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
 61   62   63   64   65 
Sentiment Classification Using BERT-CNN and SMOTE: A Case Study on Hotel Reviews Dataset Singgalen, Yerik Afrianto
Building of Informatics, Technology and Science (BITS) Vol 6 No 3 (2024): December 2024
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v6i3.6309

Abstract

The increasing importance of user-generated content in the hospitality industry necessitates advanced sentiment analysis tools to derive actionable insights from customer reviews. Traditional methods often struggle with the complexities of natural language, such as contextual dependencies and nuanced emotional expressions. This research leverages the BERT-CNN hybrid model, which combines BERT’s contextual language understanding with CNN’s feature extraction capabilities, to address these challenges and improve sentiment classification accuracy. Using a dataset of 1,828 hotel reviews from Eastparc Hotel Yogyakarta, the model achieved an impressive accuracy of 99.59%, with precision and recall exceeding 0.99. The application of SMOTE effectively resolved class imbalance, enhancing the model’s ability to generalize across diverse sentiment classes. Training and validation loss curves exhibited steady convergence, indicating robust learning and minimal overfitting. These results provided actionable insights into customer satisfaction, offering targeted recommendations for enhancing service quality and operational strategies. This study demonstrates the practicality of integrating advanced machine learning architectures in sentiment analysis, enabling the hospitality sector to transform unstructured feedback into meaningful insights. The findings contribute to academic advancements in natural language processing and practical innovations in customer experience management. Future research may expand this framework to other domains, further underscoring its adaptability and impact.
Combination of PIPRECIA and Multi-Attributive Ideal-Real Comparative Analysis for the Determination of Scholarship Students Hadad, Sitna Hajar; Chandra, Iryanto; Maryana, Sufiatul; Setiawansyah, Setiawansyah
Building of Informatics, Technology and Science (BITS) Vol 6 No 3 (2024): December 2024
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v6i3.6313

Abstract

Scholarships are a form of financial assistance given to individuals to support their education. Criteria considered in the determination of scholarship recipients may include academic achievement, special talents, financial need, participation in extracurricular activities, and potential contributions to the community. The combination of weighting using PIPRECIA and MAIRCA can be a powerful approach in determining scholarship recipients. With PIPRECIA, scholarship providers can gather preferences from various relevant parties to determine the relative weight of each evaluation criterion. Furthermore, by applying MAIRCA, scholarship recipients can be evaluated based on these criteria by comparing between ideal attributes that reflect expected standards with real attributes that reflect the actual conditions of each recipient. By integrating these two methods, the process of determining scholarship recipients becomes more structured, transparent, and takes into account diverse preferences and priorities, ensuring that aid is distributed to the most deserving and needy individuals. The results of alternative rankings in determining scholarship recipients are 1st place with a final score of 0.071 obtained on behalf of Yusuf Maqdis, 2nd place with a final score of 0.068 obtained on behalf of Kurniawansyah, and 3rd place with a final score of 0.062 obtained on behalf of Ketut Purwanti.
Penerapan Metode K-Means Untuk Pengelompokkan Data Pelaporan Di Kantor Urusan Agama Nufus, Nur Hayatin; Sriani, Sriani
Building of Informatics, Technology and Science (BITS) Vol 6 No 3 (2024): December 2024
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v6i3.6316

