• International Journal of Computer Science & Network Security
• /
• v.21 no.1
• /
• pp.1-5
• /
• 2021

Cyberbullying is a problem that is faced in many cultures. Due to their popularity and interactive nature, social media platforms have also been affected by cyberbullying. Social media users from Arab countries have also reported being a target of cyberbullying. Machine learning techniques have been a prominent approach used by scientists to detect and battle this phenomenon. In this paper, we compare different machine learning algorithms for their performance in cyberbullying detection based on a labeled dataset of Arabic YouTube comments. Three machine learning models are considered, namely: Multinomial Naïve Bayes (MNB), Complement Naïve Bayes (CNB), and Linear Regression (LR). In addition, we experiment with two feature extraction methods, namely: Count Vectorizer and Tfidf Vectorizer. Our results show that, using count vectroizer feature extraction, the Logistic Regression model can outperform both Multinomial and Complement Naïve Bayes models. However, when using Tfidf vectorizer feature extraction, Complement Naive Bayes model can outperform the other two models.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.9 no.4
• /
• pp.111-118
• /
• 2013

Today, universities in Korea give a great effort to complement basic college scholastic ability of freshman. Maybe it could be unnecessary effort from university. However, we cannot just leave students who have poor academic performance about 10 to 30% in a university. Universities have to prepare to solve this problem. Thus government and universities investigate a lot of efforts but there is no guarantee. As a result, e-learning could be the best solution to complement poor academic performance of freshman and it also could be the best way to reduce financial burden of university. So, many universities introduce e-learning system and they also support professors to make e-learning content. We need to promote content usage and to improve overall operations. In this paper, we discuss poor academic performance problems under the current middle and high school education systems and review approaches to solve these problems. From this analysis, we propose the design of an effective e-learning system and a method of operation to complement students who achieve poor academic performance.

• Journal of Elementary Mathematics Education in Korea
• /
• v.20 no.2
• /
• pp.193-213
• /
• 2016

This study has two goals. The First is to develop and apply a step-by-step program and the degree to which students' mathematical skills. The second is to analyze mathematical attitude change around the first grade students was done. The program for learning complement number is composed of series of 5 steps and 11 classes. Play for learning complement number, taking into account the difficulty of the learning steps 1-5 are organized. First step is composed of the classes which fragmented pieces of shapes to complete the entire geometry with fun activities for the entire part of the concept of learning and it maintenance concepts and can naturally learn by associating step. In second step, tools to take advantage of the real world and collecting the conservative concept. 3rd steps is to repair the mathematical concept of the parish in the learning stage of expansion. 4th step is halrigalri, number cards, making ten games etc. 5th step is to verify the concept of complement number and number operation ability. The concept of complement number through fun activities can improve students' mathematical skills, and mathematical attitude change. Early in the program, students use the finger to throw acid in the process. Simple addition and subtraction calculations may take a long time and error, but more and more we progress through the program using the fingers is eliminated and a more complex form calculations was not difficult to act out.

• Proceedings of KOSOMES biannual meeting
• /
• 2017.04a
• /
• pp.99-99
• /
• 2017

• Journal of the Korean association of regional geographers
• /
• v.23 no.1
• /
• pp.213-226
• /
• 2017

Geography textbooks and atlases are typical printed materials broadly used in the classroom and the public education as certified materials. The students' atlas, as supplementary materials, is useful in teaching and learning geography in the classroom. This study examines and evaluates the supplementary role of the students' atlas in the institutional and pedagogical perspectives. The textbook and the atlas were written by different writers and publishers based on the interpretation of the geography curriculum, the pedagogical beliefs and interests. The textbook is submitted to be certificated by Ministry of Education. Then the textbook and the atlas which is passed in the certification process can be distributed to schools to use in the classroom. Most maps and materials are supplied in the textbook and the atlas variously depended on the authors' interpretation of geography curriculum, which are designed complementally. But, that maps and materials of respective book of even different author are similar and duplicated. Sometimes maps and materials of textbook and atlas are independent, not mutual complement. It needed that geography textbook and student's atlas take a efficient role supplementarily in these certification system of textbook.

• International Journal of Internet, Broadcasting and Communication
• /
• v.12 no.1
• /
• pp.104-110
• /
• 2020

In the 4th Industrial Revolution, the competitiveness of the software industry is important, and as a solution to fundamentally secure the competitiveness of the software industry, education classes should be provided to educate high quality software personnel in educational institutions. Despite this social situation, software-related classes in universities are largely composed of competitive or individual learning structures. Cooperative learning is a learning model that can complement the problems of competitive and individual learning. Cooperative learning is more effective in improving academic achievement than individual or competitive learning. In addition, most learners have the advantage of having a more desirable self-image by having a successful experience. In this paper, we apply a pair check model, which is a type of cooperative learning, in operating system classes. In addition, the class procedure and instruction plan are designed to apply the pair check model. We analyze the test results to analyze the performance of the cooperative learning model.

• Proceedings of the Korean Information Science Society Conference
• /
• 2004.04b
• /
• pp.568-570
• /
• 2004

The error-backpropagation (EBP) algerithm for training multilayer perceptrons (MLPs) is known to have good features of robustness and economical efficiency. However, the algorithm has difficulty in selecting an optimal constant learning rate and thus results in non-optimal learning speed and inflexible operation for working data. This paper Introduces an elastic learning rate that guarantees convergence of learning and its local realization by online upoate of MLP parameters Into the original EBP algorithm in order to complement the non-optimality. The results of experiments on a speaker verification system with Korean speech database are presented and discussed to demonstrate the performance improvement of the proposed method in terms of learning speed and flexibility fer working data of the original EBP algorithm.

• Journal of applied mathematics & informatics
• /
• v.37 no.3_4
• /
• pp.271-279
• /
• 2019

We investigate how a feedforward neural network works to separate a geometric region from its complement. Our investigations are restricted to regions in ${\mathbb{R}}$ or ${\mathbb{R}}^2$ including an interval, a triangular region, a disk and the union of two disjoint disks. We also examine what happens at each layer of the network.

• Journal of The Korean Association of Information Education
• /
• v.12 no.1
• /
• pp.89-97
• /
• 2008

The purpose of this study was to design a system of web-based discovery learning and testify its effectiveness, in order to complement the difficulties of discovery learning considered to be hard to be applied to the school education because of shortage of time and materials, though discovery learning is one of inquiry learning emphasized in the 7th national curriculum of elementary science. As for the process of testifying, it compared the differences between comparative group with normal discovery learning model and experimental group with web-based system of discovery learning model, targeting the subject of extending spring among the 4th grade science. As a result, the experimental group achieved higher academic performance compared to the comparative group applied to the normal discovery learning model.

• Journal of Digital Convergence
• /
• v.16 no.7
• /
• pp.123-129
• /
• 2018

This study aims m-learning based on UTAUT and learners' satisfaction For empirical analysis, a survey was conducted on 289 university students and SPSS 22.0, AMOS 21.0 were used. The result of structual equation modeling analysis are as follows: First, performance expectancy was influenced by security, diversity, economics. Second, performance expectancy, effort expectancy affect learners' satisfaction. This research provide practical guidance in m-learning based on UTAUT amd the limltation of this research and future study are discussed. In the future, variables of m-learning based on UTAUT including the general public besides university students will be complement to analyze.