• Journal of Intelligence and Information Systems
• /
• v.28 no.2
• /
• pp.171-189
• /
• 2022

Online reviews play an essential role in the consumer's purchasing decision-making process, and thus, providing helpful and reliable reviews is essential to consumers. Previous online review helpfulness prediction studies mainly predicted review helpfulness based on the consistency of text and rating information of online reviews. However, there is a limitation in that representation capacity or review text and rating interaction. We propose a CNN-RHP model that effectively learns the interaction between review text and rating information to improve the limitations of previous studies. Multi-channel CNNs were applied to extract the semantic representation of the review text. We also converted rating into independent high-dimensional embedding vectors representing the same dimension as the text vector. The consistency between the review text and the rating information is learned based on element-wise operations between the review text and the star rating vector. To evaluate the performance of the proposed CNN-RHP model in this study, we used online reviews collected from Amazom.com. Experimental results show that the CNN-RHP model indicates excellent performance compared to several benchmark models. The results of this study can provide practical implications when providing services related to review helpfulness on online e-commerce platforms.

• Proceedings of the Korean Information Science Society Conference
• /
• 2006.10b
• /
• pp.260-263
• /
• 2006

최근 온라인 게임 산업이 커짐에 따라 이를 즐기는 유저도 급증하고 있다. 온라인 게임에서는 일반적으로 유저들이 서로를 구분하기 위해 사용하는 사용자 이름과 상호간 의사소통을 하기 위한 채팅을 지원한다. 유저의 수가 증가함에 따라 대화의 양은 더욱 더 많아지고, 선정성, 폭력성을 띄는 언어의 문제로 이어지고 있다. 이는 특히 18세 이하도 이용가능한 게임을 만드는 경우 더욱 중요하다. 하지만 대부분의 게임들이 금지어 리스트에 따른 단어 매칭방식의 비속어 필터링만을 제공하고 있다. 이러한 방법은 금지어로 지정된 단어를 포함한 정상적인 채팅도 막을 뿐만 아니라 일부 음절을 다른 기호로 바꾸어 표기한 비속어는 걸러내지 못한다. 변형된 단어들을 충분히 처리하지 못한다면 비속어 필터링 시스템은 단지 무력하고 쓸모없는 존재가 될 뿐이다. 본 논문에서는 SVM을 이용하여 학습이 가능한 비속어 필터링 시스템을 제안하고자 한다. SVM을 이용하면 사용자 편의성을 해치지 않고서도 보다 많은 종류의 비속어들을 효과적으로 걸러낼 수 있다.

• Journal of the Korea Society of Computer and Information
• /
• v.25 no.12
• /
• pp.93-100
• /
• 2020

This study aims to design and develop effective digital contents to improve the ability for artificial intelligence literacy. First, we defined AI literacy and analyzed the competencies required for artificial intelligence literacy. After selecting the educational elements for AI ability, we composed 10 educational programs. To confirm the appropriateness of designed contents, we verified through content validity test by 10 experts. The CVI value was over 0.75, which was highly valid. The developed content was installed on the online system and applied to 55 AI beginners for 4 weeks. The learners showed a positive result of at least 3.85 in the items of content difficulty, understanding, effectiveness, and learning challenge. As a result of this analysis, we can see that the developed content is positive for helping many people understand AI and improving AI literacy.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2013.05a
• /
• pp.1107-1110
• /
• 2013

컴퓨터와 멀티미디어, 네트워크 기술의 발달을 바탕으로 웹 기반 교육이 출현하였고 기존 교실 중심수업의 한계를 뛰어 넘는 교육적 잠재성에 교육 운영자 및 학습자는 많은 기대를 하게 되었다. 웹을 이용한 학습은 자기주도적인 학습이 가능하고 학습자와 교수자 간의 상호 보완적인 학습이 이루어질 수 있다는 장점이 있기 때문이다. 이러한 웹 기반 학습을 효과적으로 운영하기 위해서는 개별 교육기관 자체적으로 개발한 학습관리시스템(Learning Management System;LMS)이 필요하다. 학습자들에게 양질의 온라인 콘텐츠를 제공하고자 하는 교사들을 위해 개발된 학습관리시스템 중 하나가 Moodle LMS이다. Moodle LMS는 소스가 공개되어 있어 누구나 필요한 사람은 소스를 개선, 확장, 활용할 수 있다. 따라서, 본 논문은 Moodle LMS를 활용하여 학습자가 원활하게 토론에 참여할 수 있는 토론 시스템을 설계하였다.

