cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Mesran
Contact Email
mesran.skom.mkom@gmail.com
Phone
-
Journal Mail Official
jurnal.bits@gmail.com
Editorial Address
-
Location
Kota medan,
Sumatera utara
INDONESIA
Building of Informatics, Technology and Science
Published by Forum Kerjasama Pendidikan TInggi
ISSN : 26848910     EISSN : 26853310     DOI : -
Core Subject : Science,
Computer Science & IT
Building of Informatics, Technology and Science (BITS) is an open access media in publishing scientific articles that contain the results of research in information technology and computers. Paper that enters this journal will be checked for plagiarism and peer-rewiew first to maintain its quality. This journal is managed by Forum Kerjasama Pendidikan Tinggi (FKPT) published 2 times a year in Juni and Desember. The existence of this journal is expected to develop research and make a real contribution in improving research resources in the field of information technology and computers.
Arjuna Subject : -
Articles 56 Documents
 1   2   3   4   5 
Search results for , issue "Vol 7 No 2 (2025): September 2025" : 56 Documents clear
Perbandingan Algoritma SVM, Random Forest, dan Naive Bayes Terhadap Kasus Scam di Media Sosial Twitter Saputra, Rizky Herdian; Suryono, Ryan Randy
Building of Informatics, Technology and Science (BITS) Vol 7 No 2 (2025): September 2025
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v7i2.7236

Abstract

The rapid growth of information and communication technology has a significant impact on the level of cybercrime. The internet, which was originally used to expedite the exchange of information, is also misused by irresponsible parties. One of the prevalent forms of crime is scams, which are fraudulent activities aimed at gaining unlawful profits by exploiting victims through various tactics. The purpose of this research is to evaluate and compare the performance of three algorithms: Support Vector Machine (SVM), Random Forest, and Naive Bayes in analyzing public sentiment regarding scam cases on social media Twitter. The dataset consists of 9,132 tweets, which undergo preprocessing stages such as cleaning, case folding, and word normalization, leaving 8,879 tweets for analysis. Then, the Synthetic Minority Over-sampling Technique (SMOTE) is applied, with the dataset divided into 80% for training and 20% for testing. The results show that before applying SMOTE, the SVM algorithm achieved the highest accuracy at 82%, followed by Random Forest at 79%, and Naive Bayes at 74%. After applying SMOTE, accuracy significantly increased, with SVM reaching 88%, Random Forest at 84%, and Naive Bayes at 76%. This demonstrates that in sentiment analysis of scam cases, the SVM method achieves higher accuracy than both Random Forest and Naive Bayes.
Analisis Sentimen Masyarakat Menggunakan Algoritma Long Short Term Memory (LSTM) Pada Ulasan Aplikasi Halodoc Yulianti, Nelvi; Afdal, M; Jazman, Muhammad; Megawati, Megawati; Anofrizen, Anofrizen
Building of Informatics, Technology and Science (BITS) Vol 7 No 2 (2025): September 2025
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v7i2.7243

Abstract

Halodoc is a digital healthcare platform that provides users with convenient access to medical services online. This study aims to analyze public sentiment toward the Halodoc application based on 1,416 user reviews collected during the period from July to September 2024. The reviews are categorized into three sentiment classes: positive, negative, and neutral, using the Long Short-Term Memory (LSTM) algorithm. Prior to classification, the Word2Vec technique is applied to transform the words in the reviews into numerical vector representations for processing by the model. The analysis revealed that a portion of the reviews expressed negative sentiments, mainly concerning delays in medication delivery and slow responses from customer service. Model performance evaluation shows that the implementation of the LSTM algorithm optimized with the Adam (Adaptive Moment Estimation) optimizer and a dropout rate of 0.2 achieved the highest accuracy of 89.40% and an F1-score of 88.63%. These results indicate that the model performs very well in classifying sentiments and can be used as a useful tool for understanding user satisfaction with the Halodoc application.
Analisis Sentimen Publik Terhadap Danantara di Media Sosial X Menggunakan Naïve Bayes dan Support Vector Machine Firmanda, Fabian; Suryono, Ryan Randy
Building of Informatics, Technology and Science (BITS) Vol 7 No 2 (2025): September 2025
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v7i2.7250

