Claim Missing Document
Check
Articles

Found 5 Documents
Search

Optimalisasi Efektivitas Program MBKM: Sistem Monitoring Berbasis Lokasi dan Analisis aktivitas dengan TF-IDF Tarigan, Ita Margaretta Br; Tarigan, Siti Jamilah Br; Ginting, Raheliya Br
Journal of Information System Research (JOSH) Vol 6 No 1 (2024): Oktober 2024
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/josh.v6i1.5945

Abstract

The research is based on the importance of a monitoring system for students who study outside the classroom which is very necessary on an ongoing basis, considering that the PT and DPL coordinators must continue to monitor directly or indirectly students who participate in MBKM activities. The problem so far has been the difference between the MBKM plan and the MBKM results, where from the monitoring results, there are several weaknesses in the information and data in the MBKM program, for example, difficulty in knowing the location. This study aims to design a location-based student activity monitoring system to make it easier for PT and DPL coordinators to find out student activities and make assessments based on the history of activities outside the classroom with the MBKM program followed by students. The activity history reported each day will be processed using the Term Frequency-Inverse Document Frequency (TF-IDF) method to find similarities in activities based on the completion time and types of activities carried out by students. The results of the activity history processed with TF-IDF are in the form of reports which will later become supporting information for objective assessment of student learning outcomes. The system design method used in this study is the Web Development Life Cycle (WDLC). The design stages in WDLC start from Planning, Analysis, Design and Development, Testing and Implementation and Maintenance. On the backend side for data management and reporting, a web-based system will be built with the PHP programming language using the YII2 PHP Framework. On the frontend side used by students is a mobile-based application (android) which will be built using the Ionic Framework. Data storage media uses MariaDB. The results of this study are a system that allows for monitoring students who study outside the classroom, especially students who participate in MBKM activities based on the history of activities reported at any time. Given the rapid development of technology and information today, the author suggests that it is necessary to develop the system, especially in terms of user interface, system availability in the form of applications (Android and iOS), and also increasing security, especially in terms of reading the location of student activities. The results of the test with the query Introduction to the environment, a visit to the village head's office to discuss future work programs obtained the results of the similarity level in Salsabilah Yahnun Fadila (21040203) which is 1%, Juliana Br Harianja (21040210) which is 0.7164%, Agung Dermansyah Nainggolan (21040257) which is 0.5978%, Lisman Buulolo (22090041) which is 0.4004% and Irwan Jaya Bawamenewi (21100251) which is 0.3645%. The time needed for this classification is 2.2471 minutes. For testing with the query Participating in community service activities/mutual cooperation, the results of the similarity level in Kristina Tutiniwati Ndruru (21100187) were 0.6111%, Alviusman Harita (21040253) was 0.5593%, Friska Sariaman Manalu (22070012) was 0.4735%. The time required for this classification was 1.2344 minutes.
Implementasi Metode ARAS dan Metode Pembobotan ROC untuk Pendukung Keputusan pada Seleksi Penerimaan Karyawan Baru Arini, Wulan; Sitepu, Yanti Peronika Br; Dewani, Dewani; Fitriani, Nopita; Sembiring, David JM; Ginting, Raheliya Br
Journal Global Technology Computer Vol 4 No 3 (2025): Agustus 2025
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/jogtc.v4i3.8225

Abstract

Employees are one of the most important assets in a company. Their crucial role extends beyond carrying out daily tasks, but also through contributing ideas, innovations, and solutions that can help the company grow. Problems in the recruitment process for new employees often arise due to the large number of applicants with diverse backgrounds, abilities, and experiences. If this problem is not resolved, companies could potentially recruit employees who do not meet the required qualifications. One solution is to implement a Decision Support System (DSS). A DSS is a computer-based system designed to assist decision-makers in solving semi-structured or unstructured problems. In its implementation, a DSS can be integrated with the Additive Ratio Assessment (ARAS) method. To ensure accuracy in the ARAS calculation process, appropriate criteria weighting is required. One such weighting method is Rank Order Centroid (ROC). The purpose of this study is to implement a combination of the ROC and ARAS weighting methods to build a decision support system that can assist companies in selecting new employees who meet predetermined criteria. The combination of the ROC and ARAS methods can be an appropriate solution to overcome the problem of subjectivity, accelerate the selection process, and improve the accuracy of decision-making in hiring new employees. The process obtained a score of 1.000 on A6, indicating that the new employee was selected in the new employee selection process.
Analisis Fungsi Implikasi Max-Min dalam Pengambilan Keputusan Penentuan Penduduk Kurang Mampu Menggunakan Metode Fuzzy Tsukamoto Ginting, Clusilla Via Mia Dalmatia Br; Agnesia, Mella; Rahayu, Cici; Ginting, Raheliya Br; Surbakti, Asprina Br
Jurnal Sains dan Teknologi Informasi Vol 4 No 4 (2025): September 2025
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/jussi.v4i4.8390

