Cian Ramadhona Hassolthine
Cian Ramadhona Hassolthine has a total of 15 co-authors. Here are the top co-authors by number of shared publications:
- Muhammad Ikhwani Saputra
Universitas Siber Asia
2 shared publications - Riad Sahara
Universitas Siber Asia
2 shared publications - Syahid Abdullah
Universitas Siber Asia
2 shared publications - Ahmad Chusyairi
Universitas Siber Asia
1 shared publication - Dzaky Fatur Rahman
Universitas Multimedia Nusantara
1 shared publication Endang Yosa
Universitas Siber Asia
1 shared publication
Latest Publications
- Open Access
- 8 January 2026
- Published by Universitas Multimedia Nusantara in Ultimatics : Jurnal Teknik Informatika
- Vol. 17 (2) , 221-230
Design and Evaluation of an AI-Driven Gamified Intelligent Tutoring System for Fundamental Programming Using the Octalysis Framework
This research aims to address the challenges of student motivation and engagement in fundamental programming education by implementing the Octalysis Gamification Framework within an Intelligent Learning System. Traditional learning methods often fail to visualize abstract concepts or provide personalized feedback, leading to student demotivation. To overcome this, a platform named "Starcoder" was designed and built, integrating two conceptual pillars: the eight core drives of the Octalysis Framework and an AI-supported Intelligent Tutoring System (ITS). The system employs the Next.js framework and integrates the Gemini AI API (M.E.C.H.A.) to provide real-time, adaptive feedback and remedial learning paths. The effectiveness of the platform was evaluated using the Hedonic-Motivation System Adoption Model (HMSAM) with 54 respondents, comparing the gamified platform against traditional classroom methods. Evaluation results demonstrate that the platform significantly outperforms traditional methods, achieving an 86.44% score in Perceived Usefulness and an 85.56% score in Curiosity. Notably, Behavioral Intention to Use increased by 15.56% compared to the baseline. These findings demonstrate that the comprehensive integration of gamification frameworks with generative AI agents effectively enhances student motivation and immersion in technical education. Future work should focus on expanding the AI's capability to dynamically adjust gamification elements in real-time based on student performance.
- 8 January 2026
- Published by Universitas Multimedia Nusantara in Ultimatics : Jurnal Teknik Informatika
- Vol. 17 (2) , 221-230
Open AccessDesign and Evaluation of an AI-Driven Gamified Intelligent Tutoring System for Fundamental Programming Using the Octalysis Framework
This research aims to address the challenges of student motivation and engagement in fundamental programming education by implementing the Octalysis Gamification Framework within an Intelligent Learning System. Traditional learning methods often fail to visualize abstract concepts or provide personalized feedback, leading to student demotivation. To overcome this, a platform named "Starcoder" was designed and built, integrating two conceptual pillars: the eight core drives of the Octalysis Framework and an AI-supported Intelligent Tutoring System (ITS). The system employs the Next.js framework and integrates the Gemini AI API (M.E.C.H.A.) to provide real-time, adaptive feedback and remedial learning paths. The effectiveness of the platform was evaluated using the Hedonic-Motivation System Adoption Model (HMSAM) with 54 respondents, comparing the gamified platform against traditional classroom methods. Evaluation results demonstrate that the platform significantly outperforms traditional methods, achieving an 86.44% score in Perceived Usefulness and an 85.56% score in Curiosity. Notably, Behavioral Intention to Use increased by 15.56% compared to the baseline. These findings demonstrate that the comprehensive integration of gamification frameworks with generative AI agents effectively enhances student motivation and immersion in technical education. Future work should focus on expanding the AI's capability to dynamically adjust gamification elements in real-time based on student performance.
