Article Per Year (5 Year)
p-Index From 2021 - 2026
24.208
P-Index
This Author published in this journals
All Journal MANAJEMEN HUTAN TROPIKA Journal of Tropical Forest Management Sodality: Jurnal Sosiologi Pedesaan MANAJEMEN IKM: Jurnal Manajemen Pengembangan Industri Kecil Menengah Jurnal Ilmu dan Teknologi Kelautan Tropis IJCCS (Indonesian Journal of Computing and Cybernetics Systems) Jurnal Ilmu Sosial dan Humaniora Jurnal Kawistara : Jurnal Ilmiah Sosial dan Humaniora Journal of Indonesian Tourism and Development Studies JURNAL ELEKTRO Jurnal Perkotaan Jurnal Kebijakan dan Administrasi Publik AdBispreneur PAX HUMANA ARISTO JURNAL MEDIA INFORMATIKA BUDIDARMA Jurnal Komunikasi Kritis Humaniora MUWAZAH: Jurnal Kajian Gender Cakrawala Jurnal Penelitian Sosial Building of Informatics, Technology and Science Jurnal Mantik Journal of Information Systems and Informatics Jurnal Studi Sosial dan Politik Jurnal Teknik Informatika C.I.T. Medicom JOURNAL OF INFORMATION SYSTEM RESEARCH (JOSH) Journal of Computer System and Informatics (JoSYC) EKONOMI, KEUANGAN, INVESTASI DAN SYARIAH (EKUITAS) Jurnal Sistem Komputer dan Informatika (JSON) JOURNAL OF BUSINESS AND ECONOMICS RESEARCH (JBE) Budapest International Research and Critics Institute-Journal (BIRCI-Journal): Humanities and Social Sciences Cita Ekonomika: Jurnal Ilmu Ekonomi ARBITRASE: JOURNAL OF ECONOMICS AND ACCOUNTING International Journal on Social Science, Economics and Art KLIK: Kajian Ilmiah Informatika dan Komputer International Journal of Basic and Applied Science Indonesian Journal of Tourism and Leisure Jurnal InterAct Jurnal Sosiologi Engagement: Jurnal Pengabdian Kepada Masyarakat JKAP (Jurnal Kebijakan dan Administrasi Publik) Jurnal Kawistara Muwazah: Jurnal Kajian Gender
Yerik Afrianto Singgalen
Universitas Katolik Indonesia Atma Jaya
Religion Agriculture, Biological Sciences & Forestry Arts Humanities Biochemistry, Genetics & Molecular Biology Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Economics, Econometrics & Finance Education Electrical & Electronics Engineering Environmental Science Industrial & Manufacturing Engineering Languange, Linguistic, Communication & Media Law, Crime, Criminology & Criminal Justice Library & Information Science Physics Public Health Social Sciences Other

Published : 234 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 234 Documents
Search

 18   19   20   21   22 
Sentiment Classification of Robot Hotel Content using NBC and SVM Algorithm Singgalen, Yerik Afrianto
Journal of Computer System and Informatics (JoSYC) Vol 5 No 2 (2024): February 2024
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/josyc.v5i2.4924

Abstract

Sentiment analysis plays a pivotal role in comprehending public sentiment, notably within digital communication, where copious amounts of textual data are generated daily. This study delves into the efficacy of sentiment classification models, namely the Naive Bayes Classifier (NBC) and Support Vector Machine (SVM), within the imbalanced datasets commonly encountered in sentiment analysis tasks. Employing a comparative analysis methodology, a dataset comprising robot hotel reviews from online platforms is the basis for evaluation. Both NBC and SVM models undergo training and assessment, with and without the Synthetic Minority Over-sampling Technique (SMOTE), to rectify the class imbalance. Performance evaluation relies on critical metrics, including accuracy, recall, precision, f-measure, and Area Under Curve (AUC) to gauge model effectiveness. Findings demonstrate SVM's superiority over NBC in terms of accuracy (SVM: 76.88%, NBC: 67.43%), precision (SVM: 92.03%, NBC: 86.87%), recall (SVM: 58.88%, NBC: 41.00%), f-measure (SVM: 71.78%, NBC: 55.63%), and AUC (SVM: 0.907, NBC: 0.961). Incorporating SMOTE significantly enhances both models' performance, particularly in addressing class imbalance concerns. Although NBC exhibits a more balanced performance across precision and recall metrics, SVM demonstrates heightened accuracy and predictive capability in sentiment classification tasks. These findings underscore the pivotal role of algorithm selection and preprocessing techniques in optimizing sentiment analysis performance, thereby providing invaluable insights for practitioners and researchers alike.
Comprehensive Analysis of Sentiment Classification and Toxicity Assessment in Cultural Documentary Videos Singgalen, Yerik Afrianto
Journal of Computer System and Informatics (JoSYC) Vol 5 No 3 (2024): May 2024
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/josyc.v5i3.5150