Abstract

The process of reporting marriages at the Religious Affairs Office (KUA) in Laubaleng District is still done manually, which results in obstacles in the management, accuracy and efficiency of data access. This research aims to overcome this problem through developing a system based on the K-Means clustering method. This system is designed to group marriage reporting data based on attributes such as age, marital status, and month of marriage, so as to provide a more structured and informative data pattern. The Elbow method is used to determine the optimal number of clusters, while the K-Means algorithm is applied using Euclidean distance to calculate the closeness of the data to the centroid. The research process involves collecting reporting data from 2019 to 2024, data preprocessing, normalization, and evaluating clustering results using the Davies-Bouldin Index (DBI). The research results show that the K-Means method is effective in grouping data, providing clear visualization of the distribution of marriage patterns, and increasing the efficiency of data management at KUA. With this system, KUA can increase access speed, reduce the potential for errors, and support more accurate data-based decision making.
Analisis Customer Lifetime Value Berdasarkan Produk Menggunakan Metode RFM/P dan Algoritma Fuzzy C-Means Rachmawati, Dyana; Monalisa, Siti; Muttakin, Fitriani
Building of Informatics, Technology and Science (BITS) Vol 6 No 3 (2024): December 2024
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v6i3.6320

Abstract

212 Mart Soebrantas is a retail company based on a Sharia Cooperative. 212 Mart Soebrantas segments its customers in terms of monetary value, specifically customers who make many purchases. Currently, 212 Mart does not consider recency and frequency, because customers who make transactions of 50 thousand rupiahs receive 1 point. If the points accumulate to 200, they exchange them for a shopping voucher worth 50 thousand rupiah to shop at 212 Mart. 212 Mart Soebrantas needs to understand Customer Lifetime Value (CLV) to determine the customer categories worth keeping and profitable for 212 Mart. Therefore, 212 Mart needs to understand and know its customer segments based on product-based transactions or RFM/P. This research analyzes Customer Lifetime Value Based on Products Using the RFM/P Method and Fuzzy C-Means Algorithm at 212 Mart Soebrantas to help 212 Mart identify customer segment characteristics, and customer loyalty per product category, and provide strategic recommendations. The data used is customer transaction data from January 2023 to September 2023. The study uses products from 10 categories with 6 attributes: Member Code, Stock Name, Transaction Date, Quantity, Basic Price, and Department. The research shows that the best cluster is found in the Basic Material category with a DBI value of 0.4990, and it is a Superstar Customer based on Customer Portfolio Analysis (CPA).
Penggunaan Model Bahasa indoBERT pada metode Random Forest untuk Klasifikasi Sentimen dengan Dataset Terbatas Pranata, Joni; Agustian, Surya; Jasril, Jasril; Haerani, Elin
Building of Informatics, Technology and Science (BITS) Vol 6 No 3 (2024): December 2024
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v6i3.6335

Abstract

Masalah keterbatasan data latih menjadi tantangan utama dalam klasifikasi sentimen di berbagai bahasa, termasuk bahasa Indonesia, terutama untuk analisis sentimen terkait topik tertentu. Hal ini disebabkan oleh berbagai faktor, dan umumnya adalah kebutuhan untuk mengetahui dengan segera bagaimana sentimen terhadap suatu isu, sehingga tidak mungkin menghabiskan waktu untuk memberi label yang cukup pada data untuk proses pelatihan. Penelitian ini mengusulkan model klasifikasi sentimen dengan sumber data pelatihan yang sedikit, pada studi kasus pengangkatan Kaesang Pangarep sebagai ketua umum PSI. Algoritma Random Forest digunakan sebagai model dasar (baseline) yang dioptimasi dengan penambahan data eksternal untuk training, pemrosesan teks (text preprocessing) dan parameter tuning. Fitur input yang digunakan adalah model bahasa IndoBERT sebagai embedding kata untuk menghasilkan representasi teks yang lebih kontekstual. Hasil penelitian menunjukkan bahwa metode IndoBERT dengan Random Forest yang dioptimasi memberikan peningkatan performa yang signifikan dibandingkan baseline, sebesar 6%. Hasil klasifikasi model yang paling optimal sebesar 54% unutk F1-score dan 63% akurasi. Temuan ini menegaskan bahwa penambahan data eksternal dan optimasi parameter dapat meningkatkan kemampuan generalisasi model dalam klasifikasi sentimen bahasa Indonesia. Penelitian ini diharapkan dapat menjadi referensi metodologis bagi studi klasifikasi sentimen serupa yang menghadapi kendala ukuran dataset.
Analisis Sentimen Menggunakan Algoritma Naïve Bayes, KNN, dan Decision Tree Terhadap Ulasan Aplikasi KitaLulus Harun, Rodyah Mulyani; Fahmi, Faisal
Building of Informatics, Technology and Science (BITS) Vol 6 No 3 (2024): December 2024
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v6i3.6367

