Garuda - Garba Rujukan Digital

Analysis and Design of Sales Website at Twins Petshop Using the Waterfall Method Pinasti, Rafa Hadiya; Fajri, Ika Nur
Jurnal Informatika dan Rekayasa Perangkat Lunak Vol. 6 No. 1 (2025): Volume 6 Number 1 March 2025
Publisher : Universitas Teknokrat Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33365/jatika.v6i1.29

The pet shop industry continues to grow as people's interest in pets increases. However, many petshops face challenges in managing products and transactions that are still done manually. This is also experienced by Twins petshop, which still uses manual methods in managing product and transaction data, thus hindering data operational efficiency and market reach that has not been maximized. To overcome this problem, this study was made with the aim of designing and developing a website-based petshop sales information system, thereby helping to improve the efficiency of product and transaction data management. The development method used is the waterfall method which consists of several stages that must be carried out in stages, namely needs analysis, design, implementation, and testing. The tests are carried out using the balck-box testing method to ensure that all features run according to user needs. The results of the balckbox test show that of the eight scenarios tested, all succeeded with a 100% success percentage. Scenarios include admin logins with valid and invalid data, data editing and deletion, and adding products with invalid forms. The results of this study show that the website developed is able to increase the efficiency of product recording, transactions, and provide more complete information than the previous manual system.

Generative AI Image Sentiment Analysis on Social Media X using TF-IDF and FastText Saputra, Rahman; Pristyanto, Yoga; Fajri, Ika Nur
Journal of Applied Informatics and Computing Vol. 9 No. 5 (2025): October 2025
Publisher : Politeknik Negeri Batam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30871/jaic.v9i5.10627

This research investigates public opinion on AI-generated images on Social Media X using machine learning-driven text classification. Three classification models were evaluated: Complement Naïve Bayes (CNB) utilizing TF-IDF features, Support Vector Machine (SVM) merging TF-IDF with FastText embeddings, and IndoBERT as a modern transformer-based baseline. A total of 1,958 Indonesian tweets were collected via web scraping with relevant keywords, followed by a pipeline involving text cleaning, manual labeling into positive, negative, and neutral categories, and data balancing using the Synthetic Minority Over-sampling Technique (SMOTE) for the classical models (with class weighting applied for IndoBERT). Results show that the SVM model outperformed the others, achieving 68.7% accuracy with average precision, recall, and F1-score of 0.69, 0.69, and 0.68, respectively; CNB attained 64.1% accuracy with average metrics of 0.64; while IndoBERT recorded 58.2% accuracy with average precision, recall, and F1-score of 0.58, 0.58, and 0.57. Confusion matrix analysis revealed SVM's superior ability to distinguish positive and neutral sentiments in casual language, though IndoBERT demonstrated potential for capturing deeper semantic nuances despite underperforming due to dataset size and informal text. The findings highlight the efficacy of integrating statistical and semantic representations for improved sentiment analysis on unstructured, noisy social media data related to AI-generated imagery, while suggesting that transformer models like IndoBERT may benefit from larger datasets for optimal performance.

Sentiment Classification Analysis of Tokopedia Reviews Using TF-IDF, SMOTE, and Traditional Machine Learning Models Barus, Herianta; Fajri, Ika Nur; Pristyanto, Yoga
Journal of Applied Informatics and Computing Vol. 9 No. 5 (2025): October 2025
Publisher : Politeknik Negeri Batam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30871/jaic.v9i5.10524

This study explores sentiment classification on Tokopedia user reviews using TF-IDF for feature extraction and SMOTE to handle class imbalance. From nearly one million raw reviews sourced from Kaggle ("E-Commerce Ratings and Reviews in Bahasa Indonesia"), a final set of 6,477 relevant entries was obtained after rigorous preprocessing, including case folding, noise removal (emojis, URLs, numbers), normalization to KBBI standards, tokenization, stopword removal, and stemming with Sastrawi. The dataset consisted of 5,213 positive and 1,264 negative reviews (80.4% positive). SMOTE balanced the classes to 10,426 reviews with a 1:1 ratio for training. Five traditional machine learning models were evaluated: Naive Bayes, Logistic Regression, Support Vector Machine (SVM), Decision Tree, and Random Forest. Assessments were based on accuracy, precision, recall, F1-score, ROC-AUC, and computational time, using an 80:20 stratified split and 5-fold cross-validation. Random Forest achieved the best overall performance (accuracy: 0.9163, F1-score: 0.9133, ROC-AUC: 0.9784), while tuned SVM (C=10, RBF kernel) attained the highest accuracy of 0.9473 and F1-score of 0.9321. Cross-validation on Naive Bayes showed consistent results with an average accuracy of 88.09%. Further analysis using Logistic Regression coefficients identified influential features: positive sentiment associated with words like "mantap", "mudah", and "sukses", while negative sentiment correlated with "kecewa", "parah", and "lemot". These insights provide practical value for Tokopedia's teams to enhance user experience, such as improving app speed and addressing complaints. The findings demonstrate the effectiveness and efficiency of traditional machine learning techniques for sentiment analysis in Bahasa Indonesia contexts.

