scholarly journals Learning Behavior Analysis Using Clustering and Evolutionary Error Correcting Output Code Algorithms in Small Private Online Courses

2021 ◽  
Vol 2021 ◽  
pp. 1-11
Author(s):  
Shu-tong Xie ◽  
Qiong Chen ◽  
Kun-hong Liu ◽  
Qing-zhao Kong ◽  
Xiu-juan Cao
Keyword(s):  
Online Education ◽  
Behavior Analysis ◽  
Student Behavior ◽  
Feature Selection Method ◽  
Multiclass Classification ◽  
Classification Model ◽  
Learning Behavior ◽  
Teaching Activities ◽  
Education Data ◽  
Output Code

In recent years, online and offline teaching activities have been combined by the Small Private Online Course (SPOC) teaching activities, which can achieve a better teaching result. Therefore, colleges around the world have widely carried out SPOC-based blending teaching. Particularly in this year’s epidemic, the online education platform has accumulated lots of education data. In this paper, we collected the student behavior log data during the blending teaching process of the “College Information Technology Fundamentals” course of three colleges to conduct student learning behavior analysis and learning outcome prediction. Firstly, data collection and preprocessing are carried out; cluster analysis is performed by using k-means algorithms. Four typical learning behavior patterns have been obtained from previous research, and these patterns were analyzed in terms of teaching videos, quizzes, and platform visits. Secondly, a multiclass classification framework, which combines a feature selection method based on genetic algorithm (GA) with the error correcting output code (ECOC) method, is designed for training the classification model to achieve the prediction of grade levels of students. The experimental results show that the multiclass classification method proposed in this paper can effectively predict the grade of performance, with an average accuracy rate of over 75%. The research results help to implement personalized teaching for students with different grades and learning patterns.

scholarly journals Personalized Online Education Learning Strategies Based on Transfer Learning Emotion Classification Model

2021 ◽  
Vol 2021 ◽  
pp. 1-11
Author(s):  
Rongrong Wang ◽  
Zhengjie Shi
Keyword(s):  
Online Education ◽  
Learning Strategies ◽  
Transfer Learning ◽  
Student Behavior ◽  
Educational Process ◽  
Classification Model ◽  
Massive Data ◽  
Emotion Classification ◽  
Clickstream Data ◽  
Instructional Videos

Due to the epidemic, online course learning has become a major learning method for students worldwide. Analyzing its massive data from the massive online education platforms becomes a challenge because most learners watch online instructional videos. Thus, analyzing learners’ learning behaviors is beneficial to implement personalized online learning strategies with sentiment classification models. To this end, we propose a context-aware network model based on transfer learning that aims to predict learner performance by solving learners’ problems and improving the educational process, contributing to a comprehensive analysis of such student behavior and exploring various learning models in MOOC video interactions. In addition, we visualize and analyze MOOC video interactions, enabling course instructors and education professionals to analyze clickstream data generated by learners interacting with course videos. The experimental results show that, in the process of “massive data mining,” personalized learning strategies of this model can efficiently enhance students’ interest in learning and enable different types of students to develop personalized online education learning strategies.

Analisis Motivasi Belajar Siswa SMP Dalam Pembalajaran Outdoor-Modeling Mathematics Berdasarkan Gaya Belajar

2019 ◽  
Vol 2 (2) ◽  
Author(s):  
Sofnidar ◽  
Hartina ◽  
Kamid ◽  
Khairul Anwar
Keyword(s):  
Student Behavior ◽  
Mathematics Learning ◽  
Real Life ◽  
Data Retrieval ◽  
Learning Activities ◽  
Learning Activity ◽  
Stimulus Selection ◽  
Learning Behavior ◽  
Research Subjects ◽  
Motor Activities

