No abstract

The 21st Century learning is an effort to facilitate learners in the 21st century to experience the best learning experience so that they can achieve the learning objectives effectively. The 2013 curriculum is a shift in the 21st century education paradigm in Indonesia. One of the prominent features of 21st century learning is digital-based learning. Digital-based learning based on this research apply Learning Management System (LMS). The application of Machine Learning (Online Collaboration, Behavioural Tracking, and Learning Analytics) to LMS has great potential for realizing 21st century learning. The benefits of implementing machine learning are for LMS automation in the assessment of the 21st century learning process, making it easier for teachers to analyse learning outcomes. The purpose of this research is to create LMS model based on Machine Learning to support 21st Century Learning as the Implementation of Curriculum 2013. The utilization of machine learning shows positive result to 21st century learning process. Automated analysis can support the 21st century learning process.

The 21st century learning model is a way/technique used by teachers to facilitate the best child learning safeguard according to child’s condition, child’s learning environment, and carrying capacity. The characteristics of learner of the 21st century is important for teachers and parents to know how to facilitate their learning. Mitchel Resnick developed a Creative Learning Cycle method that promises to improve 21st century skills. Creative Learning Cycle method is suitable for elementary school. Creative Learning Cycle consists of 5 stages: Imagine, Create, Play, Share and Reflect. The purpose of this research is to create creative learning model as implementation of curriculum 2013 at elementary school in Bandung to reach 21st century skill. This study uses the correlation method between 21st century learning methods, 2013 curriculum, and 21st century skills. Creative Learning Model as a Learning Implementation of Curriculum 2013 has a positive effect on the achievement of 21st Century Skills students though not all of them have a significant influence.

Group development is the first and most important step for the success of collaborative problem solving (CPS) learning in the digital learning environment (DLE). A literacy study is needed for studies in the intelligent agent domain for group development of collaborative learning in DLE. This paper is a systematic literature review (SLR) of intelligent agents for group formation from 2001 to 2019. This paper aims to find answers to 4 (four) research questions, namely: 1) What components to develop intelligent agents for group development; 2) What is the intelligent agent model for group development; 3) How are the metrics for measuring intelligent agent performance; and 4) How is the Framework for developing intelligent agent. The components of the intelligent agent model consist of: member attributes, group attributes (group constraints), and intelligent techniques. This research refers to Srba and Bielikova's group development model. The stages of the model are formation, performing and closing. An intelligent agent model at the formation stage. A performance metric for the intelligent agent at the performance stage. The framework for developing an intelligent agent is a reference to the stages of development, component selection techniques, and performance measurement of an intelligent agent.

Abstrak -Bagi orang-orang yang bergerak di bidang fashion mengetahui tren fashion adalah hal yang penting. Salah satu cara untuk mengetahui tren adalah dengan mendeteksi topik mengenai fashion yang dibicarakan di media sosial. Penelitian ini mengimplementasikan algoritma Latent Dirichlet Allocation untuk mendeteksi topik fashion di Twitter. Tweet yang didapat, diklasifikasi dengan metode Naive Bayes lalu dibersihkan dengan cara menghapus URL, simbol, angka dan merubah setiap kata menjadi huruf kecil. Tweet lalu dibentuk menjadi kumpulan kata dan dikelompokan dengan algoritma Latent Dirichlet Allocation. Berdasarkan hasil eksperimen, konfigurasi paramater 20 topik dengan 1000 iterasi memperoleh skor UMass terbaik dengan nilai -56.342, dan konfigurasi parameter 50 topik dengan 1000 iterasi memperoleh skor PMI terbaik dengan nilai 6.272.