- Open Access
- 30 June 2025
- Published by Universitas Multimedia Nusantara in IJNMT (International Journal of New Media Technology)
- Vol. 12 (1) , 55-60
E-Commerce Product Review Sentiment Analysis: A Comparative Study of Naïve Bayes Classifier and Random Forest Algorithms on Marketplace Platforms
Achieving customer satisfaction and trust is a major challenge for success in the business world. Entrepreneurs must identify problems that arise from reviews given by customers. However, reading and sorting each review is time-consuming and considered inefficient. In order to overcome this, a study was conducted that aims to analyze sentiment on products sold in the Shopee marketplace using the Naïve Bayes Classifier and Random Forest algorithms. The focus of this study is on product reviews from XYZ Store. The main objective of this study is to determine a more accurate and efficient algorithm in classifying review sentiment, which can help companies in marketing strategies and product development. The results of this study can provide insight for companies about consumer responses to marketed products, so that they can be used as a basis for making strategic decisions to improve the quality of services and products. The results of the Random Forest method classification produce superior predictions compared to the Naïve Bayes Classifier method with an accuracy value of 92.5%, precision of 93%, Recall of 92.5% and F1-Score of 90%.
- 30 June 2025
- Published by Universitas Multimedia Nusantara in IJNMT (International Journal of New Media Technology)
- Vol. 12 (1) , 55-60
Open AccessE-Commerce Product Review Sentiment Analysis: A Comparative Study of Naïve Bayes Classifier and Random Forest Algorithms on Marketplace Platforms
Achieving customer satisfaction and trust is a major challenge for success in the business world. Entrepreneurs must identify problems that arise from reviews given by customers. However, reading and sorting each review is time-consuming and considered inefficient. In order to overcome this, a study was conducted that aims to analyze sentiment on products sold in the Shopee marketplace using the Naïve Bayes Classifier and Random Forest algorithms. The focus of this study is on product reviews from XYZ Store. The main objective of this study is to determine a more accurate and efficient algorithm in classifying review sentiment, which can help companies in marketing strategies and product development. The results of this study can provide insight for companies about consumer responses to marketed products, so that they can be used as a basis for making strategic decisions to improve the quality of services and products. The results of the Random Forest method classification produce superior predictions compared to the Naïve Bayes Classifier method with an accuracy value of 92.5%, precision of 93%, Recall of 92.5% and F1-Score of 90%.
- Open Access
- 30 April 2025
- Published by Universitas Dhyana Pura in Jurnal Teknologi Informasi dan Komputer
- Vol. 11 (1) , 26-33
KLASIFIKASI PRESTASI AKADEMIK PESERTA DIDIK DENGAN METODE MACHINE LEARNING DI SMP X
Machine learning (ML) is a field of science that focuses on designing and developing algorithmic models to create behavior based on available data. Academic achievement is a metric used for the assessment of quality educational institutions. By using academic data of students in SMP X and machine learning classification algorithms such as Random Forest, Naïve Bayes, k-Nearest Neighbors (k-NN), and Support Vector Machine (SVM), so that this research can classify the academic achievement of students in SMP X optimally seen from the comparison of the best accuracy rate among classification algorithms. The accuracy of an algorithm is a measure of how precisely it classifies a sample. Evaluation results are compared in the form of validation accuracy and standard deviation. The comparison is done to determine the best algorithm based on accuracy and stability. The results showed that the SVM algorithm has the highest validation accuracy with a value of 0.987410 which shows the best performance in predicting classes and the lowest standard deviation value of 0.005132 which shows a more stable and consistent performance, compared to other algorithms. This indicates that SVM excels in predicting the correct class with stable performance. Based on the results and analysis, it is concluded that the selected SVM algorithm is used to develop a classification model of students' academic achievement in the form of a python program that is still simple but has high accuracy, stable and consistent. This program has become a tool for SMP X in identifying students' academic achievement and as a material for reporting students' learning outcomes to parents.
