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 79 Documents
 1   2   3   4   5 
Search results for , issue "Vol 6 No 4 (2025): March 2025" : 79 Documents clear
Implementation of IndoBERT in Sarcasm Detection using Random Forest Towards Sentiment Analysis Sibarani, Sabrina Adela Br; Purba, Ronsen; Limbong, Ricky Paian
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.v6i4.5801

Abstract

Sarcasm, a subtle form of irony, often introduces a discrepancy between the literal meaning of words and the intended message, making it a significant challenge for sentiment analysis systems. Misinterpreting sarcasm in social media comments can lead to inaccurate sentiment classification, hindering decision-making processes in areas like customer feedback analysis and social opinion mining. This study addresses this issue by evaluating the effectiveness of sarcasm detection in Indonesian text using a Random Forest Classifier (RFC) integrated with IndoBERT. The research employs 10-fold cross-validation to measure performance. Without IndoBERT, the RFC model achieved average accuracy, precision, recall, and F1-score of 78.83%, 78.83%, 79.01%, and 78.83%, respectively. Incorporating IndoBERT significantly improved performance, with all metrics exceeding 84%. Furthermore, 5-fold cross-validation achieved the highest performance, with all metrics reaching 97.24%. This research contributes to developing more robust natural language processing models tailored to Indonesian linguistic contexts, specifically for sarcasm detection.
Klasifikasi Penerima Bantuan Program Indonesia Pintar (PIP) Pada Siswa SMK Menggunakan Algoritma KNN, NBC dan C4.5 Putra, Tandra Adiyatma; Permana, Inggih; Zarnelly, Zarnelly; 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.v6i4.6395

Abstract

The Indonesia Smart Program (PIP) is a government initiative aimed at providing educational assistance to students from underprivileged families. This research was conducted at SMKN 4 Pekanbaru to enhance the accuracy of distributing PIP aid using data mining methods. Three classification algorithms were used to identify students eligible for assistance: K-Nearest Neighbor (KNN), Naive Bayes Classifier (NBC), and C4.5. The data used in this study included attributes such as parental occupation, income, and the type of transportation used. The data processing involved cleaning, normalization, and splitting into test and training sets. The results showed that the KNN algorithm performed best with an accuracy of 84.20%, precision of 89.83%, and recall of 99.18%. The C4.5 algorithm excelled in model simplicity, while NBC showed less optimal results compared to KNN.
Enhancing Student Sentiment Classification on AI in Education using SMOTE and Naive Bayes Saekhu, Ahmad; Berlilana, Berlilana; Saputra, Dhanar Intan Surya
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.v6i4.6469

Abstract

This study investigates student sentiment regarding the use of artificial intelligence (AI) in education, employing the Naive Bayes model enhanced with the Synthetic Minority Over-sampling Technique (SMOTE) to address class imbalance issues. Class imbalance, a common challenge in sentiment classification, often skews model performance toward majority classes, reducing its effectiveness in recognizing minority classes. To mitigate this, SMOTE was applied to generate synthetic samples for minority classes, achieving a more balanced class distribution. The results demonstrate that incorporating SMOTE improved the Naive Bayes model's accuracy from 65% to 78.87% and significantly increased sensitivity to minority classes. Evaluation metrics, including precision, recall, and F1-score, showed satisfactory performance for certain classes, notably classes 2 and 4. However, challenges remained with class 1, where classification accuracy was lower, indicating inherent complexities in its data patterns. While SMOTE successfully enhanced model performance, it also introduced a potential risk of overfitting, particularly with limited original datasets, highlighting the importance of data quality and size. This research offers actionable insights for educators, developers, and policymakers, emphasizing the need for AI systems in education that are adaptive and responsive to student perceptions. The study concludes that Naive Bayes combined with SMOTE is an effective approach for sentiment analysis in imbalanced datasets. Future research should explore more sophisticated models and larger datasets to achieve more comprehensive and representative outcomes.
Perbandingan Algoritma NBC Dan SVM Untuk Melakukan Analisis Sentimen Terhadap PP NO.82 Tahun 2021 Rani, Arum Mustika; Hendrastuty, Nirwana
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.v6i4.6496