Prilaku belajar adalah suatu sikap y ang muncul dari diri siswa dalam menanggapi dan meresponi setiap kegiatan belajar mengajar yang terjadi. salah satu wujud dari prilaku adalah motivasi belajar. Menurut teori behavioristik, belajar adalah perubahan tingkah laku sebagai akibat adanya interaksi antara stimulus (rangsangan) dan respon (tanggapan). Stimulus yang diberikan guru dalam pembelajaran tertuang dalam rancangan aktifitas pembelajaran. Aktivitas pembelajaran merupakan kegiatan yang dirancang guru untuk mewujudkan dan atau menciptkan kondisi belajar siswa (stimulus). Pemilihan aktivitas belajar yang sesuai memungkinkan untuk terjadinya efektivitas pedagogis dalam mencapai tujuan pembelajaran, maupun dapat membentuk prilaku positif siswa (respon) dalam belajar. Desain pembelajaran berbasis outdoor-medelling mathematics memuat serangkain aktivitas kegiatan pembelajaran yang berbassis investigasi konteks masalah outdoor (masalah real life) dengan muatan konten materi modeling mathematics. Pada makalah ini akan membahas prilaku belajar dan bagaimana motivasi terbentuk melaui aktifitas kegiatan pebelajaran outdoor-medelling mathematics yang diklasifikasikan menjadi motoractivities mentalactivities, visualactivities, emotionalactivities, motoractivitie.Melalui metode kulitatif deskriptif, dengan mengambil 20 siswa kelas IX-B SMP N 1 Muaro Jambi yang mempunyai gaya belajar visual, auditorial, dan kinestetik. Setelah pelaksanaan pembelajaran, pengambilan data dilakukan melalui angket, dan lembar pengamatan beserta wawancara ke subjek penelitian. Hasil penelitian menunjukan bahwa aktivitas belajar dalam pembelajaran yang dapat memotivasi siswa belajar matematika adalah visualactivities sebesar 74,16%; motoractivities sebesar 96,67%; mentalactivities sebesar 71,66%; dan emotionalactivities sebesar 73,33%. Berdasarkan hasil analisis yang dilakukan aktivitas belajar dalam pembelajaran outdoor-medelling mathematics matematika yang paling dominan dapat memotivasi siswa belajar adalah motoractivities dengan persentasi 96,67% dengan kriteria sangat baik dan sangat memotivasi siswa belajar matematika dalam pembelajaran luar kelas. Indikatornya adalah melakukan percobaan. Kelebihan aktivitas belajar dalam pembelajaran outdoor-medelling mathematics adalah, aktivitas belajar lebih membuat siswa termotivasi untuk belajar matematika. Siswa menjadi lebih aktif dan interaksi dengan teman sesamanya semakin meningkat juga. Adapun kelemahan aktivitas belajar dalam pembelajaran luar kelas adalah sulit untuk siswa terfokus dalam aktivitas belajar yang sedang dilakukan.   Learning behavior is an attitude that arises from students in responding and responding to each teaching and learning activity that occurs. one form of behavior is learning motivation. According to behavioristic theory, learning is a change in behavior as a result of an interaction between stimulus (stimulus) and response (response). The stimulus given by the teacher in learning is contained in the design of learning activities. Learning activities are activities designed by the teacher to realize and or create the conditions for student learning (stimulus). Selection of appropriate learning activities allows for the occurrence of pedagogical effectiveness in achieving learning goals, and can form positive student behavior (response) in learning. Outdoor-based learning mathematics learning design contains a series of learning activities based on the context of outdoor problems (real life problems) with the content of modeling mathematics material. In this paper will discuss learning behavior and how motivation is formed through the activities of learning activities outdoor-modeling mathematics which are classified into mental activities, visual activities, emotional activities, motor activities. Through the descriptive qualitative method, taking 20 students of class IX-B Muaro Jambi Middle School 1 who have visual, auditory, and kinesthetic learning styles. after the implementation of learning, data retrieval was carried out through questionnaires, and observation sheets and interviews to the research subjects. The results showed that learning activities in learning that could motivate students to learn mathematics were visual activities at 74.16%, motor activities at 96.67%, mental activities at 71.66%, and emotional activities at 73.33 %%. Based on the results of the analysis carried out learning activities in mathematics outdoor-modeling mathematics learning the most dominant motivating students to learn is motor activities with a percentage of 96.67% with very good criteria and very motivating students to learn mathematics in learning outside the classroom. The indicator is to experiment. The advantages of learning activities in outdoor-modeling mathematics learning are that learning activities make students more motivated to learn mathematics. Students become more active and interactions with their peers also increase. The weaknesses of learning activities in learning outside the classroom is difficult for students to focus on the learning activities that are being done.