- 30 April 2025
- Published by Universitas Dhyana Pura in Jurnal Teknologi Informasi dan Komputer
- Vol. 11 (1) , 26-33
Open AccessKLASIFIKASI PRESTASI AKADEMIK PESERTA DIDIK DENGAN METODE MACHINE LEARNING DI SMP X
Machine learning (ML) is a field of science that focuses on designing and developing algorithmic models to create behavior based on available data. Academic achievement is a metric used for the assessment of quality educational institutions. By using academic data of students in SMP X and machine learning classification algorithms such as Random Forest, Naïve Bayes, k-Nearest Neighbors (k-NN), and Support Vector Machine (SVM), so that this research can classify the academic achievement of students in SMP X optimally seen from the comparison of the best accuracy rate among classification algorithms. The accuracy of an algorithm is a measure of how precisely it classifies a sample. Evaluation results are compared in the form of validation accuracy and standard deviation. The comparison is done to determine the best algorithm based on accuracy and stability. The results showed that the SVM algorithm has the highest validation accuracy with a value of 0.987410 which shows the best performance in predicting classes and the lowest standard deviation value of 0.005132 which shows a more stable and consistent performance, compared to other algorithms. This indicates that SVM excels in predicting the correct class with stable performance. Based on the results and analysis, it is concluded that the selected SVM algorithm is used to develop a classification model of students' academic achievement in the form of a python program that is still simple but has high accuracy, stable and consistent. This program has become a tool for SMP X in identifying students' academic achievement and as a material for reporting students' learning outcomes to parents.
- Open Access
- 1 November 2024
- Published by STMIK Lombok in Jurnal Informatika dan Rekayasa Elektronik
- Vol. 7 (2) , 293-300
EMPLOYEE CREDIT CLASSIFICATION ANALYSIS USING DECISION TREE BASED CRISP-DM MODEL (CASE STUDY OF SAMSUNG INDONESIA COMPANY)
Employee credit program is a form of employee retention as an effort to retain potential employees from the company. In its implementation, providing employee credit is not without risks that may occur. These risks include the inability or failure to pay credit installments when due. To minimize the risks that may occur, a survey and analysis with the right method is needed for cooperative members before providing employee credit. Researchers will use a Decision Tree-based algorithm as a tool for decision making in providing employee credit to Cooperatives at Samsung Indonesia Company. Researchers also use the CRoss-Industry Standard Process for Data Mining (CRISP-DM) model on the data mining development life cycle as a research step taken. This CRISP-DM model is very appropriate to use because it is a neutral model or method and can be used in various industries and combined with various tools. From the measurements that have been carried out using a sample data of 10 records from a total of 584 records, a classification model of 2 employees with non-performing employee credit status and 8 employees with performing employee credit status was obtained. The classification model was obtained based on the Gini Index Value of the Employee ID, Division, and Position attributes are 0.7, 0.3428571, and 0.2714286, respectively. So, the decision to grant credit to employees depends on the Position, after that the Division, and the last is the ID of the employee.
- 1 November 2024
- Published by STMIK Lombok in Jurnal Informatika dan Rekayasa Elektronik
- Vol. 7 (2) , 293-300
Open AccessEMPLOYEE CREDIT CLASSIFICATION ANALYSIS USING DECISION TREE BASED CRISP-DM MODEL (CASE STUDY OF SAMSUNG INDONESIA COMPANY)
Employee credit program is a form of employee retention as an effort to retain potential employees from the company. In its implementation, providing employee credit is not without risks that may occur. These risks include the inability or failure to pay credit installments when due. To minimize the risks that may occur, a survey and analysis with the right method is needed for cooperative members before providing employee credit. Researchers will use a Decision Tree-based algorithm as a tool for decision making in providing employee credit to Cooperatives at Samsung Indonesia Company. Researchers also use the CRoss-Industry Standard Process for Data Mining (CRISP-DM) model on the data mining development life cycle as a research step taken. This CRISP-DM model is very appropriate to use because it is a neutral model or method and can be used in various industries and combined with various tools. From the measurements that have been carried out using a sample data of 10 records from a total of 584 records, a classification model of 2 employees with non-performing employee credit status and 8 employees with performing employee credit status was obtained. The classification model was obtained based on the Gini Index Value of the Employee ID, Division, and Position attributes are 0.7, 0.3428571, and 0.2714286, respectively. So, the decision to grant credit to employees depends on the Position, after that the Division, and the last is the ID of the employee.
