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 889 Documents
 43   44   45   46   47 
Implementation of Toxicity, Social Network, and Sentiment Classification: Alffy Rev Live in World E-sport Championship 2022 Rahadi, Abigail Rosandrine Kayla Putri; Setiawan, Ruben William; Singgalen, Yerik Afrianto
Building of Informatics, Technology and Science (BITS) Vol 5 No 4 (2024): March 2024
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v5i4.5032

Abstract

This academic study investigates sentiment, toxicity, and social network dynamics within esports, focusing on the Esport World Championship 2022 featuring Alffy Rev's music performance. The research problem centers on discerning sentiment perceptions among esports enthusiasts and music fans while evaluating toxicity levels in online interactions during the event. Following the CRISP-DM methodology, the study systematically employs sentiment classification using Rapidminer, SVM with SMOTE for toxicity analysis, and Social Network Analysis (SNA). The findings reveal significant insights, including a sentiment classification accuracy of 98.73% using SVM with SMOTE, toxicity metrics such as Toxicity (0.04690) and Severe Toxicity (0.01203), alongside crucial SNA metrics like Diameter (2) and Density (0.001009). Additionally, frequently used words in the dataset include "keren" (94 occurrences), "Indonesia" (88 occurrences), "karya" (84 occurrences), and "Alffy" (59 occurrences). These findings offer valuable contributions to the esports community, informing community management strategies, event organization, and online engagement approaches. As a recommendation, deploying these analytical approaches could enhance community engagement and mitigate toxic interactions
Implementation of the GloVe in Topic Analysis based on Vader and TextBlob Sentiment Classification Singgalen, Yerik Afrianto
Building of Informatics, Technology and Science (BITS) Vol 5 No 4 (2024): March 2024
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v5i4.5033

Abstract

This research investigates public sentiment towards tourism and gastronomy content through sentiment classification methodologies, employing the Cross-Industry Standard Process for Data Mining (CRISP-DM) framework. Leveraging sentiment analysis techniques, including Vader and TextBlob, the study analyzes a dataset of textual content related to tourism and gastronomy to discern prevailing sentiment distributions. The findings reveal a predominant prevalence of positive sentiments (72.19%), followed by neutral (23.33%) and negative sentiments (4.48%). These results shed light on the overall sentiment dynamics surrounding tourism and gastronomy content, indicating a predominantly positive reception among users. The study contributes to the body of knowledge in sentiment analysis research, particularly within tourism and gastronomy studies, offering valuable insights into user perceptions and attitudes. Such findings have implications for content creators, marketers, and policymakers seeking to enhance tourism and gastronomy experiences. Future research could delve deeper into the factors influencing sentiment expressions and explore strategies to leverage positive sentiments for promoting and advancing tourism and gastronomy endeavors within the CRISP-DM framework.
Implementation of Sentiment Classification using k-NN, SVM, and DT for the MukaRakat Official Music Video (IDR and Toki Sloki) Singgalen, Yerik Afrianto
Building of Informatics, Technology and Science (BITS) Vol 5 No 4 (2024): March 2024
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v5i4.5044

Abstract

This study presents a comprehensive analysis of sentiment classification algorithms applied to content from the entertainment industry, specifically focusing on hip-hop music videos. Following the CRISP-DM (Cross-Industry Standard Process for Data Mining) methodology, the research evaluates the performance of three prominent algorithms: k-nearest Neighbors (k-NN), Decision Tree (DT), and Support Vector Machine (SVM) with Synthetic Minority Over-sampling Technique (SMOTE). The analysis incorporates performance metrics, including accuracy, precision, recall, f-measure, and the area under the curve (AUC) values. The dataset comprises user-generated comments and feedback from two distinct hip-hop music videos. Results indicate that all three algorithms exhibit notable accuracy in classifying sentiments, with SVM with SMOTE achieving the highest accuracy of 83.68%. DT demonstrates balanced performance metrics, particularly in precision and recall, with an accuracy of 79.12%. Meanwhile, k-NN exhibits a lower accuracy of 64.71% but showcases balanced precision and recall rates. These findings suggest the suitability of SVM with SMOTE for sentiment classification tasks in the entertainment industry, offering valuable insights for content creators, marketers, and platform administrators to enhance audience engagement and user experience. Additionally, the study underscores the importance of algorithmic evaluation and selection in content analysis, providing guidance for future research and practical applications in the entertainment domain within the framework of CRISP-DM.
Implementation of Toxicity, Sentiment, and Social Network Analysis (Epic Rap Battles of Presidency 2024) Singgalen, Yerik Afrianto
Building of Informatics, Technology and Science (BITS) Vol 5 No 4 (2024): March 2024
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v5i4.5046

