KMITL

Permanent URI for this communityhttps://dspace.kmitl.ac.th/handle/kmitl/1

Browse

Settings

Access type: UnknownSubject: search.filters.subject.Large Language Model

Search Results

Now showing 1 - 2 of 2
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    Classifying Lexical Variations in Thai Social Media: A Machine Learning and LLMs Approach
    (2025-01-01)
    Chirawat, Pimmada
    ;
    Leenoi, Dhanon
    ;
    Takhom, Akkharawoot
    ;
    Boonkwan, Prachya
    ;
    Utasri, Tharathon
    Social media platforms like Facebook, X (formerly Twitter), and TikTok produce large amounts of user content, offering valuable data for Social Media Analytics (SMA). However, analyzing Thai social media presents challenges due to lexical variations, such as spelling changes, semantic shifts, and the creation of new words (lexicogenesis). These features, along with the lack of spaces between words in Thai script, complicate traditional text analysis methods. This study addresses these challenges by using a combination of machine learning (ML) models and large language models (LLMs). We employ Bidirectional Long Short-Term Memory (Bi-LSTM) networks, pretrained models like BERT-base-Thai, and advanced LLMs such as LLaMA-3, Mistral, Gemma, and Phi to classify and analyze Thai social media content. Our research enhances the understanding of lexical variations and improves the processing of Thai language in social media, contributing to the development of more effective natural language processing tools.
      1
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    An LLM-Powered Virtual Assistant for Authoring Competency-Based Learning Objectives in Basic Education: A Proof-of-Concept Study
    (2025-01-01)
    Lertyosbordin, Chacharin
    ;
    Aphisinrungrot, Puvasit
    ;
    Boonyuen, Poramate
    ;
    Nittayathammakul, Vitsanu
    Thailand's ongoing shift toward Competency-Based Education (CBE) has emphasized the need for practical tools that help teachers translate national policy into classroom practice. However, many educators still face difficulties in developing curriculum-aligned, competency-based learning objectives (CBLOs) due to limited time, training, and pedagogical support. This study addresses that gap by designing and evaluating a proof-of-concept virtual authoring assistant powered by a large language model (LLM). The system was developed using a Rapid Application Development (RAD) framework and fine-tuned using curriculum-derived custom knowledge to align with Thailand's Basic Education Core Curriculum B.E. 2551 (A.D. 2008) across cognitive, affective, and psychomotor domains. A Design and Development Research (DDR) Type I approach guided three phases: system prototyping, expert quality evaluation, and usability testing with in-service teachers. Results revealed a Very Good quality rating from experts (M = 4.85/5.00) and a Good usability score (SUS = 81.2), confirming both pedagogical soundness and practical feasibility. The study demonstrates that an LLM-powered virtual assistant can effectively support teachers in creating high-quality CBLOs while reducing cognitive and temporal workload. This work contributes a model with strong potential for scaling AI-supported competency-based curriculum design, bridging the gap between educational policy and classroom implementation.