Claim Missing Document
Check
Articles

Found 3 Documents
Search

Analysis of Direct Scoring and Similarity-Based Scoring Approaches in Automatic Short Answer Scoring (ASAS) Bayu Wicaksono; Rasim Rasim; Yaya Wihardi
Brilliance: Research of Artificial Intelligence Vol. 5 No. 1 (2025): Brilliance: Research of Artificial Intelligence, Article Research May 2025
Publisher : Yayasan Cita Cendekiawan Al Khwarizmi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47709/brilliance.v5i1.6275

Abstract

In the era of digital education, the need for automated scoring systems for short text answers has been steadily increasing. Automatic Short Answer Scoring (ASAS) aims to automate this assessment process with efficient and consistent approaches. Two commonly used approaches in ASAS are direct scoring and similarity-based scoring. Although these two approaches have been widely used, previous research has mostly focused on metrics like RMSE and Pearson Correlation to assess model performance. This study aims to provide a more in-depth analysis by comparing both approaches in two evaluation scenarios, specific-prompt and cross-prompt, by evaluating the accuracy and stability of the models. The dataset used in this study is the Rahutomo dataset. The results of the analysis show that direct scoring outperforms similarity-based scoring in terms of lower RMSE, higher Pearson Correlation, and fewer outliers. In the specific-prompt scenario, an RMSE of 0.0817 and a Pearson Correlation of 0.9504 were obtained, while in the cross-prompt scenario, the RMSE was 0.0917 and the Pearson Correlation was 0.9286. This study provides a more comprehensive insight into model performance by not only relying on evaluation metrics but also examining the distribution of residuals and outliers, which offers a more complete picture of model stability. Based on these findings, direct scoring is recommended for implementation in ASAS systems and for future research that can extend the analysis to other datasets or languages.
Facial Expression Recognition of Students in Classroom Using Hybrid MobileNetV3-Vision Transformer with Token Downsampling Mochamad Khaairi; Rasim Rasim; Yaya Wihardi
Brilliance: Research of Artificial Intelligence Vol. 5 No. 1 (2025): Brilliance: Research of Artificial Intelligence, Article Research May 2025
Publisher : Yayasan Cita Cendekiawan Al Khwarizmi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47709/brilliance.v5i1.6323

Abstract

In large classroom environments, teachers often struggle to monitor each student’s facial expression throughout the learning process. Yet, facial expressions are important indicators of students’ emotional states and engagement, which, when detected in real time, can support a more adaptive learning experience. Most previous research on Facial Expression Recognition (FER) has relied on Convolutional Neural Networks (CNN), which tend to be limited in capturing global relationships between facial features. Additionally, many studies focus on model accuracy without evaluating their practical effectiveness in real classroom settings. This study aims to develop a facial expression recognition model that is both accurate and efficient for use in classroom contexts. A hybrid Vision Transformer (ViT) architecture is proposed, which combines MobileNetV3 for local feature extraction and a Vision Transformer for global context modeling. To reduce the number of tokens and computational cost, a Token Downsampling method is introduced within the transformer blocks. The model is trained using the FER2013 dataset and achieves a test accuracy of 71.24%, surpassing the baseline pretrained ViT model, which reached only 70.10%. Additionally, the Token Downsampling method improves inference speed. Furthermore, the model is tested on a custom dataset collected from students in a real classroom setting to evaluate its performance in practical implementation. Although the performance on the classroom dataset is not yet optimal, the results on FER2013 demonstrate the potential of this approach for further development toward real-time and accurate facial expression recognition in educational environments.
Artificial Intelligence-Based Leveling System for Determining Severity Level of Autism Spectrum Disorder R Rasim; M Munir; Yaya Wihardi; Lanto Ningrayati Amali
Scientific Journal of Informatics Vol. 12 No. 4: Special Issue
Publisher : Universitas Negeri Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15294/sji.v12i4.14440

Abstract

Purpose: The aim of this research is to analyze the use of an artificial intelligence (AI)-based leveling system to determine the severity of autism spectrum disorders (ASD). Methods: The research method is a systematic literature review. This study addresses three key questions: (i) What factors are used to determine ASD severity? (ii) What algorithms or AI models are used in classifying ASD severity? (iii) What are the results of this AI-based leveling system in terms of severity levels or categories? Results: The study results identified several key factors that influence ASD severity, including age, IQ, genetic and neurological factors, co-occurring mental health conditions, and sociodemographic variables. Various AI algorithms, including machine learning and deep learning techniques, are used to classify the severity of ASD. The results of this study highlight the effectiveness of AI in providing objective, consistent, and measurable assessments of ASD severity, although challenges such as data quality and ethical considerations remain. AI-based leveling systems show significant potential in improving assessment and intervention processes for ASD. Novelty: This research systematically synthesizes studies on AI-driven ASD severity assessment, providing insights into crucial variables for AI-based evaluation tools. By analyzing the factors influencing severity and the effectiveness of AI models, this study identifies promising approaches for classification. The findings offer valuable contributions to the development of AI-based tools in clinical and educational applications. Further research is necessary to improve AI reliability, address biases, and maximize its potential in ASD assessment and intervention.