Abstract

The advent of digital technologies has transformed interaction dynamics between companies and potential employees by creating job search platforms. KitaLulus, one of the leading platforms in Indonesia, facilitates the job search process by providing various vacancies from various companies on one platform. However, there are several complaints from users, such as a complex job application process, inefficient file storage, and poor user interface (UI) and user experience (UX). On the other hand, Twitter is one of the places that contains user reviews, both in the form of satisfaction or disappointment, so that it can be used to identify public sentiment towards the KitaLulus application. Since it is important for the current generation, it is necessary to have a quality job search application, where recommendations for improving the quality of the application can be obtained from sentiment analysis. Therefore, sentiment analysis was conducted to identify public sentiment towards the KitaLulus application. The analysis in this study used 600 review data from Twitter which were then classified by sentiment based on Naïve Bayes, KNN, and Decision Tree algorithms. This research consists of six stages, namely data collection, data cleaning, data labelling, data preprocessing starting from SMOTE, split data, transform cases, tokenize, filter stopwords, and filter tokens (by length), sentiment classification, and finally results and evaluation. The results, after SMOTE was applied at the preprocessing stage, showed that KNN was the best algorithm with accuracy of 83.33%, precision of 80.36%%, and recall of 71.09%, followed by Naïve Bayes and Decision Tree respectively.
Sistem Pendukung Keputusan Penerima Kartu Indonesia Pintar (KIP) Menggunakan Analisis Metode MOORA dan MOOSRA Prayogo, M. Ari; Jundillah, Muhammad Labib; Fahrullah, Fahrullah; Rosita, Dewi; Alimyaningtias, Wahyu Nur; Adhari, Vika Aidila; Rifkiansyah, Muhammad
Building of Informatics, Technology and Science (BITS) Vol 6 No 3 (2024): December 2024
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v6i3.6384

Abstract

The decision-making process is important to improve efficiency and accuracy, especially in assistance programs such as the Smart Indonesia Card (KIP). The problem in this study is that the selection process often faces several obstacles, such as inappropriate targets and subjectivity in decision-making. Therefore, a system is needed that can help decision-making more objectively, transparently, and efficiently. Decision Support Systems (DSS) are one solution that can be used to overcome these problems. This study aims to create a DSS in determining eligible KIP recipients, using two multi-criteria analysis methods, namely MOORA (Multi-Objective Optimization by Ratio Analysis) and MOOSRA (Multi-Objective Optimization on the basis of Simple Ratio Analysis). Analysis using the MOORA and MOOSRA methods in determining prospective students receiving the Smart Indonesia Card (KIP) was carried out using 7 alternatives and 9 criteria. This system is designed by considering criteria such as parental dependents, place of residence, type of house, average report card grades, father's education, mother's education, father's occupation, mother's occupation, and parents' income. The results of the study show that based on the analysis of the calculation of the MOORA and MOOSRA methods, the ranking results were obtained with A5 or Zaysa as alternative students who are entitled to receive KIP among other alternative students. The results of the analysis show that both methods provide consistent results in identifying students who are most entitled to receive KIP assistance. As a recommendation, this system can be further developed in the form of a web-based or mobile application to facilitate implementation and expand the scope of its use.
Perbandingan Algoritma Naïve Bayes dan LSTM untuk Analisis Sentimen Terhadap Opini Masyarakat Tentang Sandwich Generation Ramadhan, Naufal Rizqi; Hendrastuty, Nirwana
Building of Informatics, Technology and Science (BITS) Vol 6 No 3 (2024): December 2024
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v6i3.6385