Abstract

Danantara a state-owned investment management institution, has become a topic of widespread public discussion, particularly on social media platform X, where diverse public opinions are expressed. This study aims to evaluate public sentiment toward Danantara through sentiment analysis using machine learning techniques. The dataset consists of 10,108 tweets, of which 9,790 tweets remained after the preprocessing stage and were ready for analysis. The methodology involves word weighting using Term Frequency-Inverse Document Frequency (TF-IDF) and the implementation of two classification algorithms: Naïve Bayes and Support Vector Machine (SVM). To address the class imbalance in sentiment data, the Synthetic Minority Over-sampling Technique (SMOTE) was applied. Model performance was evaluated using metrics such as accuracy, precision, recall, and F1-score. Initial results show that before applying SMOTE, the Naïve Bayes algorithm achieved an accuracy of 64%, while SVM performed better with an accuracy of 80%. After applying SMOTE, Naïve Bayes accuracy improved to 72%, and SVM increased significantly to 89%. These results indicate that SMOTE is effective in handling data imbalance and enhancing classification performance. Overall, this study provides a clearer picture of public opinion toward Danantara and demonstrates that the combination of preprocessing, TF-IDF, machine learning algorithms, and data balancing techniques can produce more accurate sentiment analysis.
Penerapan Support Vector Machine untuk Analisis Sentimen Pengguna X terhadap IndiHome, Biznet, dan Starlink Alfian, Zhevin; Afdal, M; Novita, Rice; Zarnelly, Zarnelly
Building of Informatics, Technology and Science (BITS) Vol 7 No 2 (2025): September 2025
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v7i2.7429

Abstract

This study aims to analyze user sentiment on the social media platform X toward three major internet service providers in Indonesia, IndiHome, Biznet, and Starlink. The analysis focuses on five key variables: internet speed, network stability, pricing and service packages, customer service quality, and coverage availability. A total of 4,500 data points were collected through data crawling, then processed using text mining techniques and the Support Vector Machine (SVM) algorithm, with data imbalance addressed through the Random Oversampling method. Evaluation results show that IndiHome consistently demonstrated the best performance, achieving an accuracy of up to 90% in the customer service quality variable, and an overall average accuracy above 85% across all variables. Biznet generally ranked second, with accuracy ranging from 63% to 80%. Starlink placed lowest overall, although it still recorded competitive results, such as 82% accuracy in the internet speed variable. The application of Random Oversampling improved the model’s classification accuracy by an average of 6–12% compared to the non-oversampling model. This study offers strategic insights into public perception of internet services and can serve as a reference for improving service quality based on data-driven user feedback.
Analisis Sentimen Masyarakat Terhadap Kebijakan Ekspor Pasir Laut Berdasarkan Ulasan Twitter Menggunakan Algoritma Naive Bayes dan Support Vector Machine Zarqani, Zarqani; Afdal, M; Novita, Rice; Megawati, Megawati
Building of Informatics, Technology and Science (BITS) Vol 7 No 2 (2025): September 2025
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v7i1.7431

Abstract

The export of sea sand has been banned since 2003 through a Decree of the Minister of Industry and Trade. However, on May 15, 2023, President Joko Widodo once again allowed the export of sea sand through Government Regulation No. 26 of 2023. This policy sparked controversy and went viral on social media, including on Twitter. This study aims to analyze public sentiment toward the policy based on reviews on Twitter using the Naïve Bayes and Support Vector Machine (SVM) algorithms. Data was collected through crawling techniques, then processed using text preprocessing methods, word weighting using TF-IDF, and random oversampling to balance the data. The data was then categorized into four thematic variables—economy, environment, social, and geological policy—to examine a more focused distribution of sentiment. Analysis of 2,765 data points revealed that the majority of sentiment was negative (55%), indicating public opposition to the sea sand export policy, followed by neutral sentiment (30%) and positive sentiment (15%). Performance evaluation shows that SVM excels in the Economy category with nearly 95% accuracy, while in other categories the difference with Naïve Bayes is relatively small. This study is expected to provide insights into the Indonesian public's perception of the sea sand export policy and its implications across various sectors.
Analisis Sentimen Terhadap Pemain Naturalisasi dan Lokal Tim Nasional Sepakbola Indonesia Menggunakan Support Vector Machine Arrazak, Fadlan; Afdal, M; Novita, Rice; Megawati, Megawati
Building of Informatics, Technology and Science (BITS) Vol 7 No 2 (2025): September 2025
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v7i2.7471