- Open Access
- 26 February 2024
- Published by Sekolah Tinggi Manajemen Informatika dan Komputer Jayakarta in Journal of Information System, Applied, Management, Accounting and Research
- Vol. 8 (1) , 161-174
IMPLEMENTASI ALGORITMA DECISION TREE DALAM OPTIMASI PENILAIAN KINERJA OPERASIONAL
Companies nowadays derive significant benefits from adopting digital systems in their operations. Politeknik LP3I Jakarta, for example, an educational institution, has implemented digitalization to optimize operational performance assessments by auditors. Manual audit assessments consume significant time and effort. Applying intelligent algorithms, such as Decision Tree, has become key to enhancing efficiency and accuracy in decision-making during assessments. The objective of this research is to evaluate the effectiveness of operational performance assessments by identifying and addressing these issues, implementing the Decision Tree algorithm. Decision Tree, which has evolved through a series of algorithms like C5.0, is the appropriate choice as it can make decisions based on specific conditions from the input data. The Decision Tree method and C5.0 Algorithm will help in rapidly and accurately calculating assessments based on criteria. This implementation can minimize manual audit activities, save time, and improve the accuracy of operational performance evaluations. The outcome of this research is higher efficiency in the operational performance assessment process, allowing auditors to focus on strategic aspects and in-depth analysis. Thus, Politeknik LP3I Jakarta and similar institutions can experience positive impacts from technology integration in their operational management, supporting progress and enhancing the quality of educational services.
- 26 February 2024
- Published by Sekolah Tinggi Manajemen Informatika dan Komputer Jayakarta in Journal of Information System, Applied, Management, Accounting and Research
- Vol. 8 (1) , 161-174
Open AccessIMPLEMENTASI ALGORITMA DECISION TREE DALAM OPTIMASI PENILAIAN KINERJA OPERASIONAL
Companies nowadays derive significant benefits from adopting digital systems in their operations. Politeknik LP3I Jakarta, for example, an educational institution, has implemented digitalization to optimize operational performance assessments by auditors. Manual audit assessments consume significant time and effort. Applying intelligent algorithms, such as Decision Tree, has become key to enhancing efficiency and accuracy in decision-making during assessments. The objective of this research is to evaluate the effectiveness of operational performance assessments by identifying and addressing these issues, implementing the Decision Tree algorithm. Decision Tree, which has evolved through a series of algorithms like C5.0, is the appropriate choice as it can make decisions based on specific conditions from the input data. The Decision Tree method and C5.0 Algorithm will help in rapidly and accurately calculating assessments based on criteria. This implementation can minimize manual audit activities, save time, and improve the accuracy of operational performance evaluations. The outcome of this research is higher efficiency in the operational performance assessment process, allowing auditors to focus on strategic aspects and in-depth analysis. Thus, Politeknik LP3I Jakarta and similar institutions can experience positive impacts from technology integration in their operational management, supporting progress and enhancing the quality of educational services.
