• Proceedings of the Korea Information Processing Society Conference
• /
• 2016.10a
• /
• pp.323-326
• /
• 2016

웹 서비스를 기반으로 이루어진 MOOC(Massive Open Online Course)는 대규모 학습자에게 공개된 온라인 교육이다. MOOC는 교수와 학습자 사이 커뮤니티를 통해 상호 참여적으로 수업을 진행한다. 그러나 무료로 강의를 들을 수 있고 성적을 내지 않기 때문에 학습자들에게 큰 동기 부여가 되지 않아 등록하는 학습자는 많지만 수료하는 학습자는 현저히 적게 나타났다. 본 논문은 이러한 문제 해결 방안 마련을 위해 KDD Cup 2015에서 제공한 MOOC 데이터를 통해 중도 포기와 관련된 변수들을 선정하였으며, Decision Tree, KNN, Logistic Regression, Naive Bayesian, SVM, Neural Network인 6가지 머신 러닝 알고리즘을 통해 데이터 예측의 정확률을 확인하였다. 그 결과 Naive Bayesian이 89.3%로 가장 높은 정확률을 보였다. 본 연구를 통해 중도포기를 정확히 예측하며, 향후 학습자들에게 특정 동기부여의 효과로 학습을 수료하는 결과를 기대할 수 있다.

• Journal of the Korea Society of Computer and Information
• /
• v.17 no.1
• /
• pp.105-115
• /
• 2012

This study paid attention to the possibility of broadcasting contents as a learning resource, which promoted the knowledge composition and the process of creation from the software having enriched contents not a delivering tool for the information in one direction. and tried to implement it thru e-PBL, which is one of teaching-learning models in e-learning. In order to implement the possibility of broadcasting contents in the e-PBL enviroment as a learning resource, the study focused on the design and development of e-PBL based on the broadcasting contents and found out the educational possibility for the broadcasting contents as the learning resource in e-PBL enviroment. This study focused on the design of learning module and development process which integrated strategic plans to maximize the utilization of broadcasting contents including development of online learning community. Also, This is verified by applying the learning module was to prove a differentiation.

• Korean Journal of Childcare and Education
• /
• v.10 no.1
• /
• pp.5-26
• /
• 2014

This study examined the effects of web-based learning experiences, learning style, and Internet self-efficacy that influence beginning child care teachers belief about web-based learning. The participants were 215 beginning child care teachers who work in child care centers. Data were analyzed by means of frequency analysis, correlation, and multiple regression for SPSS windows. The results were as follows: First, significant statistical differences were detected in web-based learning experiences and beliefs about web-based learning. Online teacher learning community use and frequency were significant gaps in beliefs about web-based learning. Second, there were statistical differences in learning styles and beliefs about web-based learning. And teachers with assimilator learning style showed high difficulty beliefs about web-based learning. Third, teachers' belief about web-based learning was significantly related to Internet self-efficacy. It means that teachers that have high Internet self-efficacy show high belief about web-based learning. Forth, among the teachers' personal variables, a higher level of online teacher learning community use and Internet self-efficacy predicted higher beliefs about web-based learning. Thus, this study suggested the importance of web-based learning experiences and Internet self-efficacy to beliefs about web-based learning. And it implicated ways to improve positive beliefs about web-based learning of beginning child care teachers.

• Journal of The Korean Association of Information Education
• /
• v.9 no.3
• /
• pp.473-482
• /
• 2005

We think that the class homepage can be solution for the problems in the cyber space or on-line community because students can practice activities in the on-line community, communicate with teachers or colleague, exchange opinions with parents and use it for learning. However, students would lose interest easily in the existing class homepage for lack of its immersion elements as compared with the commercial on-line communities. The class homepage needs to have immersion elements to reach its purpose. It is one of the solutions to use the avatars. Therefore, we studied on the influence of the avatars as the immersion of the elementary class homepage and the students cyber-self. As a result, we knew that the avatars can act enough as immersion element to achieve construction purpose of the class homepage and that use avatar helps in affirmative cyber self formation of elementary students.

• Journal of The Korean Association of Information Education
• /
• v.13 no.3
• /
• pp.273-280
• /
• 2009

The internet becomes a new communication tool in the knowledge and information society and the people are expanded at the place of information interchange and exchange of view. In recent robot education institutions provide their own official homepages to introduce the robot educational resources. But because they have restrictive searching the functions and providing general robot education resources and don't offer a place that teachers can express their thoughts and share common interests with other users, online community among teachers for robot education and users couldn't have built. In this paper, we propose an Online Robot Education Community(OREC) that teachers and users in different robot education institutions can interchange or share their technical information, learn robot techniques, participate in discussion of their experiences on work, share their common interests, and be provided updated latest news in real-time.

