cover
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
ISSN : 26848910     EISSN : 26853310     DOI : -
Core Subject : Science,
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 777 Documents
Perbandingan Algoritma LSTM, BI-LSTM, dan CNN untuk Klasifikasi Komentar Masyarakat: Pembangkitan Serigala Direwolf pada Media X Novriyandi, Agung; Hendrasuty, Nirwana
Building of Informatics, Technology and Science (BITS) Vol 7 No 1 (2025): June (2025)
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v7i1.7398

Abstract

The resurrection of the Direwolf by Colossal Biosciences, a biotechnology company based in Dallas, Texas, USA, through cloning and gene editing technology has sparked widespread debate and discussion in society. Cloning is the process of creating a genetically identical copy of an organism, and in this context, it is used to bring back the Direwolf, a species that has been extinct for around 12,500 years. This study aims to compare the performance of Long Short-Term Memory (LSTM), Bidirectional LSTM (BI-LSTM), and Convolutional Neural Network (CNN) algorithms in classifying public comments related to the resurrection of the Direwolf on Media X. Using a dataset of 3400 comments, after undergoing cleaning and preprocessing to eliminate noise and improve data quality, 1424 valid comments were obtained, consisting of 869 negative, 270 positive, and 285 neutral comments. This study will evaluate the performance of the three algorithms based on metrics such as accuracy, precision, and recall. The evaluation results show that the LSTM model has the highest accuracy at 73%, followed by BI-LSTM at 70%, and CNN at 66%. Based on these results, the LSTM approach can be considered a better approach in classifying public comments related to the topic of Direwolf resurrection. The results of this study are expected to provide useful information for the development of sentiment analysis systems and understanding public opinion related to cloning and gene editing technology.
Landscape of AHP Integration in Decision Support Systems: A Bibliometric Analysis of Scopus Publications Saputra, Imam; Mesran, Mesran; Utomo, Dito Putro; Siregar, Annisa Fadillah
Building of Informatics, Technology and Science (BITS) Vol 7 No 1 (2025): June (2025)
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v7i1.7451

Abstract

This study employs bibliometric analysis to provide a comprehensive overview of the research landscape concerning the integration of the Analytic Hierarchy Process (AHP) and Decision Support Systems (DSS). Utilizing 1770 documents retrieved from the Scopus database (1985-2025) and employing Biblioshiny for analysis, this research examines publication trends, citation patterns, keyword co-occurrence, collaboration networks, and thematic evolution within the field. The findings reveal a significant growth in publications, particularly after 2015, highlighting the increasing scholarly interest. Citation analysis identifies influential works and key contributing countries. Keyword analysis underscores "decision support systems," "analytic hierarchy process," and "decision making" as central themes, with emerging interest in areas like "artificial intelligence." Collaboration network analysis illustrates significant co-authorship patterns and international collaborations. Thematic mapping further categorizes research themes, identifying well-established "Motor Themes" (e.g., "decision support system," "GIS") and fundamental "Basic Themes" (e.g., "decision making," "analytic hierarchy process"). This study provides valuable insights into the intellectual structure, evolutionary trends, and collaborative dynamics of the AHP-DSS integration research field, highlighting its robust nature and potential future directions.
Implementasi Metode MAUT dalam Analisis Penentuan Tenaga Pengajar Non ASN Terbaik Maulana, Imam; Irmayani, Deci; Suryadi, Sudi
Building of Informatics, Technology and Science (BITS) Vol 7 No 1 (2025): June (2025)
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v7i1.7460

Abstract

The need for quality teaching staff is becoming increasingly important along with the development of technology and globalization, including in educational institutions such as SDN 115467 Kanopan Ulu. In addition to teaching staff from ASN, this school also relies on non-ASN staff who play a significant role in supporting the quality of education. However, the process of determining the best non-ASN teaching staff is often faced with the challenges of subjectivity and differences in assessment standards. To overcome this, this study proposes the implementation of a Decision Support System (DSS) based on the Multi Attribute Utility Theory (MAUT) method. The MAUT method allows for more objective, transparent, and fair decision-making by considering various assessment criteria, such as competence, experience, and contribution of teaching staff. In this study, non-ASN teaching staff data were analyzed using the Microsoft Excel application and DSS software during the research period in October 2024. Based on the application of this method, Tuti Alawiyah (A15) was ranked first with the highest score, namely 0.731. These results indicate that Tuti Alawiyah has the best performance according to the criteria used in the MAUT method, reflecting her superiority over other candidates. The results of the study indicate that the MAUT method is able to provide accurate and consistent evaluation results, thus supporting a more rational and in-depth decision-making process. This study not only provides theoretical contributions to the development of the DSS system, but also provides practical benefits for educational institutions to improve the motivation of non-ASN teaching staff and, overall, the quality of education. This topic is relevant to the needs of modern education in Indonesia, especially in efforts to improve the transparency and accuracy of teaching staff assessments.
Data Mining Dalam Clusterisasi Risiko Tinggi Obesitas Menggunakan Metode K-Means Clustering Hasby, Anzila; Bangun, Budianto; Masrizal, Masrizal
Building of Informatics, Technology and Science (BITS) Vol 7 No 1 (2025): June (2025)
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v7i1.7462

