AGENTS: Journal of Artificial Intelligence and Data Science

The Application of Large Language Models in Sentiment Analysis for Presidential Candidate Elections

2024-12-13T05:56:25+00:00

The presidential candidate election in Indonesia is a hot topic on social media, especially Twitter. This study analyzes public sentiment regarding the 2024 presidential candidate election using the IndoBERT model, which is specifically designed for the Indonesian language, on a dataset of 8,442 tweets. This research follows the CRISP-DM methodology, which includes business understanding, data understanding, data preparation, modeling, evaluation, and deployment. The data was collected through crawling with keywords related to the election, followed by preprocessing and manual labeling before being processed by the model.

The results show that IndoBERT achieved an accuracy of 98%, with precision, recall, and F1-score also at 98% at the 10th epoch. Batch size evaluation indicated that a batch size of 4 yielded the best performance. This model is effective in classifying sentiment related to the 2024 presidential candidate election and serves as a useful tool for understanding public opinion.

The Application of the Human-Centered Design Method in Designing Psychological Services for Students of the Faculty of Science and Technology

2024-11-25T09:31:53+00:00

The Human-Centered Design method is a method used to better understand the comfort and ease of users when utilizing a service. This methodology is considered effective in focusing on the comfort and ease of users. In this research, the case study for the application of this method is psychological services for students of the Faculty of Science and Technology. This method is typically used in UI/UX design to help designers better understand users through the level of comfort and ease desired by users when using the service. This study aims to apply and test whether the Human-Centered Design method is effective in designing the psychological service created. The implementation of this Human-Centered Design method is expected to test whether it is suitable for use in designing psychological services for students of the Faculty of Science and Technology. The results of this study are expected to provide new insights into the application of the Human-Centered Design method in the case study of psychological services for students of the Faculty of Science and Technology and can be applied to other case studies.

Designing a Flashcard Game with a Time Tracker Feature for Early Childhood on Android Platform

2024-11-25T06:09:44+00:00

Early childhood is a golden period where the development of important aspects such as religious values, motor skills, cognitive abilities, and socio-emotional aspects begin to form. Early Childhood Education (ECE) plays a crucial role, with technology being a factor that influences children's education. This study aims to develop an Android-based educational game app using the flashcard method, which can stimulate children's cognitive development and help them understand basic concepts interactively. The app also includes a time tracker feature to facilitate learning. The research methodology involves collecting data from feedback provided by parents who observe their children while using the game. The data is analyzed based on parameters such as learnability, efficiency, memorability, errors, and satisfaction. The results show that the flashcard game app works well, and the app has been successfully designed to help children learn interactively and engagingly. This study emphasizes that technology, through educational games, can support early childhood learning more efficiently, helping children grasp basic concepts and enabling parents to monitor their child's development. The app is expected to be an effective solution in early childhood education in line with technological advancements.

ANALISIS SENTIMEN KOMENTAR PENGGUNA TERHADAP GAME MOBA LOKAPALA DI GOOGLE PLAY STORE MENGGUNAKAN ALGORITMA SUPPORT VECTOR MACHINE

2024-10-11T23:44:41+00:00

Di era modern ini, game banyak dipengaruhi oleh kemajuan teknologi. Perkembangan game yang semakin kompleks dan menawan dapat dimainkan secara terhubung menggunakan koneksi internet oleh jutaan pemain di seluruh dunia. Industri game di Indonesia menunjukkan perkembangan signifikan dengan munculnya berbagai game dari pengembang lokal, salah satunya Lokapala, game Multiplayer Online Battle Arena (MOBA) yang mengusung keunikan budaya Indonesia. Meskipun demikian, game ini menerima berbagai tanggapan dari pengguna di Google Play Store. Penelitian ini bertujuan untuk menganalisis sentimen pengguna terhadap game Lokapala di Google Play Store menggunakan algoritma Support Vector Machine (SVM). Data ulasan pengguna dikumpulkan dan dipra-proses melalui tahap-tahap seperti pembersihan data, tokenisasi, penghapusan stopwords, dan stemming. Setelah itu, fitur-fitur diekstraksi menggunakan metode TF-IDF. Hasil analisis menunjukkan bahwa SVM dengan kernel Radial Basis Function (RBF) berhasil mengklasifikasikan sentimen pengguna dengan akurasi sebesar 90% dari total 300 ulasan yang dianalisis. Proses ini tidak hanya membantu dalam memahami persepsi pengguna secara keseluruhan, tetapi juga mengidentifikasi aspek-aspek tertentu dari game yang mendapatkan apresiasi atau kritik. Dengan demikian, pengembang game dapat memanfaatkan hasil analisis ini untuk meningkatkan kualitas dan kepuasan pengguna, serta memperkuat daya saing game di pasar lokal maupun global.

Decision Support System Recommendations for Providing Social Aid with Multi Objective Optimization By Ratio Analysis (MOORA)

2024-04-16T03:15:38+00:00

Cash Direct Assistance (BLT) is one of the conditional assistance programs from the government as a form of poverty alleviation program. The selection process of potential recipients of BLT in Lamatti Riaja Village, Sinjai Regency, it is not entirely accurate as it is still done manually, resulting in many recipients not meeting the criteria. Based on this, research is conducted to design a decision support system that will facilitate the automatic checking of data for eligible residents who are entitled to BLT funds for each disbursement. This aims to make the selection process more objective, time-efficient, and minimize potential errors in selecting BLT recipients. In this research, the Multi Objective Optimization By Ratio Analysis (MOORA) method is employed. The calculation process utilizes the MOORA algorithm, and the implementation of the system is in the form of a website using the System Development Life Cycle design method, providing good and accurate results. The testing method used is Black Box testing. This research produces a Decision Support System website with the implementation of a data management subsystem using MySQL. The simulation results of the BLT recipient data calculation using the MOORA algorithm minimize errors in the selection process for potential BLT recipients.