Abstract

Sandwich Generation is a term for a group of people who have elderly parents and children, so they have to take care of both generations. Opinions about this phenomenon have elicited various responses on social media twitter, which requires in-depth analysis. This study identifies the problems of the lack of research comparing the performance of Naïve Bayes and LSTM algorithms in analyzing public opinion sentiment about the sandwich generation, the complexity of social media data analysis with the characteristics of informal language, abbreviations, and symbols that are difficult to analyze manually, the need to explore the algorithm's ability to classify sentiment, and determine the most accurate method to analyze public opinion sentiment. Sentiment analysis is used to evaluate opinions, feedback, and emotions by classifying texts into positive, negative, or neutral categories. The results obtained from this study are that the LSTM method has better performance when compared to Naive Bayes. The LSTM method produced an accuracy, precision and recall value of 91.85%. while the Naive Bayes method has an accuracy value of 83%, precision of 90% and recall of 82%.
Klasifikasi Sentimen Menggunakan Metode Passive Aggressive dengan Menggunakan Model Bahasa BERT pada Dataset Kecil Subhi, Yazid Abdullah; Agustian, Surya; Irsyad, Muhammad; Insani, Fitri
Building of Informatics, Technology and Science (BITS) Vol 6 No 3 (2024): December 2024
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v6i3.6389

Abstract

Text classification is one of the most popular tasks in natural language processing, especially in the context of sentiment classification. Insufficient training data poses a significant challenge in many text classification studies. This research focuses on optimizing classification performance using the Passive Aggressive (PA) algorithm, leveraging limited training data. It compares conventional text representation methods like TF-IDF with modern approaches employing word embeddings such as FastText and BERT. The primary dataset encompasses sentiment issues related to Kaesang Pangarep's appointment as the chairman of PSI, gathered through Twitter crawling, and classified into positive, negative, and neutral sentiment labels. Two versions of the training data, each containing only 300 balanced tweets for positive, negative, and neutral classes, were used. The data was split 80% for training and 20% for validation in the search for an optimal model. External data with different issues and pre-existing sentiment labels was used to augment the training data. Experimental results demonstrated that the BERT language model, used as input features for the Passive Aggressive method with hyperparameter tuning, outperformed TF-IDF features. Evaluation on the test data revealed that BERT features with Passive Aggressive achieved an F1-score of 0.52, surpassing the conventional TF-IDF representation with an F1-score of 0.42. The utilization of the BERT language model significantly contributed to improving text classification performance in the field of natural language processing, particularly for the Passive Aggressive method.
Analisis Sentimen Komentar Perplexity AI di X Tentang Pendidikan Menggunakan Support Vector Machine Ardiansah, Yoga; Monalisa, Siti; Muttakin, Fitriani
Building of Informatics, Technology and Science (BITS) Vol 6 No 3 (2024): December 2024
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v6i3.6396

Abstract

Chatbots with Artificial Intelligence are increasingly popular in everyday life. Due to its ability to reason and convey information expressively, Artificial Intelligence (AI) using Natural Language Processing (NLP) models can communicate like humans. Users find one of Perplexity's AI chatbots interesting because it can pinpoint sources of information. As time goes by and the number of Perplexity users increases, sentiment analysis is used to measure user happiness. This sentiment analysis serves as the data source for this research, helping understand how users react to social media X (Twitter). The Support Vector Machines (SVM) method was used in this study, where SVM maximises the distance (margin) between data groups to determine the ideal hyperplane. According to the survey, 90.11% of respondents expressed positive sentiments, 5.30% expressed negative opinions, and 4.69% expressed neutral sentiments. Using a ratio of 80% training data and 20% test data, the f1 score reached 96%, with accuracy and precision of 92% each.

Page 63 of 93 | Total Record : 926

 61   62   63   64   65 

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