Applied Information Technology and Computer Science (AICOMS)

Sentiment Analysis of Twitter Comments on Manchester United's Performance Using the Support Vector Machine Algorithm

Ambrosius Dwi Cahyadi, Muhamad Rizvi Roshan, Muhamad Rizky Pribadi — Fri, 28 Jun 2024 00:00:00 +0000

Manchester United is one of the largest clubs in the English Premier League with an exceptional history in European and global football. In the 2023/2024 season, Manchester United experienced a very poor season, leading to various positive and negative sentiments from its fans, especially on social media. Sentiment data was gathered from Twitter, where Manchester United fans expressed their opinions regarding the team's performance in the Premier League. This study employs the Support Vector Machine (SVM) method to process and classify data collected from Twitter, aiming to analyze the sentiments of Manchester United fans based on their social media comments. The results indicate that the performance of the Support Vector Machine is relatively poor, achieving an accuracy of 58.73%. This is due to the dataset relying on a single keyword, which led to suboptimal and less complex data, resulting in the Support Vector Machine (SVM) producing relatively low accuracy.

Sentiment Analysis of Land Partner Applications Using the Naive Bayes Classifier and K-Nearest Neighbor Algorithms

Ananda Wijaya, Mario Rivaldo, Muhammad Rizky Pribadi — Fri, 28 Jun 2024 00:00:00 +0000

The transportation industry is now an important element as the times develop, especially for today's young generation. Mitra Darat itself is also one of these industries. An application that allows users to easily find out the bus departure schedule that they will take anywhere and anytime on their mobile device. Reviews are definitely given for every app available both positive and negative. With this, we are trying to conduct sentiment analysis research for the Mitra Darat application through reviewing comments from the Google Play Store so that we can identify sentiments related to the use of the Mitra Darat application, as well as provide valuable insights to land transportation service providers to understand user views and improve user services. from the results of our sentiment analysis. The algorithms we use are KNN and NBC. These two algorithms are commonly used by many people because of their expertise in classifying sentiment analysis data and are also popular among researchers. Based on our test results, it can be concluded that our sentiment analysis model designed using the NB algorithm displays higher accuracy performance than KNN. The accuracy of the NB model reached 99.28%, while KNN achieved an accuracy of 80%. This shows that the naïve Bayes algorithm is more suitable to obtain maximum accuracy compared to using k-nearest neighbors.

Development of a Regional Development Information System Based on a Website Using the Waterfall Method

Inayah Tulkhoiriyah, Safar Dwi Kurniawan, Darmanto Darmanto — Fri, 28 Jun 2024 00:00:00 +0000

Regional Development is a crucial aspect in achieving community progress and welfare. The Regional Development Information System (SIPD) serves as a vital tool in supporting the planning, management, and monitoring of development projects. This study discusses the development of a web-based SIPD using the Waterfall software development method. The Waterfall method was chosen for its structured and linear framework, with clear stages from analysis to design, implementation, testing, and maintenance. The study focuses on the design and implementation of a system capable of presenting regional development information transparently and accurately to the public. The development of SIPD involves several steps, including requirements analysis, responsive user interface design, integration of project monitoring features, and testing to ensure the system's reliability and security. Implementing the website as the primary platform enables easy access for stakeholders, including local governments, the public, and related parties. The results of this study indicate that the development of a web-based SIPD using the Waterfall method provides an efficient and structured solution. The system facilitates quick and easy access to regional development information, enhances transparency, and strengthens public involvement in the development process. Therefore, the application of the Waterfall method in the development of a web-based SIPD is expected to provide a solid foundation for improving the effectiveness of regional development planning and management.

Classification of Public Opinion Regarding the Naturalization of Football Players Using KNN and SMOTE

Rikky Rikky; Michelle Graciela, Hafiz Irsyad — Fri, 28 Jun 2024 00:00:00 +0000

This study analyzes public sentiment toward the naturalization of football players using the K-Nearest Neighbor (KNN) method and the Synthetic Minority Oversampling Technique (SMOTE). KNN is employed for sentiment classification, while SMOTE addresses class imbalance in the dataset. The methodology includes data collection, labeling, cleaning, preprocessing, classification, and model evaluation using Google Colab and Python. The results indicate that without SMOTE, the model performs better, achieving high precision, recall, F1 score, and accuracy. In contrast, applying SMOTE reduces performance, particularly in precision and F1 score. The "Manhattan Neighbor 7" and "Manhattan Neighbor 3" models without SMOTE demonstrate near-perfect results, while SMOTE significantly decreases several evaluation metrics. Additionally, the analysis of public opinions on YouTube reveals a tendency toward negative sentiment in podcasts about player naturalization, hosted by Bung Towel and Anjas Asmara, reflecting public skepticism and critical views on the topic. This study provides valuable insights into public sentiment and the effectiveness of classification methods in the context of national sports issues.