Public Sentiment Analysis on Corruption Issues in Indonesia Using IndoBERT Fine-Tuning, Logistic Regression, and Linear SVM Kono, Maria Fatima; Fajri, Ika Nur; Pristyanto, Yoga
Journal of Applied Informatics and Computing Vol. 9 No. 5 (2025): October 2025
Publisher : Politeknik Negeri Batam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30871/jaic.v9i5.10537

Sentiment analysis is a method in Natural Language Processing (NLP) that aims to understand public perceptions based on textual data from social media. Opinions expressed in digital platforms play an important role as they reflect public trust and attitudes toward strategic issues in Indonesia. This study aims to compare the performance of three IndoBERT-based approaches for sentiment classification, namely IndoBERT with full fine-tuning, IndoBERT as a feature extractor combined with Logistic Regression, and IndoBERT as a feature extractor combined with Linear SVM. The dataset was collected through the Twitter API, consisting of 2,012 tweets, which after preprocessing and balancing resulted in 2,252 labeled data for positive and negative sentiments. The preprocessing stage included cleansing, normalization, tokenization, stopword removal, and stemming. The dataset was then split into 80% training data, 10% validation data, and 10% testing data. Experimental results show that IndoBERT with full fine-tuning achieved the best performance, with an accuracy of 82.67%, an F1-score of 82.35%, and an AUC value of 0.87. Logistic Regression and Linear SVM produced lower accuracies of 80.20% and 78.22%, respectively. These findings indicate that fine-tuned IndoBERT is more effective in capturing the semantic nuances of the Indonesian language, while the non fine-tuning approaches offer better computational efficiency at the cost of reduced accuracy. This study contributes to the development of NLP methods for the Indonesian language, particularly in sentiment analysis, and highlights the potential of transformer-based models for analyzing strategic issues in social media.

Comparison of Light Gradient Boosting Machine, eXtreme Gradient Boosting, and CatBoost with Balancing and Hyperparameter Tuning for Hypertension Risk Prediction on Clinical Dataset Murtiningsih, Dewi Ayu; Sari, Bety Wulan; Fajri, Ika Nur
Journal of Applied Informatics and Computing Vol. 9 No. 5 (2025): October 2025
Publisher : Politeknik Negeri Batam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30871/jaic.v9i5.10400

Hypertension is a long-lasting condition that is highly prevalent and significantly contributes to cardiovascular issues, making early identification a crucial preventive action. This research evaluates the efficacy of three boosting algorithms, eXtreme Gradient Boosting (XGBoost), Light Gradient Boosting Machine (LGBM), and CatBoost in forecasting hypertension risk. A publicly accessible dataset consisting of 4,363 samples was employed, followed by data preprocessing, feature selection through a voting method that integrates Boruta, Recursive Feature Elimination (RFE), and SelectKBest, as well as addressing class imbalance using the Synthetic Minority Over-sampling Technique (SMOTE) and ADASYN (Adaptive Synthetic Sampling Approach). The models were additionally fine-tuned through hyperparameter optimization using GridSearchCV and Repeated Stratified K-Fold Cross Validation. The evaluation results demonstrate that all three algorithms exhibited strong predictive capabilities, with CatBoost leading the way, achieving an accuracy of 0.992, precision of 0.992, recall of 0.992, F1-score of 0.992, and ROC-AUC of 0.9987. Analyzing the confusion matrix further validated that CatBoost had the lowest number of misclassifications when compared to XGBoost and LGBM. Additionally, the use of SHapley Additive exPlanations (SHAP) for model interpretability highlighted that the key factors influencing the prediction of hypertension risk are blood pressure, body mass index (BMI), overall physical activity, waist circumference, triglyceride levels, age, and LDL cholesterol levels, aligning with established medical knowledge. To facilitate real-world use, the top-performing model was implemented into a user-friendly website interface, allowing users to predict their hypertension risk interactively. These findings illustrate that boosting algorithms, especially CatBoost, offer an accurate, dependable, and interpretable machine learning method for creating hypertension risk prediction systems.

Sentiment Analysis of the Film "JUMBO" on Twitter Using the Naive Bayes Method and Support Vector Machine (SVM) with a Text Mining Approach Widodo, Tegar Robi; Fajri, Ika Nur; Sari, Bety Wulan
Journal of Applied Informatics and Computing Vol. 9 No. 5 (2025): October 2025
Publisher : Politeknik Negeri Batam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30871/jaic.v9i5.10557

This study aims to perform sentiment analysis on reviews of the film “JUMBO” collected from the Twitter platform, using the Naive Bayes and Support Vector Machine (SVM) methods. The data were gathered through a crawling process on Twitter, yielding 2,011 tweets, which were then processed through several pre-processing steps, including case folding, cleaning, normalization, tokenization, stopword removal, and stemming. Subsequently, the data were transformed into numerical representations using TF-IDF, followed by sentiment labeling into positive, negative, and neutral categories. For the Naive Bayes method, training and evaluation were conducted using 5-fold Cross Validation. The results showed that the Naive Bayes model achieved an accuracy of 80.60%, precision of 73.83%, recall of 73.50%, and an F1-score of 69.98%. Meanwhile, the SVM method obtained an accuracy of 75.87%, precision of 76.36%, recall of 62.45%, and an F1-score of 65.64%. Compared to the baseline random classifier, which only achieved an accuracy of 32.47%, both primary methods significantly outperformed it in classifying film review sentiments. The analysis also indicates that the F1-score is lower than the accuracy due to the imbalanced data distribution, with a considerably higher number of positive reviews. This study also presents visualizations of sentiment distribution and word clouds to provide a clearer understanding of audience opinions. The results demonstrate that the Naive Bayes method performs well and has potential for use in sentiment analysis of films on social media platforms. These findings are expected to provide valuable insights for the creative industry, particularly in evaluating audience responses and improving the quality of future film productions.

Title

Found 6 Documents
Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title Search

Found 6 Documents Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title

Found 6 Documents
Search