Abstract

The inclusion of naturalized players in Indonesia's national football team has sparked diverse public reactions, particularly on social media platforms like Twitter. This study aims to compare public opinion toward naturalized and local players through sentiment analysis. A total of 2,342 tweets were categorized into three sentiment classes: positive, neutral, and negative. Naturalized players received a higher number of positive sentiments, totaling 809, compared to 333 negative and 231 neutral sentiments. In contrast, local players gained 465 positive sentiments, 317 negative, and 187 neutral, indicating a generally more favorable perception of naturalized players among the public. Further analysis was conducted using the Support Vector Machine (SVM) classification algorithm along with the SMOTE technique for data balancing, focusing on five key aspects: performance, experience, physical condition, adaptability, and communication. The classification results showed that naturalized players outperformed in physical condition with an accuracy of 96 percent, followed by performance and adaptability, each at 90 percent. On the other hand, local players showed superiority only in communication with an accuracy of 92 percent. In terms of precision and recall, naturalized players again led in physical condition, achieving 97 percent precision and 96 percent recall, while local players excelled in communication with both precision and recall at 92 percent. These findings offer valuable insights for policymakers and football organizations in formulating more effective naturalization strategies.
Analisis Sentimen Masyarakat Terhadap Kebocoran Pusat Data Nasional Sementara Menggunakan Algoritma Random Forest dan Support Vector Machine Basri, Faishal Khairi; Afdal, M; Angraini, Angraini; Rozanda, Nesdi Evrilyan
Building of Informatics, Technology and Science (BITS) Vol 7 No 2 (2025): September 2025
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v7i2.7473

Abstract

A ransomware attack on Indonesia’s Temporary National Data Center (PDNS) in June 2024 triggered major public concern over data security and government preparedness. This study aims to analyze public sentiment toward the incident using an Aspect-Based Sentiment Analysis approach on 2,700 Indonesian-language tweets collected from the X platform. The research follows the SEMMA (Sample, Explore, Modify, Model, Assess) methodology, involving text preprocessing, aspect extraction using part-of-speech tagging and named entity recognition, feature representation using Term Frequency-Inverse Document Frequency, and aspect refinement through semantic coherence. Extracted aspects are grouped into five categories: data security, institutions, infrastructure, politics and economy, and impact. Sentiment classification is carried out using the IndoBERTweet model. Results indicate a strong dominance of negative sentiment, particularly in the infrastructure and institutional categories, with no positive sentiment recorded in the political and economic aspect. To address class imbalance in sentiment distribution, the Synthetic Minority Oversampling Technique is applied during model training. Performance evaluation of two algorithms—Random Forest and Support Vector Machine—shows that Random Forest performs best, achieving 96% accuracy on a 70:30 data split and 99.05% average accuracy using 10-fold cross-validation. These findings highlight the effectiveness of aspect-based sentiment analysis and demonstrate Random Forest's superiority in handling imbalanced sentiment classification tasks.
Comparison of RoBERTa and IndoBERT on Multi-Aspect Sentiment Analysis of Indonesian Hotel Reviews with Tuning Optimization Syarif, Rizky Ahsan; Sibaroni, Yuliant
Building of Informatics, Technology and Science (BITS) Vol 7 No 2 (2025): September 2025
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v7i2.7523

Abstract

The hospitality industry heavily relies on online reviews as a crucial source of information that influences potential guests' decisions. However, conducting sentiment analysis on hotel reviews can be challenging due to the complexity of language and contextual diversity, especially in Indonesian. This study aims to develop and optimize a RoBERTa-based sentiment analysis model to improve the accuracy of sentiment classification in Indonesian hotel reviews, focusing on the aspects of facilities, cleanliness, location, price, and service. The methodology includes data collection through web scraping from the Traveloka platform, manual labeling, and text pre-processing. The RoBERTa model was trained and optimized using fine-tuning techniques and evaluated using metrics such as accuracy, precision, recall, F1-score, and AUC. The results show that the optimized RoBERTa model achieves competitive performance, although the IndoBERT model with Bayesian Optimization demonstrates superior performance, particularly in terms of accuracy and efficiency in identifying positive and negative sentiments. This study is expected to contribute to the development of more effective and accurate aspect-based sentiment analysis (ABSA) for Indonesian-language hotel reviews. It also opens opportunities for applying NLP technology in the hospitality industry and across other review platforms, thereby improving sentiment analysis quality and assisting hotel managers in enhancing service and customer experience.
Milk Production Estimation Model for Cattle Based on Image Processing using Random Forest, XGBoost, and LightGBM Niswati, Za'imatun; Nurdiati, Sri; Buono, Agus; Sumantri, Cece
Building of Informatics, Technology and Science (BITS) Vol 7 No 2 (2025): September 2025
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v7i2.7585