Comparison of SVM and Naïve Bayes Algorithms in Sentiment Analysis of TikTok Comments on Skincare Products

Steven Liem, Thomas Setiawan, M. Rizky Pribadi — Fri, 28 Jun 2024 00:00:00 +0000

This research compares the performance of the Support Vector Machine (SVM) and Naïve Bayes algorithms in sentiment analysis of TikTok comments about skincare products, using the Synthetic Minority Over-sampling Technique (SMOTE) to address data imbalance. The evaluation results indicate that SVM outperforms Naïve Bayes, achieving an accuracy of 59.43% compared to 47.65%. Additionally, SVM excels in the F1 Score metric (60.37% versus 54.74%), although Naïve Bayes demonstrates slightly higher precision (67.96% compared to 62.76%). Therefore, SVM proves to be more effective in classifying sentiment comments, making it the recommended algorithm for sentiment analysis tasks in the skincare product domain on TikTok.

Design of a Web-Based Outpatient Service Management Information System at Community Health Centers

Mokh Miftakhudin, Safar Dwi Kurniawan — Fri, 28 Jun 2024 00:00:00 +0000

The Web-Based Outpatient Service Management Information System at Community Health Centers is an application designed to support outpatient service processes for patients seeking medical check-ups at health centers. This application aims to assist health center staff in providing better services to patients. It also serves as a platform for storing patient data related to medical check-ups conducted at the health center. The application is developed using Hypertext Preprocessor (PHP) as the programming language, the Waterfall development method, and Unified Modeling Language (UML) for design modeling. The study resulted in a web-based application that allows health center staff to manage patient data, examiner data, queues, patient medical records, visits, prescriptions, medications, patient referral information, payment data, and generate necessary reports to support patient services.

Sentiment Analysis of Indonesian National Team Football Match Results in the U-23 Asian Cup on the YouTube Platform using the Support Vector Machine (SVM) Algorithm

Danang Pangestu, Maulana Malik, Muhammad Risky Pribadi — Mon, 22 Jul 2024 00:00:00 +0000

This study aims to analyze YouTube users' perceptions of the Indonesian national football team's matches in the 2024 AFC U23 Asian Cup. The research seeks to identify whether user sentiments toward the team's match results are positive, negative, or neutral. By using comments from the YouTube platform, the study examines public reactions to the outcomes of the Indonesian national team's matches in the U23 Asian Cup. Sentiment analysis of the match results was conducted using the Support Vector Machine (SVM) algorithm. Two SVM-based classification models were evaluated, one utilizing 40% of the data for testing and the other using 60%.

The findings reveal that the first model, with 40% test data, achieved an accuracy of 65.41%, while the second model achieved an accuracy of 63.76%. Although the first model demonstrated slightly higher accuracy, the second model performed better in terms of precision (61.65%), recall (63.76%), and F1-Score (55.68%).

Sistem Informasi Manajemen Perbendaharaan (Simara) Politeknik Negeri Ketapang

Eka Wahyudi, Indra Pratiwi, Darmanto Darmanto, Ar -Razy Muhammad — Sat, 01 Jun 2024 00:00:00 +0000

Perkembangan teknologi informatika disertai dengan teknologi komputer yang canggih dalam waktu yang relatif singkat telah mencapai perkembangannya sampai di setiap bidang kerja dan di setiap lapisan masyarakat. Pada dasarnya teknologi informatika dikembangkan untuk mempermudah masyarakat pada umumnya untuk mendapatkan informasi yang layak untuk dikonsumsi. Dengan memanfaatkan Teknologi Informasi diharapkan dapat membantu dalam pekerjaan, pemrosesan/pengolahan data-data penting serta pelayanan sebagaimana diharapkan oleh masyarakat. Dalam melaksanakan Good Government Politeknik Negeri Ketapang merencanakan pemanfaatan teknologi informasi untuk menunjang kinerja manajemen pemerintahan sebagai upaya mengimplementasikan dan mengembangkan pinformasi yang terpadu. Lembaga pendidikan tinggi yang baik harus memiliki sistem informasi manajemen pendidikan yang cukup dan baik guna memberikan pelayanan prima kepada seluruh civitas akademika. Politeknik Negeri Ketapang sebagai lembaga pendidikan tinggi bertanggung jawab dalam pengelolaan keuangan yang meliputi penerimaan, pengeluaran, dan penyimpanan dana dalam jumlah yang cukup besar. Seiring dengan perkembangan teknologi informasi yang semakin pesat, penggunaan sistem informasi dalam pengelolaan keuangan menjadi semakin penting guna mempercepat proses pengolahan data, meningkatkan akurasi, dan mengoptimalkan pengambilan keputusan. Oleh karena itu, penelitian ini bertujuan untuk membangun sistem informasi Simara yang dapat membantu pengelolaan keuangan di Politeknik Negeri Ketapang. Diharapkan penelitian ini dapat memberikan manfaat yang signifikan bagi pengelolaan keuangan di Politeknik Negeri Ketapang serta menjadi rujukan bagi institusi lain yang memiliki kebutuhan serupa dalam pengelolaan keuangan.