Abstract

Government Regulation (PP) No. 82/2021, which regulates the payment of pensions and allowances for Constitutional and Supreme Court Justices, has sparked public debate, especially after allegations of significant cuts to the Supreme Court's budget. This issue raises concerns regarding policy transparency, making it important to analyze public sentiment towards this PP. This study uses two sentiment analysis methods, namely Naïve Bayes Classifier (NBC) and Support Vector Machine (SVM), to evaluate public opinion based on data from Twitter. The dataset consists of 2,719 tweets that have gone through preprocessing stages, such as cleansing, stemming, and using SMOTE techniques, with 70% data division for training and 30% for model testing. This study tests the performance of NBC and SVM through four scenarios: (1) without stemming and without SMOTE, (2) without stemming with SMOTE, (3) with stemming without SMOTE, and (4) with stemming and SMOTE. The results show that SVM has a more stable performance than NBC in all scenarios. In the scenario without stemming and without SMOTE, both models recorded 100% accuracy, but NBC failed to detect positive sentiment accurately. When SMOTE was applied without stemming, NBC's accuracy decreased to 97%, while SVM still achieved a perfect accuracy of 100%. In the scenario with stemming without SMOTE, NBC recorded 97% accuracy, while SVM reached 99%. With the application of SMOTE and stemming, NBC accuracy decreased to 95%, while SVM again recorded a perfect accuracy of 100%. This study concludes that SVM is the best method for sentiment analysis of PP No. 82 of 2021, especially in scenarios with stemming and SMOTE, providing important insights into public opinion and confirming the superiority of SVM in sentiment classification related to public policy.
Implementasi LDA, TF-IDF, dan BERT dalam Sistem Rekomendasi Dosen Pembimbing untuk Mahasiswa Syabilla, Mutiara; Zeniarja, Junta; Nabila, Qotrunnada
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.v6i4.6499

Abstract

The selection of thesis supervisors is often done manually, which tends to be time-consuming in matching students' research topics with the expertise of faculty members. This study develops a thesis supervisor recommendation system based on the title and abstract of students' final projects, integrating Latent Dirichlet Allocation (LDA), Term Frequency-Inverse Document Frequency (TF-IDF), and Bidirectional Encoder Representations from Transformers (BERT). The research dataset includes 1,096 records from 71 faculty members in the Informatics Engineering Department at Universitas Dian Nuswantoro, collected through Google Scholar. The analysis process begins with text preprocessing such as case folding, tokenization, and stemming, followed by topic analysis using LDA, term-specific weighting through TF-IDF, and context-rich vector representation using BERT. The model matches students' research topics with faculty expertise using Cosine Similarity. Evaluation results show an accuracy of 80%, precision of 66%, and recall of 19%, indicating that the model can provide accurate recommendations, though some relevant items are still missed. This model proves effective in facilitating the selection of thesis supervisors. This research is expected to assist students in finding suitable supervisors and help faculty members identify students with relevant research interests.
Comparison of Naive Bayes and SVM Methods for Identifying Anxiety Based on Social Media Nugraha, Endri Rizki; 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.v6i4.6506

Abstract

This research aims to detect anxiety patterns from social media posts using Naive Bayes (NB) and Support Vector Machine (SVM) algorithms. Tweets are extracted using Data Crawling techniques, then continued their way into labeling using Depression Anxiety Stress Scale (DASS-42) questionnaire along with Random Oversampler to balance out the unbalanced dataset and NB and SVM were chosen for their effectiveness in text sentiment classification. This study integrates textual features obtained from the Term Frequency-Inverse Document Frequency (TF-IDF) and Bag of Words (BoW) methods. The study compares the performance of these algorithms in detecting anxiety using datasets from the X platform. The comparison aims to identify the advantages and limitations of each method in handling textual sentiment data. This research aims to analyze sentiment data by calculating accuracy, recall, and F1-score to determine the most optimal performance outcome. The results indicate that the SVM with TF-IDF feature extraction achieved the highest accuracy of 72% and an average F1-Score of 61%, while the NB with BoW achieved 56% accuracy and an average F1-Score of 49%. These findings highlight the effectiveness of combining SVM and TF-IDF features which improve model effectiveness with SVM producing the best overall result in identifying anxiety from social media data.
Penerapan Naïve Bayes Untuk Analisis Sentimen Pada Ulasan Aplikasi Mobile Legends Perkasa, Attila Elang; Putri, Astrid Novita
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.v6i4.6507

Abstract

Indonesia has become one of the potential markets for the gaming industry, continually increasing the number of gamers. One of the most popular mobile games in Indonesia is Mobile Legends. Mobile Legends is an online multiplayer battle arena (MOBA) video game developed by Moonton, a game development company based in China. The influence of reviews on the reputation of an app also affects potential new users, whether the reviews are positive or negative. Research has shown that the Naïve Bayes model provides good accuracy for sentiment analysis. This study is expected to help understand the perceptions and experiences of players of the game. The study uses the KDD (Knowledge Discovery in Data) method due to its advantages in identifying organized patterns from a complex dataset, making the data easier to understand. During the research process, 320,513 positive reviews, 185,777 negative reviews, and 20,210 neutral reviews were obtained. The accuracy value remained constant at 87% for the 80:20 data split scenario. Performance on the negative class showed high precision at 88%. The negative recall was 92%, indicating that the model could accurately capture truly negative reviews. A stable F1-Score of 82% signifies a good balance between precision and recall for the negative class. Performance on the positive class showed 87% precision and 83% recall. The F1-Score between the two was nearly balanced, indicating that the model performed similarly for both labels overall.
Classification of Key and Time Signature in Western Musical Notation by using CRNN Algorithm with Bounding Box Soeroso, Dennis Adiwinata Irwan; Winarno, Sri; Luthfiarta, Ardytha; Aryanti, Firda Ayu Dwi
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.v6i4.6510

