Garuda - Garba Rujukan Digital

Aspect-Based Sentiment Analysis on Application Review using Convolutional Neural Network Putri Arta Aritonang; Monika Evelin Johan; Iwan Prasetiawan
ULTIMA InfoSys Vol 13 No 1 (2022): Ultima InfoSys : Jurnal Ilmu Sistem Informasi
Publisher : Universitas Multimedia Nusantara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31937/si.v13i1.2684

As an obligatory application during the COVID-19 pandemic by Indonesians, PeduliLindungi must have provided outstanding quality services to its users. However, as of December 2021, users’ sentiment toward the quality and service of the PeduliLindungi application was still low, with an application rating of 3.6 out of 5 on the Google Play Store. This study uses text mining techniques for the Aspect-Based Sentiment Analysis (ABSA) task in the PeduliLindungi application review, a sentiment analysis task based on the aspect category of the application. This study aims to classify the users’ sentiment on aspects of the application and provide insight and knowledge to improve the quality of the PeduliLindungi application. The ABSA method used in this study is the classification of aspects and sentiments using the Convolutional Neural Network (CNN) algorithm. The results showed that the CNN model could produce such good performance with an f1 score of 92.23% in the aspect classification and 95.13% in the sentiment classification. The results of user sentiment modelling showed the dominance of negative sentiment in the eight aspects of the application, namely Visual Experience, Scan – Check-in/Out, Vaccine Certificate, eHac, COVID Test, Register/Login, Performance and Stability, and Privacy, Data, and Security. Index Terms—Aspect-Based Sentiment Analysis, Convolution Neural Network, PeduliLindungi, Text Classification, Text Mining.

Image Error Detection: A Systematic Literature Review Raymond Oetama; David Tjahjana; Iwan Prasetiawan; Catherine Anastasia
G-Tech: Jurnal Teknologi Terapan Vol 7 No 3 (2023): G-Tech, Vol. 7 No. 3 Juli 2023
Publisher : Universitas Islam Raden Rahmat, Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33379/gtech.v7i3.2494

The advancement of technology, as well as the creation of new techniques and methodologies for image analysis, is rapid. However, image detection may face some errors. Image error detection will be discussed in this comprehensive literature review. Throughout the papers, this work attempts to learn about the types of images used, algorithms that are frequently used, techniques that are frequently used, and metrics used to test the correctness of the suggested approach. The most commonly used image type is medical images such as Magnetic Resonance Imaging, the algorithm that is widely used is a Convolutional Neural Networks based algorithm. The method that is widely used is a machine learning-based method, and the measurement that is widely used is a Peak Signal Noise Ratio measurement method to measure the accuracy of the algorithm.

Unmasking the Sentiments of Labuan Bajo: An Instagram-based Analysis for Tourism Insights through VADER Sentiment Analysis Johan Setiawan; Vegeterrikin Gousander; Iwan Prasetiawan
G-Tech: Jurnal Teknologi Terapan Vol 7 No 3 (2023): G-Tech, Vol. 7 No. 3 Juli 2023
Publisher : Universitas Islam Raden Rahmat, Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33379/gtech.v7i3.2615

Labuan Bajo merupakan tujuan utama wisata yang terkenal, menarik banyak wisatawan asing dan lokal yang dengan antusias membagikan pengalaman mereka melalui foto dan video di Instagram. Penelitian ini bertujuan untuk mengeksplorasi umpan balik dari wisatawan lokal dan asing yang telah mengunjungi Labuan Bajo, serta mengidentifikasi tujuan wisata paling populer di daerah tersebut. Data penelitian dikumpulkan dari Instagram dengan menggunakan tagar "labuanbajo". Metode analisis sentimen berbasis leksikon VADER digunakan untuk mengukur polaritas sentimen. Temuan eksperimental menunjukkan tingkat akurasi yang impresif, yaitu 72%, dengan metode sentimen leksikon VADER. Hasil penelitian mengungkapkan bahwa tujuan wisata Labuan Bajo cenderung membangkitkan sentimen positif, dengan 58,55% dari 3.351 data yang dikumpulkan dikategorikan sebagai positif, mencapai total 1.962 kali. Destinasi populer yang sering dikunjungi wisatawan antara lain Pulau Komodo, Pulau Padar, Pink Beach, Pulau Kelor, Pulau Rinca, Pulau Kanawa, dan Desa Waerebo.

