articles

Found 2 Documents
Search

PERFORMANCE AND ACCURACY OF CHATGPT IN GENERATING MALAY ACADEMIC TEXTS: A COMPARATIVE STUDY WITH EXPERT CORRECTIONS Yaqin, Lalu Nurul; Hassan, Hasmidar; Yusof, Badriyah
LLT Journal: A Journal on Language and Language Teaching Vol 28, No 1 (2025): April 2025
Publisher : English Education Study Programme of Sanata Dharma University, Yogyakarta, Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24071/llt.v28i1.11698

Abstract

The increasing use of artificial intelligence in academic writing has raised concerns about the accuracy and coherence of AI-generated texts, particularly in underrepresented languages like Malay. This study evaluates the performance of ChatGPT in generating Malay academic texts by comparing AI-generated outputs with expert corrected versions, focusing on grammatical errors, structural inconsistencies, and lexical inaccuracies. A comparative analysis was conducted on two datasets: Trained Dataset (TD), where prompts included detailed context, and Untrained Dataset (UTD). ChatGPT-generated texts were reviewed by Malay linguistics and translation experts, who identified and corrected grammatical errors. A quantitative and qualitative analysis assessed error frequency and categorized linguistic challenges. Findings reveal that UTD contained significantly more grammatical errors (87 errors) than TD (18 errors), demonstrating the role of structured prompts in enhancing text quality. Common errors in UTD included incorrect sentence structure (27.59%), omission of names (14.94%), and inappropriate word choices (11.49%). While TD showed improved grammatical accuracy, errors in phrase structure, conjunction usage, and affixation persisted. The study concludes that AI-generated Malay texts lack syntactic stability, requiring expert intervention and model refinement. These findings highlight the need for linguistic adaptation, expanded training datasets and the integration of expert to enhance AI-generated Malay academic writing. Ultimately, this study presents a case study that provides empirical evidence that context-aware prompt engineering and expert-in-the-loop approaches are essential for enhancing the quality of AI outputs, especially in non-English settings. It also advocates for the development of AI models that can capture nuances and linguistic diversity, vital for inclusive education for all.
Dysphemism in eating expressions in Javanese: A study of cognitive semantics Hermandra, Hermandra; Citraresmana, Elvi; Sarudin, Anida; Hassan, Hasmidar
Studies in English Language and Education Vol 11, No 2 (2024)
Publisher : Universitas Syiah Kuala

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24815/siele.v11i2.36643

Abstract

The word eating can produce positive meaning as it is closely tied to human needs. This term is also intricately linked to eating habits. In Javanese society, this term serves to satisfy basic human needs and plays a pivotal role in defining social etiquette. Eating expressions have a broader meaning when examined from a dysphemistic perspective within cognitive semantics. This study employed a descriptive qualitative methodology, with data collection covering interviews, active listening, observation, and note-taking. The data were then analyzed using image schemas and conceptual meaning. The study found that the eating expressions underwent dysphemism in Javanese such as lambene ngemrus wae ket mau! (your mouth keeps eating!), wes, ngrokoti koyo tikus! (you eat like a rat!), Gimin esuk-esuk wis nguntal (Gimin ate too early this morning), wah, yahene wis nyekek ping pindho (you have eaten twice by this time), nyo, badhogen kabeh, aku rasah dingengehi (eat all the food and dont bother to spare for me), panganan kok di gaglak (how come you gulping the food?), and menungso kok gragas?! (how on earth could you only eat?!). Moreover, the study identified conceptual metaphors, comprising six structural metaphors and two orientational metaphors. Structural metaphors arise from systematic relationships observed in daily experiences, whereas orientational metaphors impart spatial direction, including the recognition of top-down image schemes, part-whole image schemes, existence image schemes, and merging image schemes.