• Journal of the Korea Convergence Society
• /
• v.12 no.7
• /
• pp.133-142
• /
• 2021

This study aims to expand the effect of online education into the aspect of active exploration and sharing of class-related issues by learners. Based on theoretical discussions, Two types of motivation (personal and social) to explore issues, engagement, attitude toward issue content, and eWOM model were verified. As a result of the study, it was found that the impact of personal and social motivations that online education has on engagement on specific issues, and the positive(+) influence on attitudes toward issue content and word of mouth intentions on SNS, considering engagement as a parameter. In this study, the role of engagement in inducing the next learning by oneself was confirmed, and it can be seen that social and personal motives for issues and class content should be utilized to increase engagement.

• Journal of Industrial Convergence
• /
• v.21 no.8
• /
• pp.1-12
• /
• 2023

The purpose of the study is to analyze the impact of blended learning's external classroom formats and internal teaching strategies, which has been implemented in university classes due to COVID-19, on students' academic achievement and learners' perceptions, as well as to provide insights into the desirable direction of online education. The study was conducted during the 1st semester of 2022 at G University, targeting students taking Calculus I. The experimental group consisted of 117 students, while the control group consisted of 707 students. Blended learning, involving a combination of face-to-face classes, online classes, and mixed teaching methods, was implemented, and academic achievement and learner perceptions were assessed. The research findings indicate that compared to solely online classes, adopting a blended learning approach with online classes before the midterm and face-to-face classes afterwards resulted in a decline in academic achievement. The unprepared and simplistic external format of blended learning was found to be ineffective, however, a blended learning model consisting solely of online classes, incorporating a mix of asynchronous and synchronous instruction, demonstrated positive learner perceptions. Additionally, utilizing technology in the teaching strategies yielded positive outcome.

• Journal of Korea Game Society
• /
• v.7 no.1
• /
• pp.59-68
• /
• 2007

Online games are getting more popular among today's fun-seeking young students. The immersive power of these Internet-based games is so strong that many educators consider the integration of the games and learning to enhance learner motivation. However, the online games, which are primarily aiming g for 'fun', have cognitive, emotional, and social features and impacts that are different from the so-called 'educational' games. Therefore an interdisciplinary approach for better understanding of the online game in regard to its impact on learning and fun should be essential. In this study, the researcher will analyze relevant literature and theories from cognitive psychology, media and communication theory, and Ludology to grasp holistic understanding of online game phenomena, which will serve as basis of further research and development in this emerging area.

• The Journal of the Korea Contents Association
• /
• v.11 no.9
• /
• pp.524-535
• /
• 2011

For success in E-learning, support from a learning environment that enables learners to perform self-directed learning more effectively is assumed. However, most existing e-learning systems do not maximize the improvement in learners' self-regulated learning ability because they only partially accommodate factors that can facilitate self-directed learning. In this paper, a web-based e-learning system is designed and proposed that enables support of an enhanced self-directed learning environment by providing various learning methods, evaluation methods, learning content levels, and strategies for learning motivation in various conditions, and synthetically reflecting them. To validate the effectiveness of the proposed system, it was applied to the subject of data structures in a university course, and an online survey was conducted with the students. The results indicated that the proposed system can support a learning environment in which students can perform more effective self-directed learning, enhancing their learning ability.

• The Journal of the Korea Contents Association
• /
• v.11 no.2
• /
• pp.487-494
• /
• 2011

This paper is to investigate the efficacy of cyber education by self-assessment strategy. Self-assessment strategy contains self-monitoring function and self-control function. 202 students of online university attended and analyzed with frequency, correlation, t-test, Paired t-test. The major findings were as follows. The learners who experienced self-assessment in the initial stage of class had higher changes in social distance to the mentally disabled people positively than the learners who didn't experienced that. This self-assessment strategy can be assumed that it is effective strategy to improve e-learning efficacy and it will contribute to self-directed education for enhancement of on-line education.

• Journal of the Korean Society for Library and Information Science
• /
• v.47 no.1
• /
• pp.399-417
• /
• 2013

The purposes of this study are to investigate students' attitudes regarding group projects and to suggest an effective way to promote collaborative learning using Wiki. This study employed a survey questionnaire, which was distributed to students enrolled in classes provided by a university in Seoul. The result revealed that students preferred individual projects to group projects because various barriers occur in the process of group projects. Students' responses also indicated that rapport among group members influences the success of a group project. In addition, Wiki, as a Web 2.0 tool for group collaboration, was recognized as being useful in terms of promoting openness, modification, and effectiveness. Based on these findings, this study suggests the following for effective collaborative learning: (1) conducting peer- and self-assessments to avoid social loafing, (2) establishing rapport among group members, and (3) using Wiki in an active manner.