Abstract

This research explores sentiment classification and toxicity assessment in cultural documentary videos through a systematic analysis framework based on the Cross-Industry Standard Process for Data Mining (CRISP-DM). The study evaluates the sentiment polarity of viewer comments by utilizing a diverse array of machine-learning algorithms, including k-NN, DT, NBC, and SVM. It identifies toxic language patterns across multiple videos. Additionally, the research employs SMOTE to address class imbalance issues and enhance model performance. The results reveal high accuracy rates ranging from 72.24% to 96.79% in sentiment classification, indicating the effectiveness of the proposed methodology. Moreover, toxicity analysis unveils varying degrees of toxic language prevalence, with toxicity scores ranging from 0.01270 to 0.09334 across different videos. Despite these achievements, the study acknowledges the inherent limitations of toxicity scoring algorithms in capturing contextual nuances. Overall, this research contributes to understanding sentiment dynamics and toxicity trends in cultural documentary content and underscores the importance of employing advanced machine learning techniques within a structured analytical framework for insightful data interpretation and decision-making.
Comprehensive Analysis of Sentiment and Toxicity Dynamics in Tourist Vlog Reviews: A CRISP-DM Approach Singgalen, Yerik Afrianto
Journal of Computer System and Informatics (JoSYC) Vol 5 No 3 (2024): May 2024
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/josyc.v5i3.5154

Abstract

This research employs the CRISP-DM framework to analyze sentiment and toxicity dynamics in tourist vlog reviews thoroughly. The study delves into sentiment classification and toxicity identification nuances by leveraging machine learning algorithms such as k-NN, SVM, NBC, and DT with SMOTE. Utilizing a dataset comprising a substantial number of posts, the analysis reveals varying levels of accuracy across different algorithms. For instance, k-NN and SVM showcase promising accuracy rates of 85.90% and 86.27% in sentiment classification, while NBC and DT with SMOTE yield 72.52% and 71.14%, respectively. Furthermore, the research elucidates the limitations of toxicity analysis, with NBC demonstrating a precision of 64.96% and DT exhibiting lower recall rates. These findings highlight the importance of robust methodologies for understanding sentiment and toxicity dynamics in online content, particularly in tourist vlog reviews.
Sentiment and Toxicity Analysis of Biometric Authentication and Facial Recognition Technology Content Reviews using Cross-Industry Standard Process for Data-Mining Singgalen, Yerik Afrianto
Journal of Computer System and Informatics (JoSYC) Vol 5 No 3 (2024): May 2024
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/josyc.v5i3.5167

Abstract

This study investigates sentiment analysis methodologies within the framework of CRISP-DM (Cross-Industry Standard Process for Data Mining), aiming to discern the efficacy of various algorithms in sentiment classification tasks. The research uses a structured approach to evaluate SVM, NBC, DT, and K-NN algorithms with the SMOTE oversampling technique, uncovering distinct performance metrics and limitations. Results indicate SVM achieving 59.88% accuracy, NBC at 59.25%, DT with 52.09%, and K-NN obtaining 54.80%, highlighting the differential precision, recall, and f-measure. Additionally, content analysis identifies pertinent themes such as Biometric security, Cloud storage, and Emotion Analysis, enriching sentiment dynamics comprehension. The toxicity scores of analyzed videos reveal nuanced sentiment nuances, with the first video exhibiting Toxicity: 0.13227 and the second scoring Toxicity: 0.12794. This study underscores the significance of informed algorithm selection and evaluation methodologies within CRISP-DM, fostering optimized sentiment analysis outcomes while acknowledging diverse topical nuances.
Coastal and Marine Tourism Monitoring System Design using Rapid Application Development (RAD) Singgalen, Yerik Afrianto
Journal of Information System Research (JOSH) Vol 5 No 2 (2024): Januari 2024
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/josh.v5i2.4720