Abstract

Milk is a livestock product consumed by individuals of all ages. Therefore, it is essential to increase milk production in Indonesia to meet domestic demand. The growth of dairy cattle populations and milk production has not been able to keep up with rising consumption, resulting in a reliance on imports for most dairy products and their derivatives, with imports steadily increasing over the years. Therefore, alternative solutions are needed to enhance the milk production. One approach is to develop a milk production estimation model to determine the optimal number of dairy cattle to be cultivated by farmers and livestock companies to meet domestic demand. The objective of this study was to create a dairy milk production estimation model through image analysis using the Random Forest, XGBoost, and LightGBM algorithms. The milk production estimation model used in this study used CLAHE for contrast enhancement and VGG-16 for feature extraction. The results showed that XGBoost provided the best performance, explaining 74% of the data variation in the Y variable with a relatively small estimation error of 0.92. After parameter tuning using Grid Search, an improvement was observed, where XGBoost explained 86% of the data variation in the Y variable, and the estimation error decreased to 0.72. Image processing and machine learning technologies are part of precision agriculture that aims to improve the efficiency, productivity, and sustainability of livestock operations.
Analisis Perbandingan Algoritma Random Forest dan K-Nearest Neighbors pada Klasifikasi Tingkat Stres Pekerja Manurung, Syalom Kristian; Pratama, Irfan
Building of Informatics, Technology and Science (BITS) Vol 7 No 2 (2025): September 2025
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v7i2.7589

Abstract

Work stress has become a prominent concern in the modern professional landscape, as it can lead to reduced productivity, diminished work quality, and decreased mental well-being among employees. This study aims to evaluate and compare the performance of two machine learning algorithms, namely Random Forest and K-Nearest Neighbors (KNN), in classifying levels of work stress. The data were obtained through an online questionnaire completed by 212 respondents from various employment sectors in Indonesia. The responses were converted from Likert scale to numerical values, grouped using the K-Means clustering method, and categorized into five levels of stress, ranging from no stress to very high stress. To address data imbalance, the Synthetic Minority Over-sampling Technique (SMOTE) was applied. The modeling process was conducted using three different data split scenarios, namely 90:10, 80:20, and 70:30, and evaluated using metrics such as accuracy, precision, recall, f1-score, and cross-validation. The findings indicate that the Random Forest algorithm consistently outperformed KNN across all scenarios. After applying SMOTE, both algorithms showed improved performance, with the Balanced Random Forest model achieving the highest accuracy and f1-score of 92 percent in the 70:30 scenario. These results suggest that combining Random Forest with SMOTE offers an effective and reliable solution for classifying work stress levels and could be developed as an objective and efficient early detection system.

Page 1 of 6 | Total Record : 56

 1   2   3   4   5 

Filter by Year

2025 2025


Reset
Filter By Issues
All Issue Vol 7 No 3 (2025): December 2025 Vol 7 No 2 (2025): September 2025 Vol 7 No 1 (2025): June (2025) Vol 6 No 4 (2025): March 2025 Vol 6 No 3 (2024): December 2024 Vol 6 No 2 (2024): September 2024 Vol 6 No 1 (2024): June 2024 Vol 5 No 4 (2024): March 2024 Vol 5 No 3 (2023): December 2023 Vol 5 No 2 (2023): September 2023 Vol 5 No 1 (2023): June 2023 Vol 4 No 4 (2023): March 2023 Vol 4 No 3 (2022): December 2022 Vol 4 No 2 (2022): September 2022 Vol 4 No 1 (2022): June 2022 Vol 3 No 4 (2022): March 2022 Vol 3 No 3 (2021): December 2021 Vol 3 No 2 (2021): September 2021 Vol 3 No 1 (2021): June 2021 Vol 2 No 2 (2020): December 2020 Vol 2 No 1 (2020): June 2020 Vol 1 No 2 (2019): December 2019 Vol 1 No 1 (2019): June 2019 Vol 1 No 1 (2019): Edisi Juni More Issue