- Open Access
- 13 February 2024
- Published by Yayasan Rahmatan Fiddunya Wal Akhirah in JEKIN - Jurnal Teknik Informatika
- Vol. 4 (1) , 1-9
Prediksi Harga Steel Hot-Rolled Dengan Model Recurement Neural Network
Steel Hot-rolled Coil atau yang biasa disebut dengan sebutan Baja Canai Panas merupakan sebuah produk baja yang dihasilkan dengan proses penggulungan di dalam suhu yang sangat tinggi. Sebagai bahan baku utama dunia yang sering dipakai dalam pembuatan konstruksi bangunan, jembatan, rel kereta api, dan keperluan otomotif sehingga harga Steel Hot-rolled Coil sangat fluktuatif dan sering kali membuat perencanaan pembelian menjadi tidak efektif. Oleh karena itu, diusulkan sebuah metode prediksi harga Steel Hot-rolled Coil dengan mempelajari pola dan tingkah laku pada data time series harga yang sudah lampau. Metode yang direkomendasikan pada penelitian ini yaitu prediksi harga Steel Hot-rolled Coil dengan menggunakan salah satu arsitektur Artificial Neural Network (ANN) yaitu Recurrent Neural Network (RNN). Dengan semakin optimal model yang dibangun maka semakin tinggi akurasi yang didapatkan. Parameter RNN yang optimal dapat diperoleh dengan algoritma optimasi RMSProp (Root Mean Square Propagation). Dari proses pelatihan dan pengujian, didapatkan akurasi terbaik sebesar 90.90% pada data latih dan 91.02% pada data uji.
- 13 February 2024
- Published by Yayasan Rahmatan Fiddunya Wal Akhirah in JEKIN - Jurnal Teknik Informatika
- Vol. 4 (1) , 1-9
Open AccessPrediksi Harga Steel Hot-Rolled Dengan Model Recurement Neural Network
Steel Hot-rolled Coil atau yang biasa disebut dengan sebutan Baja Canai Panas merupakan sebuah produk baja yang dihasilkan dengan proses penggulungan di dalam suhu yang sangat tinggi. Sebagai bahan baku utama dunia yang sering dipakai dalam pembuatan konstruksi bangunan, jembatan, rel kereta api, dan keperluan otomotif sehingga harga Steel Hot-rolled Coil sangat fluktuatif dan sering kali membuat perencanaan pembelian menjadi tidak efektif. Oleh karena itu, diusulkan sebuah metode prediksi harga Steel Hot-rolled Coil dengan mempelajari pola dan tingkah laku pada data time series harga yang sudah lampau. Metode yang direkomendasikan pada penelitian ini yaitu prediksi harga Steel Hot-rolled Coil dengan menggunakan salah satu arsitektur Artificial Neural Network (ANN) yaitu Recurrent Neural Network (RNN). Dengan semakin optimal model yang dibangun maka semakin tinggi akurasi yang didapatkan. Parameter RNN yang optimal dapat diperoleh dengan algoritma optimasi RMSProp (Root Mean Square Propagation). Dari proses pelatihan dan pengujian, didapatkan akurasi terbaik sebesar 90.90% pada data latih dan 91.02% pada data uji.
- Open Access
- 6 February 2024
- Published by Sekolah Tinggi Manajemen Informatika dan Komputer Jayakarta in Journal of Information System, Applied, Management, Accounting and Research
- Vol. 8 (1) , 118-127
Pembuatan Aplikasi Chatbot Faq Untuk Motionbank
Currently, Frequently Asked Questions (FAQ) are used to address common questions often asked by users. However, users frequently avoid reading FAQ as they are considered less efficient in providing answers to common queries. The objective of this research is to enhance Customer Service Efficiency and provide Quick and Consistent Responses. Therefore, a FAQ Chatbot is needed to improve customer service efficiency and offer prompt responses to frequently asked questions in the MotionBank application. The FAQ Chatbot is an interactive system designed to deliver quick and accurate answers to common user queries. By utilizing artificial intelligence through Natural Language Processing methods on the Dialogflow platform, the FAQ Chatbot can automatically comprehend questions and respond with fast, relevant information, providing more responsive customer service. The research results indicate that the FAQ Chatbot application is capable of addressing frequently asked questions posed by users. The application also offers an interactive experience, responding quickly to common questions and assisting users in obtaining information related to MotionBank.
