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 926 Documents
 65   66   67   68   69 
Spatio-temporal COVID-19 Spread Prediction: Comparing SVM with Time-Expanded Features and RNN Models Gusti Aji, Raden Aria; Prasetiyowati, Sri Suryani; Sibaroni, Yuliant
Building of Informatics, Technology and Science (BITS) Vol 6 No 4 (2025): March 2025
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v6i4.6548

Abstract

Covid-19 which spread in early 2020, still needs to be observed, considering the high growth rate of the pandemic at that time. The right prediction model is needed, because it can estimate the speed and extent of its spread for some time to come. This study develops a prediction model for the classification of the spread of Covid-19 in the future using SVM with time-based feature expansion and RNN. The scenario developed to determine the effect of time-based feature expansion and kernel function on classification performance using time series and spatial data. The results obtained show that SVM with time-based feature expansion achieves the most optimal performance using a polynomial kernel with an accuracy of 96.23%, a precision of 96.48%, a recall of 96.23%, and an F1-score of 96.21%. The performance of the SVM is superior to RNN which achieves an accuracy of 93.55%, a precision of 87.51%, a recall of 93.55%, and an F1-score of 90.43. Spatial prediction using Kriging interpolation can provide an overview of the spread of COVID-19 in all villages in Bandung City. The contribution of this research can provide much-needed information for policy makers and the community in managing future pandemic predictions and management strategies in the field of public health.
Analisis Loyalitas Pelanggan Berdasarkan Model LRFM Menggunakan Metode K-Means Putri, Runi Aulia; Jazman, Muhammad; Syaifullah, Syaifullah; Rahmawita, Medyantiwi
Building of Informatics, Technology and Science (BITS) Vol 6 No 4 (2025): March 2025
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v6i4.6565

Abstract

In the era of intense competition in the beauty industry, it is important for companies to understand customer behavior and identify loyal customer segments. Ths study aims to analyze customer loyalty at the Lanona Skincare Beauty clinic using the LRFM (Length, Recency, Frequency, Monetary) model with the K-Means Clustering method. Beauty clinics have not implemented CRM as part of theur business strategy. There is ineffective marketing strategies. Customer transaction data from April to October 2023 was collected and analyzed to determine customer value based on LRFM parameters. The analysis results show that K-Means is effetive in grouping cutomers until the best three clusters are obtained. Cluster 1 with a results of 0,620 is the most loyal customers, cluster 2 with a results of 0,100 is grouped into new inactive customers and cluster 3 with a results of 0,353 is high frequency customers but low revenue contribution. The proposed marketing strategies for each cluster include rewarding an improving communication to maintain customers loyalty. This research provides valuable insights for Lanona Skincare Beauty Clinic in creating a more focused and succesfull marketing plan to increase customer happiness and loyalty.
Analisis Sentimen Pada Ulasan Aplikasi Bank Syariah Indonesia Mobile Menggunakan Support Vector Machine dan Naïve Bayes Aqilla, Nabila Fadia; Jazman, Muhammad; Syaifullah, Syaifullah; Rahmawita, Medyantiwi
Building of Informatics, Technology and Science (BITS) Vol 6 No 4 (2025): March 2025
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v6i4.6567

Abstract

The internet plays a crucial role in facilitating various human activities, including in the field of electronic banking services, which encompasses various financial services such as ATMs, internet banking, SMS banking, and mobile banking. All of these aim to enhance service quality with a focus on security, convenience, and effectiveness. BSI is one of the banks offering mobile banking services. Based on user reviews, the BSI Mobile app often experiences technical issues such as bugs and transaction failures. To assess the level of satisfaction with the app, the researcher uses sentiment analysis methods. This method also helps potential customers identify aspects that need improvement or development in the products and services to enhance their quality. The study employs Support Vector Machine (SVM) and Naïve Bayes algorithms. The test results show that the Naïve Bayes algorithm achieves an accuracy of 74.37%, recall of 74.37%, precision of 75.46%, and an F1-score of 74.5%. Meanwhile, the SVM algorithm achieves an accuracy of 77.39%, precision of 77.8%, recall of 77.39%, and an F1-score of 77.38%. These findings indicate that SVM performs better in sentiment classification tasks compared to Naïve Bayes. With its superior performance, SVM is the more suitable algorithm for analyzing user perceptions of the BSI Mobile app. Therefore, the findings of this study can contribute to the development of more innovative digital service strategies and enhance competitiveness in the digital era.
Perbandingan Kinerja Algoritma Random Forest, KNN, dan SVM dalam Analisis Sentimen Cryptocurrency AndaruJaya, Rinaldi Sukma; Suryono, Ryan Randy
Building of Informatics, Technology and Science (BITS) Vol 6 No 4 (2025): March 2025
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v6i4.6572