scholarly journals Constructing an Emotion Estimation Model Based on EEG/HRV Indexes Using Feature Extraction and Feature Selection Algorithms

Sensors ◽  
2021 ◽  
Vol 21 (9) ◽  
pp. 2910
Author(s):  
Kei Suzuki ◽  
Tipporn Laohakangvalvit ◽  
Ryota Matsubara ◽  
Midori Sugaya
Keyword(s):  
Feature Selection ◽  
Single Channel ◽  
Feature Selection Method ◽  
Classification Model ◽  
Features Selection ◽  
Selection Methods ◽  
Emotion Classification ◽  
Model Based ◽  
Physiological Indexes ◽  
Emotion Estimation

In human emotion estimation using an electroencephalogram (EEG) and heart rate variability (HRV), there are two main issues as far as we know. The first is that measurement devices for physiological signals are expensive and not easy to wear. The second is that unnecessary physiological indexes have not been removed, which is likely to decrease the accuracy of machine learning models. In this study, we used single-channel EEG sensor and photoplethysmography (PPG) sensor, which are inexpensive and easy to wear. We collected data from 25 participants (18 males and 7 females) and used a deep learning algorithm to construct an emotion classification model based on Arousal–Valence space using several feature combinations obtained from physiological indexes selected based on our criteria including our proposed feature selection methods. We then performed accuracy verification, applying a stratified 10-fold cross-validation method to the constructed models. The results showed that model accuracies are as high as 90% to 99% by applying the features selection methods we proposed, which suggests that a small number of physiological indexes, even from inexpensive sensors, can be used to construct an accurate emotion classification model if an appropriate feature selection method is applied. Our research results contribute to the improvement of an emotion classification model with a higher accuracy, less cost, and that is less time consuming, which has the potential to be further applied to various areas of applications.

scholarly journals Historical Learning Behavior of High School Students During the Covid-19 Pandemic

2021 ◽  
Vol 2 (1) ◽  
pp. 21-34
Author(s):  
Muhammad Teguh ◽  
Wahidul Basri
Keyword(s):  
High School ◽  
High School Students ◽  
High School Teachers ◽  
Learning Process ◽  
Student Behavior ◽  
Learning Behavior ◽  
School Teachers ◽  
School Students ◽  
History Learning

This article was written with the aim of analyzing the behavior of high school students and all of their factors during history learning during the Covid-19 pandemic, so that knowing the history learning behavior of high school students and responses from high school teachers related to student behavior in the history learning process during the Covid-19 pandemic and analyzing how the reinforcement measures carried out by high school teachers towards students and the effect felt during online learning. The research method used was descriptive qualitative. The subjects of the study were research articles related to students' historical learning behavior during the Covid-19 pandemic, The sample of research articles is 26 journals consisting of national journals and international journals. The results of this study were 1) forms of student behavior in various history lessons; 2) student behavior is influenced by the creativity ability of teachers and the role of the family, and 3) The history teacher provides reinforcement during the online history learning process to students. The conclusion of this study is to maximize the history learning behavior of high school students during the pandemic has 5 (five) aspects learning and management of teaching in the Covid-19 era, know the benefits of learning history using Google classroom, increasing the effectiveness of the teaching and learning process during the Covid-19 Pandemic, the role of families in accompanying student, and increase student activeness in taking online learning.

Sign in / Sign up

Export Citation Format

Share Document