Optimizing XGBoost with Optuna for Attendance-Based Prediction of Student Academic Success Marcello Roy; Ririn Ikana Desanti; Iwan Prasetiawan; Suryasari Suryasari
Journal of Applied Data Sciences Vol 7, No 2: May 2026
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v7i2.1116

The growth of data analytics in higher education has increased the need for predictive models that identify students’ academic potential and support data-driven decision-making. Academic institutions are able to enhance student outcomes by implementing suitable interventions that are based on an accurate early prediction of Grade Point Average (GPA). This study aims to develop a practical and accurate GPA prediction model based on Extreme Gradient Boosting (XGBoost), enhanced through Optuna-based hyperparameter tuning, to support academic monitoring systems in higher education. This model is intended to assist academic monitoring systems in higher education. Using academic performance data, attendance records, and course load information obtained from 961 undergraduate students, a quantitative predictive modeling approach was implemented. The CRISP-DM framework was implemented during the modelling process, which included the following stages: data understanding, data preparation, modelling, evaluation, and deployment. To ensure the stability and relevance of the model, exploratory analysis and correlation assessments were implemented to determine feature selection. Optuna was employed to optimize hyperparameters, utilizing Bayesian optimization with adaptive trial pruning to efficiently examine the parameter space. Experimental results demonstrate that the Optuna-tuned XGBoost model achieved superior predictive performance compared to baseline XGBoost models and models optimized using Grid Search and Random Search. The proposed model attained a coefficient of determination (R²) of 0.8637 and a Root Mean Square Error (RMSE) of 0.1165, indicating improved accuracy and robustness in handling large prediction errors. To enhance practical applicability, the final model was deployed in a Streamlit-based web application that enables real-time GPA prediction and supports academic advisors. Overall, the findings confirm that Optuna-based hyperparameter tuning significantly enhances XGBoost performance and provides a solution for data-driven academic monitoring in higher education institutions.

Optimizing XGBoost with Optuna for Attendance-Based Prediction of Student Academic Success Marcello Roy; Ririn Ikana Desanti; Iwan Prasetiawan; Suryasari Suryasari
Journal of Applied Data Sciences Vol 7, No 2: May 2026
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v7i2.1116

The growth of data analytics in higher education has increased the need for predictive models that identify students’ academic potential and support data-driven decision-making. Academic institutions are able to enhance student outcomes by implementing suitable interventions that are based on an accurate early prediction of Grade Point Average (GPA). This study aims to develop a practical and accurate GPA prediction model based on Extreme Gradient Boosting (XGBoost), enhanced through Optuna-based hyperparameter tuning, to support academic monitoring systems in higher education. This model is intended to assist academic monitoring systems in higher education. Using academic performance data, attendance records, and course load information obtained from 961 undergraduate students, a quantitative predictive modeling approach was implemented. The CRISP-DM framework was implemented during the modelling process, which included the following stages: data understanding, data preparation, modelling, evaluation, and deployment. To ensure the stability and relevance of the model, exploratory analysis and correlation assessments were implemented to determine feature selection. Optuna was employed to optimize hyperparameters, utilizing Bayesian optimization with adaptive trial pruning to efficiently examine the parameter space. Experimental results demonstrate that the Optuna-tuned XGBoost model achieved superior predictive performance compared to baseline XGBoost models and models optimized using Grid Search and Random Search. The proposed model attained a coefficient of determination (R²) of 0.8637 and a Root Mean Square Error (RMSE) of 0.1165, indicating improved accuracy and robustness in handling large prediction errors. To enhance practical applicability, the final model was deployed in a Streamlit-based web application that enables real-time GPA prediction and supports academic advisors. Overall, the findings confirm that Optuna-based hyperparameter tuning significantly enhances XGBoost performance and provides a solution for data-driven academic monitoring in higher education institutions.

Title

Found 5 Documents
Search

Abstract

Abstract

Abstract

Abstract

Abstract

Title Search

Found 5 Documents Search

Abstract

Abstract

Abstract

Abstract

Abstract

Title

Found 5 Documents
Search