Abstract

Cryptocurrency is a digital money based on blockchain technology that offers security and transparency in transactions, so it has increasingly attracted the attention of the public, including in Indonesia. With the number of investors surpassing 20 million, cryptocurrencies have generated a variety of opinions on social media. Some see it as a promising modern investment opportunity, while others highlight the risks of price fluctuations, security, and unclear regulations. To understand public sentiment towards cryptocurrencies, machine learning-based sentiment analysis is a relevant solution. This research compares the performance of three popular algorithms, namely Random Forest, K-Nearest Neighbors (KNN), and Support Vector Machine (SVM), in sentiment analysis of public opinion. These three algorithms have different advantages and disadvantages, depending on the characteristics of the data and the purpose of the analysis. Random Forest is known to be stable but requires high computation, KNN is easy to apply but less reliable on high-dimensional data, and SVM excels at separating complex data but requires careful parameter tuning. Previous research has shown differences in the accuracy of these three algorithms on various datasets, so further evaluation is needed to determine the most effective algorithm. The results of this study are expected to provide guidance in choosing the right algorithm for sentiment analysis, especially on cryptocurrency-related opinion data, as well as expand the understanding of the application of algorithms on dynamic and complex data.
Analisis Sentimen Acara Clash of Champions dengan Algoritma Naïve Bayes dan Support Vector Machine Purnama, Putri Intan; Suryono, Ryan Randy
Building of Informatics, Technology and Science (BITS) Vol 6 No 4 (2025): March 2025
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v6i4.6575

Abstract

With the advancement of information and communication technology, it has become easier for people to exchange information and access educational content, including through online learning platforms such as Ruangguru. One of Ruangguru's flagship programs is Clash of Champions, which attracts public attention and generates various sentiments on social media. However, analyzing public sentiment towards this program faces challenges, especially due to the imbalance in the amount of data between majority and minority sentiments, which may affect the accuracy of sentiment analysis models. This study aims to compare the performance of two algorithms, namely Naïve Bayes and Support Vector Machine (SVM), in analyzing public sentiment towards this program. Using 5,226 tweets from social media X, the data was balanced using the Synthetic Minority Oversampling Technique (SMOTE) method to overcome the data imbalance problem. After the data was divided into 80% for training and 20% for testing, the results showed that before using SMOTE, Naïve Bayes had an accuracy of 78%, while SVM reached 82%. After SMOTE was applied, Naïve Bayes' accuracy increased to 79%, while SVM rose to 84%. In addition to accuracy, significant improvements were also seen in precision, recall, and f1-score, especially for positive sentiments. The results show that SVM is superior to Naïve Bayes, both in accuracy and other evaluation metrics. This research provides an in-depth understanding of the effectiveness of algorithms in sentiment analysis on entertainment-based educational programs and is expected to be a reference for the development of similar models in the future.
Pemantauan Cerdas Berbasis IoT pada Kualitas Air Hidroponik untuk Optimalisasi Pertanian Presisi Ade Kusuma, Muhammad Wira; Ahsyar, Tengku Kharil; Saputra, Eki; Megawati, Megawati
Building of Informatics, Technology and Science (BITS) Vol 6 No 4 (2025): March 2025
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v6i4.6589

Abstract

This study introduces an IoT-based hydroponic water quality monitoring system designed to enhance the efficiency, reliability, and accessibility of hydroponic environment management. The system monitors four key parameters: pH, temperature, Total Dissolved Solids (TDS), and water level, using sensors connected to an ESP8266 microcontroller. Data is transmitted in real-time via the MQTT protocol, processed through the Node-RED middleware, and stored in a MariaDB database. Interactive web-based data visualization supports data-driven decision-making and simplifies user monitoring of system conditions. Agile methodology and DevOps were implemented to ensure iterative system development, responsiveness to changes, and continuous updates via Continuous Integration/Continuous Deployment (CI/CD). Field tests conducted in a greenhouse environment demonstrated that the system could improve operational efficiency and sustainability, while also being flexible enough to adapt to various types of plants. The User Acceptance Test (UAT) yielded an average score of 4.8 out of 5, indicating high user satisfaction with the system's functionality and interface. This study also identifies future development opportunities, including the integration of additional sensors, automated control mechanisms, and predictive analytics powered by machine learning to optimize crop yields and management efficiency. With its innovative approach, this research not only advances IoT-based hydroponic technology but also makes a significant contribution to developing resilient, scalable, and efficient smart farming solutions.
A Optimizing Word2Vec Dimensions for Sentiment Analysis of Photomath Reviews using Random Forest and SVM Varissa Azis, Diva Azty; Sibaroni, Yuliant
Building of Informatics, Technology and Science (BITS) Vol 6 No 4 (2025): March 2025
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v6i4.6616