Abstract

To achieve sustainable tourism, a monitoring system of tourism activities is needed to minimize the environmental impact of the intensity of tourist visit activities. The development of coastal tourism needs particular attention, considering the diversity of activities around the coast related to environmental sustainability, including coral reefs. This study designed an information system and database to monitor coastal tourism activities to minimize the risk of damage to the coastal environment due to tourism activities. The method used in system design is Rapid Application Development (RAD), which has the following stages: requirement planning, user design, construction, and cutover. Meanwhile, the system and database design context is adjusted to the tourist destinations of Luari Beach, North Halmahera Regency, North Maluku Province, Indonesia. The results of this study show that identifying user needs at the requirements planning stage shows the need for a database of tourists visiting the destination and data related to the vehicles used. There is a need for a database related to beach conditions or beach environments and data on people involved as small entrepreneurs around coastal tourist areas. Considering the user's needs, at the user design stage, a prototype design is carried out using Oracle Apex with a dashboard display according to the data needed. At the construction stage, database configuration is carried out to display data visualization so that managers of beach tourist destinations understand the context and priority. System features and functions are tested at the cutover stage to evaluate application performance. The cutover result shows that successful applications can be used in decision-making. Thus, tourism destination managers take infrastructure development policies following existing conditions and short-, medium-, and long-term development plans.
Implementation of Rapid Application Development (RAD) for Community-based Ecotourism Monitoring System Singgalen, Yerik Afrianto
Journal of Information System Research (JOSH) Vol 5 No 2 (2024): Januari 2024
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/josh.v5i2.4749

Abstract

One of the challenges of tourism development in North Halmahera Regency is integrating technology in decision-making to determine leading and priority tourist destinations. Thematically, the ecology-based tourism development approach is the concept of ecotourism that balances environmental sustainability with tourism economic growth; however, tourism databases and information systems need to be developed by considering economic, socio-cultural, and environmental distribution and growth. This research adopts the Rapid Application Development (RAD) method in designing the Community-based Ecotourism Monitoring System. The stages in the RAD method consist of requirements planning, user interface design, construction, and cutover stages. At the requirement planning stage, this system will accommodate three main aspects: local attraction, local transportation, and local accommodation. A local attraction focuses on ecotourism development approaches, while local transportation refers to local transportation services managed individually or community-based. In addition, local accommodation refers to the business of homestay accommodation services as a form of community participation in tourism activities. At the construction stage, the instrument used in designing this system database is oracle-apex, which utilizes map, classic report, and form (modal dialog) features. Features and functions are tested at the cutover stage, and access rights restrictions are provided based on administrator, user, and viewer roles. The system design results show that policymakers must support community involvement in each tourist destination in determining priority areas for ecotourism infrastructure development. The testing result shows that all the features and operators are thriving and ready to be used. Thus, implementing RAD in the design of a community-based ecotourism monitoring system can be adapted to the context of ecotourism in North Halmahera Regency, North Maluku Province, Indonesia.
Implementing Rapid Application Development (RAD) for Statistical Analysis of Tourism and Travel Vlog Content Singgalen, Yerik Afrianto
Journal of Information System Research (JOSH) Vol 5 No 2 (2024): Januari 2024
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/josh.v5i2.4787