Abstract

This research delves into the complex realm of digital political communication, employing a comprehensive approach that integrates toxicity analysis, sentiment classification, and social network analysis within the framework of the CRISP-DM methodology. The study illuminates the multifaceted nature of online discourse through meticulous examination, elucidating the coexistence of harmful content, diverse sentiments, and intricate network structures. Leveraging VADER and TextBlob algorithms, toxicity and sentiment distribution patterns are meticulously identified, with metrics such as Toxicity, Severe Toxicity, Identity Attack, Insult, Profanity, and Threat presenting distinct numerical values. For instance, Toxicity measures at 0.09275 with a severe threshold of 0.98622, while sentiment analysis reveals varying proportions of negative, neutral, and positive sentiments across English, French, and German content. Specifically, VADER sentiment analysis for English content shows 25.38% classified as unfavorable, 41.13% as neutral, and 33.49% as positive sentiments, while TextBlob sentiment analysis for English content displays 8.59% negative, 64.12% neutral, and 27.29% positive sentiments. Similarly, TextBlob sentiment analysis for French content indicates 1.75% negative, 96.49% neutral, and 1.75% positive sentiments, and for German content, it illustrates 2.00% negative, 96.52% neutral, and 1.48% positive sentiments. These findings provide crucial insights into public sentiment, information dissemination, and community formation within online political discourse. The implications of this research extend to policymakers, electoral candidates, and digital platform developers, offering evidence-based strategies to cultivate healthier online environments and promote informed civic engagement. Further investigation is warranted to explore emerging trends and adapt analytical frameworks to the evolving landscape of digital communication. Ultimately, this study advances our understanding of digital political communication and underscores the necessity of interdisciplinary approaches in addressing contemporary socio-political challenges in the digital era.
Implementasi Library Textblob dan Metode Support Vector Machine Pada Analisis Sentimen Pelanggan Terhadap Jasa Transportasi Online Laia, Yardiana; Berutu, Sunneng Sandino; Sumihar, Yo’el Pieter; Budiati, Haeni
Building of Informatics, Technology and Science (BITS) Vol 6 No 1 (2024): June 2024
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v6i1.5090

Abstract

Online transportation services have become an inseparable part of human life today. This research aims to develop an effective sentiment analysis method to measure public opinion about the quality of online transportation services, which has a significant impact on company reputation and public acceptance of these services. In this research, we propose the use of TextBlob library to perform sentiment analysis of public opinion on online transportation services. This library allows to measure the positive, negative and neutral polarity and subjectivity of opinion text collected from Gojek, Maxim and Grab application reviews through Google Play Store. Sentiment analysis steps are carried out starting from data preparation, data pre-processing, data labeling using the Text Blob library. Furthermore, building a sentiment classification model based on the Support Vector Machine (SVM) algorithm through training and testing stages. Model testing results are evaluated with confusion matrix. The results of the analysis with textblob showed that online transportation received the highest positive sentiment of 40.1%, followed by neutral sentiment of 26.7% and negative sentiment of 25.2%. Meanwhile, the model performance measurement results show that the precision obtained the highest value in positive sentiment of 0.93. The recall parameter reaches the highest value in negative sentiment of 0.95 and f1-score in neutral and positive sentiment of 0.92. Thus, this research not only contributes to the development of sentiment analysis classification, but also has a significant practical impact in improving online transportation services and providing useful information to the public, thus encouraging innovation and continuous improvement in online transportation services.
Prediction of Theft with Machine Learning Technology at Police Station Hadmanto, Aditya; Prianggono, Jarot
Building of Informatics, Technology and Science (BITS) Vol 6 No 1 (2024): June 2024
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v6i1.5107

Abstract

This study originated from the increase in theft cases in the jurisdiction of Banjarbaru District Police which resulted in material and psychological losses for victims and disturbed the overall sense of security of the community. The research aims to develop a method that can assist the police in preventing and tackling theft crimes more effectively using machine learning algorithms. Research methods include research design, quantitative approach, and data collection and analysis techniques. The data analyzed included various categories of relevant information, such as the victim's gender, age, occupation, location of the incident, as well as details related to the modus operandi and losses suffered by the victim. The main data used is data on victims of theft crimes in the Banjarbaru Police jurisdiction during the 2019-2023 period. Data collection was carried out using primary data available from Min Ops Reskrim Polresta Banjarbaru. using the K-Nearest Neighbor (KNN) and Naïve Bayes (NB) algorithms to process historical data on theft crimes in Banjarbaru. The results reveal the general characteristics of theft cases, including time patterns, locations, and modus operandi, and compare the effectiveness between KNN and NB algorithms in predicting theft crimes. The conclusions emphasize the potential of machine learning in identifying theft patterns and provide recommendations for further development to support better decision-making and planning of crime prevention strategies
Market Basket Analysis to Determine Muslim Clothing Supply in Indonesia Ahead of Eid Al-Fitr Indra Gunawan, Gun Gun; Aji, Tri Wahyu; Juliane, Christina
Building of Informatics, Technology and Science (BITS) Vol 6 No 1 (2024): June 2024
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v6i1.5162