• Journal of Korea Game Society
• /
• v.11 no.3
• /
• pp.55-62
• /
• 2011

G-learning, based on online game, virtual reality activities and communities, is considered as a fresh, differentiated idea at learning which drives learners' interest and attention. The paper is to analyzed effectiveness of G-learning at the mathematics classes in elementary school. Fourth, fifth and sixth grade students in Seoul are selected as an experimental groups and their achievement scores are measured. The difference between G learning group and textbook group was significant. This result shows that G-learning has a positive effect on learning.

• Journal of Digital Convergence
• /
• v.12 no.1
• /
• pp.51-60
• /
• 2014

Modern society is rapidly changing by the Internet, and it is getting influential on the field of education. Learners can learn what they want to learn actively and freely at their desired level at anywhere in their free time by using the internet. The purpose of this study, therefore, is to find out the methods for improving writing ability through e-learning. The results of the study are as follows: First, learners can attend a lecture to improve their writing ability and can get learning materials from on-line course sites, internet websites, communities and blogs. Second, e-learning is learner-centered education, so it stimulates learners learning motivation and interest. Third, learners have an opportunity to express their ideas freely, and they can gain cultural comprehension while they communicate with people in the world by e-mail and chatting.

• The Journal of the Korea Contents Association
• /
• v.10 no.4
• /
• pp.458-470
• /
• 2010

As digital technologies have strongly impacted the whole social aspects, so museum recently emerging as an alternative or supplementary learning environment to school, after active adoption to the technologies, gave birth to museum websites called 'Virtual Museums' which, then, result in enhancing the educational roles and functions of physical museum. In this context, this study aimed to review the process of how virtual museum has been developed in terms of its educational roles and characteristics in accordance with the evolutionary development of web. Especially, the analysis of the status quo of the current virtual museums in both Korea and overseas presented specific aspects of the educational elements and roles embedded in virtual museum which have been emphasized in many related research and studies. The categories of the roles of the virtual museum, as a result, were classified into 'digital archive,' 'learning resources,' and 'communigy,' each of which were, then, further elaborated for its individual educational uses. Eventually this study purposed to expand the public awareness and knowledge of virtual museum as the alternative online learning environments needed in the 21st century.

• 한국어정보학회:학술대회논문집
• /
• 2017.10a
• /
• pp.116-121
• /
• 2017

cQA(Community-based Question Answering) 시스템은 온라인 커뮤니티를 통해 사용자들이 질문을 남기고 답변을 작성할 수 있도록 만들어진 시스템이다. 신규 질문이 인입되면, 기존에 축적된 cQA 저장소에서 해당 질문과 가장 유사한 질문을 검색하고, 그 질문에 대한 답변을 신규 질문에 대한 답변으로 대체할 수 있다. 하지만, 키워드 매칭을 사용하는 전통적인 검색 방식으로는 문장에 내재된 의미들을 이용할 수 없다는 한계가 있다. 이를 극복하기 위해서는 의미적으로 동일한 문장들로 학습이 되어야 하지만, 이러한 데이터를 대량으로 확보하기에는 어려움이 있다. 본 논문에서는 질문이 제목과 내용으로 분리되어 있는 대량의 cQA 셋에서, 질문 제목과 내용을 의미 벡터 공간으로 사상하고 두 벡터의 상대적 거리가 가깝게 되도록 학습함으로써 의사(pseudo) 유사 의미의 성질을 내재화 하였다. 또한, 질문 제목과 내용의 의미 벡터 표현(representation)을 위하여, semi-training word embedding과 CNN(Convolutional Neural Network)을 이용한 딥러닝 기법을 제안하였다. 유사 질문 검색 실험 결과, 제안 모델을 이용한 검색이 키워드 매칭 기반 검색보다 좋은 성능을 보였다.

• KIPS Transactions on Computer and Communication Systems
• /
• v.12 no.3
• /
• pp.103-110
• /
• 2023

With the spread of the Internet, anonymous communities emerged along with the activation of communities for communication between people, and many users are doing harm to others, such as posting aggressive posts and leaving comments using anonymity. In the past, administrators directly checked posts and comments, then deleted and blocked them, but as the number of community users increased, they reached a level that managers could not continue to monitor. Initially, word filtering techniques were used to prevent malicious writing from being posted in a form that could not post or comment if a specific word was included, but they avoided filtering in a bypassed form, such as using similar words. As a way to solve this problem, deep learning was used to monitor posts posted by users in real-time, but recently, the community uses words that can only be understood by the community or from a human perspective, not from a general Korean word. There are various types and forms of characters, making it difficult to learn everything in the artificial intelligence model. Therefore, in this paper, we proposes a preprocessing technique in which each character of a sentence is imaged using a CNN model that learns the consonants, vowel and spacing images of Korean word and converts characters that can only be understood from a human perspective into characters predicted by the CNN model. As a result of the experiment, it was confirmed that the performance of the LSTM, BiLSTM and CNN-BiLSTM models increased by 3.2%, 3.3%, and 4.88%, respectively, through the proposed preprocessing technique.