Abstract

Technological developments have sparked creativity through innovation in tourism marketing strategies through various video content. There have not been many studies that use video statistical data as a reference to create other creative content and identify opportunities to increase viewers and subscribers to access a broader range of system users. This research offers ideas for designing Tourism and Travel Vlog Content Statistical Analysis using the Rapid Application Development (RAD) approach. The stages in the RAD method consist of the requirements planning stage, user design stage, construction stage, and cutover stage. This study's results show that user needs identification shows the need for Author Channel data, statistics, and relation patterns that can be used in Social Network Analysis (SNA). At the user design stage, the dashboard design creates a page where images or background videos are taken in content to SNA and Chain Network pages. In the construction stage, design is carried out according to the use case diagram to manage data and make data as helpful information in identifying publication opportunities so that the video rating made is by tourist preferences so that it can trigger intentions to visit tourist sites. At the cutover stage, testing the features and functions of the application is carried out; the test results show that all pages can be accessed without any problems. Thus, this application can analyze statistical data of content published on various platforms. This application generally benefits content creators who consider statistical information in addition to popular content design.
Influence Analysis of the Teacher Ratio and Facilities on Failure to Pass the Class Using Multiple Linear Regression Suni, Eugenius Kau; Sutresno, Stephen Aprius; Christanto, Henoch Juli; Singgalen, Yerik Afrianto
Journal of Information System Research (JOSH) Vol 5 No 3 (2024): April 2024
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/josh.v5i3.4989

Abstract

The quality of education needs to be observed and maintained in building an effective teaching and learning environment. There are several factors that can affect the quality of education in a school, such as the availability of human resources, supportive learning facilities, environmental conditions, and various other factors. The focus of this research is on the ideal number of teachers in a school, considering the number of students and the availability of facilities such as laboratories and libraries, which will be correlated with the failure to pass the class rate. Data were obtained from the official website of the Kemdikbudristek regarding educational statistics, comprising 29 districts in Tangerang Regency for the academic year 2023/2024 at the senior high school level. The analysis was conducted using multiple linear regression, and it was found that the variables "availability of laboratory" and "availability of library" did not correlate with the failure to pass the class rate, whereas the "teacher ratio" variable correlated with the failure to pass the class rate with a value of +0.46. This can be explained that for every increase of 1 unit in the teacher ratio variable, or in other words, the fewer teachers teaching in a school compared to the number of students, the failure to pass the class rate will also increase by 0.46 students. Therefore, the results of this research can provide input for schools, especially in Tangerang Regency, to pay attention to the number of teachers in each school.
Sentiment and Topic Analysis of Aftermovie Piala Presiden eSports 2019 (Onic Esport) Setiawan, Ruben William; Rahadi, Abigail Rosandrine Kayla Putri; Singgalen, Yerik Afrianto
Journal of Information System Research (JOSH) Vol 5 No 3 (2024): April 2024
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/josh.v5i3.5036

Abstract

This research addresses the research problem of sentiment classification and topic analysis in the context of the Aftermovie Piala Presiden Esports 2019 (Onic Esport), employing the CRISP-DM methodology. Leveraging a dataset comprising 1830 posts, sentiment analysis was conducted on 191 posts using Vader and TextBlob algorithms, revealing the distribution of polarity values: 7.41% negative, 58.02% neutral, and 34.57% positive sentiments. Furthermore, the study evaluates the performance of classification algorithms, such as k-nearest Neighbors (k-NN), Support Vector Machine (SVM), and Decision Tree (DT), utilizing SMOTE. Notably, SVM demonstrated an accuracy of 90.34%, AUC of 0.995, precision of 99.91%, recall of 80.77%, and F-measure of 89.29%. Similarly, DT exhibited an accuracy of 94.83%, AUC of 0.950, precision of 92.12%, recall of 98.12%, and F-measure of 95.00%. K-NN displayed an accuracy of 92.83%, AUC of 0.972, precision of 98.01%, recall of 87.46%, and F-measure of 92.42%. The analysis also revealed frequently used words in the dataset, including 'onic' (127 occurrences), 'udil' (95 occurrences), and 'piala' (28 occurrences). This study sheds light on sentiment patterns and prevalent topics among esports enthusiasts, offering insights for content optimization and event management strategies.
Sentiment and Toxicity Analysis of Sport Event MotoGP Mandalika Circuit Using Cross-Industry Standard Process for Data-Mining Singgalen, Yerik Afrianto
Journal of Information System Research (JOSH) Vol 5 No 3 (2024): April 2024
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/josh.v5i3.5056