Abstract

Enterprise transaction data is a valuable source of insights for companies to increase sales. In preparation for Eid al-Fitr, this study leverages Market Basket Analysis with the FP-Growth algorithm to uncover buying patterns within Indonesia's Muslim clothing market. Market Basket Analysis is one way to explore information through data to find customer buying patterns that are often used as insight into company decision-making. The data processing method uses the FP-Growth algorithm, which generates association rules based on calculating the frequency of occurrence of itemsets. Using the FP-Growth algorithm gives good results in the determination of association rules. From Muslim fashion store transaction data over the last 12 months, it produced 30 item set patterns with a minimum support value of 0.009 and confidence of 0.58. By identifying these in-demand product pairings, businesses can make informed decisions about stock allocation. This ensures they have the right combination of items available to meet customer needs during the surge in demand leading up to Eid al-Fitr. Additionally, these patterns can inform targeted promotional campaigns and strategic bundling initiatives, maximizing sales and customer satisfaction throughout this critical sales period.
Klasifikasi Suara Anjing Menggunakan Pretrained Model Yet Another Mobile Network Berbasis Convolutional Neural Network Djuardi, Rich Deshan; Rochadiani, Theresia Herlina
Building of Informatics, Technology and Science (BITS) Vol 6 No 1 (2024): June 2024
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v6i1.5165

Abstract

In everyday life, pets such as dogs often become an inseparable part of human life. Motivations for keeping a pet can vary from individual to individual, ranging from the need for a loyal companion to the responsibility of caring for another living creature. Among the various choices of pets, dogs are often considered the most loyal and loyal friends towards humans. This uniqueness makes many people choose to keep dogs as part of their family. Often, dog owners may not understand the message that the sounds produced by their beloved pets are trying to convey. These dog sounds have a special purpose that can reflect various emotions, such as joy, sadness, or anger. A dog's voice can also be an indicator of their health that owners need to pay attention to. The main focus of this research is to develop dog voice classification technology to help owners understand and communicate with their pet dogs. In this research, a pre-trained YAMNet model is used as a basis for classifying various audio events. The model training process uses the CNN algorithm contained in the YAMNet architecture. The total data used was 373 data which were classified into 4 classes, namely, bark, howling, growling, whimper. The results of this research model achieved 97.8% accuracy with precision, recall and f1-scores for each class >= 95%.
Analisis Sentimen Terhadap Publisher Rights Dalam Mengunggah Konten Digital Menggunakan Ensemble Learning Putri, Anisa; Mustakim, Mustakim; Novita, Rice; Afdal, M
Building of Informatics, Technology and Science (BITS) Vol 6 No 1 (2024): June 2024
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v6i1.5179

Abstract

Digital content encompasses various forms of information, ranging from informative text to interactive videos. YouTube, as one of the most popular social media platforms, is widely used in Indonesia. However, the proposed Publisher Rights Bill or the Draft Presidential Regulation on the Responsibility of Digital Platforms for Quality Journalism has sparked debate. In the context of YouTube, this regulation has the potential to threaten content creators. Negative reactions from various parties highlight concerns about the impact of this regulation. Therefore, this study aims to analyze sentiment towards Publisher Rights in the uploading of digital content using an ensemble learning approach. The analysis found that 60% of the sentiment was negative, reflecting concerns about copyright, royalties, or ethical issues. A total of 32% of the sentiment was neutral, indicating uncertainty or a lack of information, and only 8% of the sentiment was positive, supporting the policy of protecting publisher rights and recognizing their value and contributions. This study employed ensemble techniques based on Bagging (Random Forest) and Boosting (Adaboost), where the accuracy of Random Forest was higher at 83% compared to Adaboost's accuracy of 68%.
Perbandingan Algoritma Linear Regression, Support Vector Regression, dan Artificial Neural Network untuk Prediksi Data Obat Putri, Suci Maharani; Novita, Rice; Mustakim, Mustakim; Afdal, M
Building of Informatics, Technology and Science (BITS) Vol 6 No 1 (2024): June 2024
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v6i1.5184

Abstract

Regression is a crucial focus in various fields aiming to forecast future values to aid decision-making and strategic planning. Different regression algorithms have their advantages and disadvantages, and their performance can vary depending on the data characteristics. Therefore, further analysis is needed to identify the appropriate algorithm that provides the best solution for the problem at hand. This study compares three popular regression algorithms: Linear Regression (LR), Support Vector Regression (SVR), and Artificial Neural Network (ANN) to predict drug data at a pharmacy in Riau province. Currently, the pharmacy lacks an accurate method for estimating monthly drug needs, relying instead on rough estimates. This often results in either shortages or overstock, leading to losses, especially if the drugs expire. Three types of drugs, namely Amoxicillin, Antacids, and Paracetamol were selected to test the proposed algorithms. The analysis and comparison show that the SVR algorithm outperforms the others on all three drug types when focusing on the RMSE metric. However, when the focus is on the MAPE metric, the ANN algorithm proves to be superior. Although LR does not excel in any metric, all three algorithms (LR, SVR, and ANN) have MAPE values below 10%, indicating highly accurate predictions. This accuracy is evidenced by the prediction results of all proposed models, which effectively follow the patterns and trends in the actual data

Page 45 of 89 | Total Record : 889

 43   44   45   46   47 

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