Abstract

Technology in the Industrial Revolution 4.0 era supports modern learning through apps like Photomath, simplifying math problem-solving for users. However, diverse user reviews highlight the need for sentiment analysis to evaluate app quality. This research analyzes 9,059 reviews of Photomath collected from the Google Play Store using Python. Word2Vec is used in the study to compare Random Forest and Support Vector Machine (SVM) classifiers for feature extraction. To ensure clean and consistent data, preprocessing techniques such as stemming, tokenization, and stopword removal were used. Text with rich semantic aspects was mathematically represented using Word2Vec. The findings show that SVM using an RBF kernel performed better than Random Forest, with an F1-score of 88.5%, 88.5% accuracy, 88.7% precision, and 88.5% recall. Performance was effectively improved by combining 300-dimensional Word2Vec with stemming algorithms. While Random Forest achieved slightly lower accuracy, it shows promise for specific use cases. This study offers practical insights for improving Photomath by tailoring updates based on user sentiment. The findings emphasize the importance of preprocessing, dimensional optimization, and classifier selection in developing accurate sentiment analysis models. Limitations include the dataset size and the use of classical machine learning models. Future research could address these by exploring larger datasets or deep learning techniques to further improve performance.
Analisis Sentimen Terhadap Ulasan Aplikasi Disney+ Hotstar Pada Google Playstore Menggunakan Metode Naïve Bayes Arsad, Reza Al; Erizal, Erizal
Building of Informatics, Technology and Science (BITS) Vol 6 No 4 (2025): March 2025
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v6i4.6641

Abstract

Technology in Indonesia has advanced rapidly, making many changes in all aspects of life, one of which is the online streaming aspect, namely the Disney+ Hotstar application. Now Disney+ Hotstar is available on tablets, smart TVs, computers, and smartphones accessed from various places and times. Disney+ Hotstar has thousands of hours of various Pixar, Marvel films, as well as exclusive Indonesian and various countries' series. Although Disney+ Hotstar has a variety of interesting films and features, it does not guarantee that users are satisfied using the application. Because users have different opinions and assessments, this point can be seen from user reviews available on the Google Playstore. The main purpose of this study was to determine the assessment or sentiment of user reviews of the Disney+ Hotstar application by analyzing it. The technique used uses the Naive Bayes algorithm. A total of 1000 review data were obtained on December 28, 2024 from the Google Playstore via Google Colab, then processed using RapidMiner. The dataset went through the cleaning and preprocessing stages to become 873 review data. There were 128 good reviews and 745 bad reviews. TF-IDF weighting was performed before classification using 873 datasets. The classification stage used a cross-validation system and applied the Naive Bayes approach. Testing from this study revealed the accuracy results of the Naive Bayes algorithm of 76.06%, precision of 34.12%, and recall of 67.97%.
Penerapan Logits Processing Pada Teknologi Transformer untuk Penciptaan Melodi Berbentuk Notasi ABC dalam Pengembangan Game Indie Dhiaulhaq, Muhammad Faishal Ali; Huda, Arif Akbarul; Hadinegoro, Arifiyanto
Building of Informatics, Technology and Science (BITS) Vol 6 No 4 (2025): March 2025
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v6i4.6642

Abstract

Generative Artificial Intelligence (Gen AI) technology is increasingly being used by creative professionals, including musicians and game developers. Many game developers now turn to open or paid music assets, but the variety of options is usually quite limited. This research aims to assist game developers in generating music assets in ABC notation format. The research methods include data collection in the form of ABC notation, data processing, model development, and metric evaluation. The data was collected by extracting ABC notation along with the characteristic musical components of each item. Data processing involved handling missing values and feature selection, while data preparation included labeling and tokenization. The model used was GPT-2 based on the Transformer architecture, pretrained on a general dataset. Integration of the model with ABC notation data was enhanced using Logits Processing to improve output control. The evaluation results show that Transformer technology can generate pitch patterns consistent with the validation data, with the EMD values concentrated in the range of 1.0–1.5 and an average of 1.60. Although there are some outliers and differences in pitch distribution between the validation data and generated results, the Horror genre with a Joyful mood and Excitement emotion achieved the highest combined fitness score of 0.528. The model still requires further refinement to produce more consistent pitch distributions. This research demonstrates the potential of Transformer technology in generating music assets for games, but further studies are needed to improve accuracy and consistency in the results.
Comparison of Random Forest and Decision Tree for Depression Detection Using Interaction Patterns Fathin, Felicia Talitha; Maharani, Warih
Building of Informatics, Technology and Science (BITS) Vol 6 No 4 (2025): March 2025
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v6i4.6660

Abstract

This research focuses on evaluating the efficacy of Random Forest and Decision Tree, in detecting depression on tweets and interaction patterns on X social media. Depression as a global health problem often happens because of individuals' online behavior. This study uses data from X social media users in Indonesia who have filled out the DASS-42 questionnaire with an analysis approach that includes crawling data that includes tweets and interactions on X. The purpose of this research is to more accurately and comprehensively identify signs of depression by analyzing the interaction patterns of users on social media platforms through the integration of of several many methods for feature extraction and preprocessing situations.The methods used include data preprocessing, feature combination using TF-IDF, Bag of Words, and Word2Vec and model evaluation utilizing metrics such as Precision, Recall, Accuracy, and F1-score. The findings of this research show that Random Forest performs better than Decision Tree, with a combination of TF-IDF, BoW, Word2Vec and TF-IDF, Word2Vec features obtained an accuracy of 0.60. Although Random Forest is superior, both models are difficult to identify the positive class of depression which can be seen from the relatively low F1-score and recall values. Other factors affecting model performance include lack of data relevance, low interaction rate, and limited feature extraction.

Page 67 of 93 | Total Record : 926

 65   66   67   68   69 

Filter by Year

2019 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