Abstract

Determining the underprivileged population is a crucial aspect in the distribution of social assistance to ensure it is targeted. Fuzzy logic methods, specifically the Tsukamoto Fuzzy Inference System (FIS), are capable of addressing uncertainty and subjectivity in the decision-making process. This study aims to analyze the application of the Max-Min implication function in the Tsukamoto fuzzy system to determine the category of underprivileged population based on income, number of dependents, and housing conditions. The results show that the use of the Max-Min implication function produces consistent, transparent, and reliable decisions to support government policy in distributing social assistance. Based on the test results, where Income = 1.5 million, Number of dependents = 5, and housing condition score = 4, the ability level of Mrs. Clu is included in the underprivileged category.
Sosialisasi Keamanan Data Menggunakan Teknologi Informasi pada Kantor Camat Batang Serangan Tarigan, Ita Margaretta Br; Ginting, Raheliya Br; Sinuhaji, Nirwan; Kaban, Roberto; Ginting, Puspita Sari Br; Wahyu, Muhammad; Siregar, Desi Nuri Anggita
Jurnal IPMAS Vol. 4 No. 2 (2024): Agustus 2024
Publisher : Pustaka Digital Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.54065/ipmas.4.2.2024.475

Abstract

Kegiatan pengabdian kepada masyarakat ini berupa sosialisasi tentang pentingnya menjaga keamanan data menggunakan Teknologi Informasi. Pengabdian ini bertujuan untuk membantu para masyarakat di Kantor Camat Batang Serangan agar memproleh informasi tentang kemajuan Teknologi Informasi dan bagaimana cara menjaga keamanan data agar tidak mudah dicuri dan dimanfaatkan oleh oknum-oknum yang tidak bertanggung jawab. Subjek pada kegiatan pengabdian ini adalah masyarakat beserta perangkat yang ada di Kantor Camat Batang Serangan. Metode dalam pengabdian masyarakat ini berupa sosialisasi yang dilakukan dengan pemberian informasi manfaat dan peran Teknologi Informasi dalam menjaga keamanan data dan cara pencegahan dalam menghadapi pencurian data seiring perkembangan Teknologi Informasi dimasa sekarang ini. Hasil dari kegiatan kepada masyarakat terlihat bahwa masih banyak masyarakat saat ini yang belum peka terhadap bahaya dari penyalahgunaan data dan infromasi, sehingga dengan adanya sosialisasi ini diharapkan dapat membantu masyarakat mendapatkan bekal pemanfaatan Teknologi Informasi yang dapat digunakan sebagai langkah preventif awal dalam mengamankan data dan informasi mereka tentunya dapat mengurangi kecemasan dalam melakukan akses internet khususnya dalam upaya mencari dan melakukan eksplor terhadap pengetahuan yang lebih luas. Berdasarkan dengan survey yang telah dilakukan sebelum dan sesudah proses pengadian didapatkan peningkatan pemahaman terhadap keamanan data tersebut dimana sebelum dilakukan pengabdian pemahaman masyarakat sebesar 75% dan setelah dilakukan sosialisasi pengetahuan meningkatn sebesar 83%. Terjadi peningkatan sebesar 8% yang menandakan bahwasannya sosialisasi berhasil dilakukan.
SMOTE and BERT Approaches for Handling Class Imbalance in Sentiment Analysis of the CoreTax Application on Big Data Ginting, Meiliyani Br; Surbakti, Asprina Br; Ilham, Safarul; Utomo, Dito Putro; Ginting, Raheliya Br
Building of Informatics, Technology and Science (BITS) Vol 7 No 2 (2025): September 2025
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v7i2.8310

Abstract

Coretax is a tax information system developed by the Directorate General of Taxes (DJP) to support digital and integrated tax administration processes, covering everything from taxpayer registration to reporting and auditing. Although it was designed to improve efficiency, transparency, and accuracy in tax management, its implementation has sparked mixed reactions among the public due to various technical challenges and the complexity of the annual tax reporting process. This situation highlights the need for a sentiment analysis that can objectively capture public perceptions of the system’s performance. In this study, Natural Language Processing (NLP) and Machine Learning techniques were applied to analyze 3,000 tweets from Twitter (X) related to Coretax. One of the main issues identified in the dataset is class imbalance, where positive sentiments significantly outnumber negative and neutral ones, leading to biased classification results. To address this issue, the Synthetic Minority Over-sampling Technique (SMOTE) was used to balance the dataset by generating synthetic samples for the minority classes. The BERT model was then employed for sentiment classification because of its strong ability to understand contextual meaning through its transformer-based architecture. Experimental results show that before applying SMOTE, the BERT model achieved an accuracy of 77%, which increased to 80% after SMOTE was implemented, along with improvements in precision, recall, and F1-score, particularly for the minority classes. These findings demonstrate that the combination of SMOTE and BERT significantly enhances the performance of sentiment analysis in understanding public responses to Coretax. This approach can serve as a valuable reference for evaluating and improving tax digitalization policies, ensuring they are more effective, inclusive, and responsive to public needs.