- 6 February 2024
- Published by Sekolah Tinggi Manajemen Informatika dan Komputer Jayakarta in Journal of Information System, Applied, Management, Accounting and Research
- Vol. 8 (1) , 118-127
Open AccessPembuatan Aplikasi Chatbot Faq Untuk Motionbank
Currently, Frequently Asked Questions (FAQ) are used to address common questions often asked by users. However, users frequently avoid reading FAQ as they are considered less efficient in providing answers to common queries. The objective of this research is to enhance Customer Service Efficiency and provide Quick and Consistent Responses. Therefore, a FAQ Chatbot is needed to improve customer service efficiency and offer prompt responses to frequently asked questions in the MotionBank application. The FAQ Chatbot is an interactive system designed to deliver quick and accurate answers to common user queries. By utilizing artificial intelligence through Natural Language Processing methods on the Dialogflow platform, the FAQ Chatbot can automatically comprehend questions and respond with fast, relevant information, providing more responsive customer service. The research results indicate that the FAQ Chatbot application is capable of addressing frequently asked questions posed by users. The application also offers an interactive experience, responding quickly to common questions and assisting users in obtaining information related to MotionBank.
- Open Access
- 30 June 2023
- Published by Universitas Siber Asia in Jurnal Masyarakat Siber (JMS)
- Vol. 2 (1) , 9-11
Sosialisasi Blended Learning Sebagai Media Pembelajaran Daring
Kegiatan pengabdian ini dilatarbelakangi oleh ketertarikan peneliti untuk melihat permasalahan pada saat pembelajaran online berlangsung. Banyak hasil pembelajaran siswa yang rendah karena banyaknya tugas yang diberikan oleh guru pada semua mata pelajaran sehingga menumpuk yang mengakibatkan siswa menjadi lelah, tidak antusias dalam belajar dan menjadikan hasil belajar siswa menjadi menurun. Tujuan dari pengabdian ini adalah menjelaskan dan mendeskripsikan bagaimana penerapan metode blended learning di SMA Islam Al Khalidin dan apa kendala yang dihadapi selama pelaksanaan blended learning di SMA Islam Al Khalidin. Dalam kegiatan tersebut, tim menyampaikan materi tentang blended learning kepada para peseta. Dengan diadakannya sosialisasi ini, guru dan siswa mengerti model pembelajaran lain yang lebih menyenangkan, guru juga dapat menyusun pembelajaran menjadi komponen ajar yang berkesinambungan antara materi yang diajar secara daring maupun luring. Dari pelatihan yang sudah dilaksanakan, peserta mendapatkan peningkatan pengetahuan mengenai blended learning dilihat dari pretest sebesar 72% dan posttest sebesar 78%.
- 30 June 2023
- Published by Universitas Siber Asia in Jurnal Masyarakat Siber (JMS)
- Vol. 2 (1) , 9-11
Open AccessSosialisasi Blended Learning Sebagai Media Pembelajaran Daring
Kegiatan pengabdian ini dilatarbelakangi oleh ketertarikan peneliti untuk melihat permasalahan pada saat pembelajaran online berlangsung. Banyak hasil pembelajaran siswa yang rendah karena banyaknya tugas yang diberikan oleh guru pada semua mata pelajaran sehingga menumpuk yang mengakibatkan siswa menjadi lelah, tidak antusias dalam belajar dan menjadikan hasil belajar siswa menjadi menurun. Tujuan dari pengabdian ini adalah menjelaskan dan mendeskripsikan bagaimana penerapan metode blended learning di SMA Islam Al Khalidin dan apa kendala yang dihadapi selama pelaksanaan blended learning di SMA Islam Al Khalidin. Dalam kegiatan tersebut, tim menyampaikan materi tentang blended learning kepada para peseta. Dengan diadakannya sosialisasi ini, guru dan siswa mengerti model pembelajaran lain yang lebih menyenangkan, guru juga dapat menyusun pembelajaran menjadi komponen ajar yang berkesinambungan antara materi yang diajar secara daring maupun luring. Dari pelatihan yang sudah dilaksanakan, peserta mendapatkan peningkatan pengetahuan mengenai blended learning dilihat dari pretest sebesar 72% dan posttest sebesar 78%.