Abstract

Obesity is a condition of excess body fat due to an imbalance between calorie intake and expenditure. This problem has become a global epidemic, including in Indonesia, with serious impacts on physical, mental, and social health. Women are more susceptible to obesity due to biological factors and lifestyle choices, as evidenced by data from a community health centre where 76.6% of central obesity patients were women. This study developed an obesity risk segmentation model for women using the K-Means Clustering algorithm based on secondary data from Kaggle (n=898), incorporating variables such as age, family history, dietary patterns, physical activity levels, and mode of transportation used. The results of preprocessing and StandardScaler normalisation showed two optimal clusters (Silhouette Score: 0.267), where Cluster 1 (young age 24.53 years, family history of obesity 1.91, fast food consumption 1.84, low physical activity 2.71) has a higher risk compared to Cluster 0 (age 41.41 years with a healthier lifestyle), revealing a significant interaction between genetic factors and lifestyle as the main triggers. These findings provide a scientific basis for group-based interventions, such as targeted nutrition education programmes for the young population, while demonstrating the effectiveness of data mining approaches in public health for classifying the risk of non-communicable diseases.
Decision Support System for Aircraft Takeoff and Landing Using Mamdani Fuzzy Logic Based on Weather Parameters Armansyah, Armansyah; Irianto, Suhendro Yusuf
Building of Informatics, Technology and Science (BITS) Vol 7 No 1 (2025): June (2025)
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v7i1.7464

Abstract

Aviation safety is highly influenced by weather conditions, particularly during take-off and landing, necessitating an accurate feasibility assessment. Traditional manual methods rely on subjective judgment, making them prone to inconsistencies and errors. This study proposes a decision support system utilizing Mamdani fuzzy logic to process real-time meteorological data from the Radin Inten II station and assess take-off and landing feasibility. The system evaluates key weather parameters, including wind speed, wind direction, visibility, precipitation, and cloud height. Testing 31 data samples from BMKG, the system achieved an accuracy of 96.77%, with 30 out of 31 outputs matching standard aviation criteria. These results indicate that the system significantly improves decision-making reliability. The Mamdani fuzzy logic approach proves effective in interpreting complex weather data and generating consistent, data-driven recommendations to support safe aircraft operations.
Density-Based Spatial Clustering, K-Means and Frequent Pattern Growth for Clustering and Association of Malay Cultural Text Data in Indonesia Mustakim, Mustakim; Salisah, Febi Nur
Building of Informatics, Technology and Science (BITS) Vol 7 No 1 (2025): June (2025)
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v7i1.7512

Abstract

Several studies state the need to develop information technology to disseminate information related to culture in Indonesia. There are many similar studies but they still have weaknesses, one of which is that they do not use machine learning and intelligent computing. This research answers the challenges of previous researchers, namely developing machine learning-based learning applications using the Density-Based Spatial Clustering of Application Noise (DBSCAN) and Frequent Pattern Growth (FP-Growth) algorithms. The results of the modeling of the two algorithms are deemed to still require improvement in the future, as it is proven that DBSCAN does not yet have optimal validity. So in this research, one of the comparison algorithms is used, namely K-Means Clustering, with a better evaluation than DBSCAN. The modeling results were implemented into mobile programming as a cultural learning application in Indonesia, especially Riau Malay Culture, the black box testing results had an accuracy of 100% and the User Acceptance Test (UAT) was 86%. Thus, it is concluded that this application can be used effectively and efficiently for general users.
Modifikasi Algoritma Sattolo Shuffle Untuk Mengacak Soal Pada Aplikasi Ujian Online Nasution, Surya Darma; Mesran, Mesran
Building of Informatics, Technology and Science (BITS) Vol 7 No 1 (2025): June (2025)
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v7i1.7580

Abstract

The use of Computer-Based Testing (CBT) systems has become a popular evaluation method due to its efficiency and ability to accelerate the assessment process. However, challenges such as cheating and the similarity of question sequences among participants still frequently occur. This study aims to design and implement a modified Sattolo Shuffle algorithm with the addition of a Linear Congruential Generator (LCG) as a source of random numbers in the exam question randomization process. The Sattolo Shuffle algorithm was chosen because it produces a single cyclic permutation that ensures each question element is repositioned, reducing the potential for recurring patterns. The LCG is used to generate random indices deterministically but variably, based on specific parameters and an initial value (seed) derived from the participant’s serial number. The implementation was carried out in a web-based CBT system consisting of 50 questions in each exam session. Testing on three participants showed that the generated question sequences were completely different, with no identical orders found. Each participant received a unique combination of questions with an even distribution of question positions. Initial results demonstrate the algorithm's effectiveness in increasing question variation and preventing duplication, making it a potential solution to enhance security and fairness in CBT administration. This research is expected to contribute significantly to the development of more randomized, fair, and cheat-resistant online exam systems.
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.