Abstract

This research seeks to employ the Convolutional Recurrent Neural Network (CRNN) algorithm to develop a method for classifying key and time signatures from sheet music images. The research design involved compiling a dataset of 285 sheet music images, which includes 15 types of key signatures and 19 types of time signatures. The methodology encompasses annotation using the bounding box technique, image preprocessing, and applying the CRNN model for classification using K-Fold Cross Validation because of the limited dataset. Then, the model is evaluated using the Multi Class Confusion Matrix and performance metrics. The primary findings of this study reveal that the developed model achieves 96% accuracy in key signature classification and 95% in time signature classification when utilizing bounding boxes. Conversely, the absence of bounding boxes substantially negatively impacted the accuracy of key signature classification, resulting in only a 58% accuracy rate. Time signature classification performed even worse, with an accuracy of just 19%. This research highlights the substantial accuracy enhancements achievable by incorporating bounding boxes. Therefore, we anticipate that this research will help singers, especially those in choirs, to understand and express music better using existing technologies while enhancing the accuracy of optical music recognition using the CRNN model.
Klasifikasi Citra X-Ray Tuberkulosis Menggunakan Convolutional Neural Networks Mubarak, Haykal Alya; Novita, Rice
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.v6i4.6515

Abstract

Tuberculosis (TB) is a serious infectious disease that is still one of the main causes of death in the world, especially in developing countries. X-ray image analysis is an important step in controlling this disease. This research aims to classify X-ray images of tuberculosis using a deep learning approach with three Convolutional Neural Networks (CNN) architectures: DenseNet201, Xception, and MobileNetV2. The dataset used consists of 3,000 X-ray images, divided into two categories: normal and TBC, obtained from Kaggle, which are then processed through normalization, augmentation, and data division using the hold-out method with a ratio of 70:30, 80:20 , and 90:10. The research results show that DenseNet201 with the Nadam optimizer at 90:10 data division produces the highest accuracy of 100%, making it the best combination for TBC X-ray image classification. Xception achieved the best accuracy of 96.66% with the Nadam optimizer at a data split of 80:20. MobileNetV2 shows an optimal accuracy of 98.69% using the Adam optimizer at a 90:10 data split. This research proves that DenseNet201 with the Nadam optimizer is very effective in handling medical image classification, especially for tuberculosis. These results provide an important contribution to the development of deep learning-based technology to improve the accuracy of tuberculosis diagnosis.
Klasifikasi Citra CT Scan Kanker Paru-Paru Menggunakan Pendekatan Deep Learning Mulya, Anggi; Novita, Rice
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.v6i4.6528

Abstract

This research aims to develop a reliable deep learning model for classifying CT-scan images of lung cancer. This research has the advantage of evaluating the performance of several Convolutional Neural Networks (CNN) architectures including DenseNet121, InceptionResNetV2, InceptionV3 and ResNet152V2 to compare their performance in classification accuracy. The dataset consists of 1,561 CT scan images obtained from Kaggle and the dataset is categorized into malignant cancer, benign cancer and normal. Through a combination of innovative data pre-processing techniques, such as augmentation with random rotation and normalization, division of the dataset using the hold-out method with ratios of 70:30, 80:20, and 90:10, and model training using Adam's optimizer and SGDM, researchers achieved very high classification accuracy. The evaluation results showed that InceptionV3 with SGDM optimizer at 90:10 ratio achieved performed very well with an accuracy of 99.38% while InceptionResNetV2 with Adam optimizer at 80:20 hold-out the highest performance, with an accuracy of 99.40%. These promising results indicate great potential in supporting the early discovery of lung cancer, thereby improving the accuracy of diagnosis and the chances of patient recovery. This research opens up opportunities for further development, such as the application of fine-tuning, ensemble learning, or integration with clinical decision support systems for medical applications.

Page 1 of 8 | Total Record : 79

 1   2   3   4   5 

Filter by Year

2025 2025


Reset
Filter By Issues
All Issue Vol 7 No 4 (2026): March 2026 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