Abstract

This research identifies a research gap in understanding the impact of contextual factors on sentiment and toxicity within online discussions of sports events, focusing on the MotoGP event in Mandalika. By exploring how contextual nuances influence public sentiment and toxicity levels, this study aims to enhance the effectiveness of online discourse management and improve user experiences in digital platforms hosting event-related content. This research investigates the nuances of public sentiment and toxic language within textual data, specifically focusing on content videos of the MotoGP event held in Mandalika. Methodologically, the study embraces the CRISP-DM framework, facilitating structured data analysis, model development, and subsequent deployment. The findings reveal promising outcomes in terms of the performance of machine learning algorithms; notably, the k-NN algorithm attains an accuracy rate of 94.33%, precision of 96.48%, recall of 92.01%, f-measure of 94.19%, and an AUC score of 0.982. Similarly, the Support Vector Machine (SVM) demonstrates commendable accuracy, achieving 87.54%, precision of 99.53%, recall of 75.45%, f-measure of 85.82%, and an AUC score of 0.986. Furthermore, the toxicity analysis uncovers varying levels of harmful language, ranging from 0.01229 to 0.08933. These findings underscore the imperative nature of considering both sentiment dynamics and toxicity in managing online discourse effectively and enhancing user experiences across digital platforms. The sentiment analysis underscores the importance of understanding and effectively managing public emotions in the context of sports events like MotoGP. By acknowledging and addressing positive and negative sentiments, event organizers can better engage with their audience, mitigate potential issues, and ultimately enhance the overall experience for all involved.
Co-Authors A.Y. Agung Nugroho Agnes Harnadi Agung Mulyadi Purba Alfonso Harrison Aloisius Gita Nathaniel Astuti Kusumawicitra Astuti Kusumawicitra Astuti Kusumawicitra Laturiuw Astuti Kusumawicitra Laturiuw Asyifa Catur Rahmadini Bernardus Alvin Rig Bernardus Alvin Rig Biafra Daffa Farabi Biafra Daffa Farabi Billy Macarius Sidhunata Brito, Manuel Charitas Fibriani Christanto, Henoch Juli Christine Dewi Danny Manongga Dasra, Muhamad Nur Agus Eko Sediyono Eko Widodo Elfin Saputra Elfin Saputra Elly Esra Kudubun Fang, Liem Shiao Faskalis Halomoan Lichkman Manurung Gatot Sasongko Gilberto Dennis G E Sidabutar Gintu, Agung Rimayanto Gudiato, Candra Harnadi, Agnes Henoch Juli Christanto Henoch Juli Christanto Heru Prasadja Hindriyanto Dwi Purnomo Hironimus Cornelius Royke Irene Sonbay Irwan Sembiring Jesslyn Alvina Seah Jonathan Tristan Santoso Juli Christanto, Henoch Kartikawangi, Dorien Kusumawicitra, Astuti Manuel Brito Marthen Timisela Mavish, Steven Michael Kenang Gabbatha Nantingkaseh, Alfonso Harrison Nicolas Arya Nanda Susilo Nugroho, A. Y. Agung Octa Hutapea Octa Hutapea Pamerdi Giri Wiloso Pamerdi Giri Wiloso Pamerdi Giri Wiloso, Pamerdi Giri Pedro Manuel Lamberto Buu Sada Pinia, Nyoman Agus Perdanaputra Pontolawokang, Theresya Ellen Pristiana Widyastuti Pristiana Widyastuti Priya Tharsini Purwoko, Agus Puspitarini, Titis Radyan Rahmananta Radyan Rahmananta Rafael Christian Rahadi, Abigail Rosandrine Kayla Putri Richard Emmanuel Adrian Sinaga Rosdiana Sijabat Samuel Piolo Seingo, Martha Maraka Setiawan, Ruben William Siemens Benyamin Tjhang Sri Yulianto Joko Prasetyo Stephen Aprius Sutresno, Stephen Aprius Suharsono SUHARSONO Suni, Eugenius Kau Tabuni, Gasper Timisela, Marthen Titi Susilowati Prabawa Titis Puspitarini Widodo, Eko Winayu, Birgitta Narindri Rara Yan Dirk Wabiser Yoel Kristian Zsarin Astri Puji Insani