• Journal of the Korea Society of Computer and Information
• /
• v.26 no.1
• /
• pp.265-274
• /
• 2021

In this paper, we propose a novel recommendation model based on Doc2vec using search keywords and product details. Until now, a lot of prior studies on recommender systems have proposed collaborative filtering (CF) as the main algorithm for recommendation, which uses only structured input data such as customers' purchase history or ratings. However, the use of unstructured data like online customer review in CF may lead to better recommendation. Under this background, we propose to use search keyword data and product detail information, which are seldom used in previous studies, for product recommendation. The proposed model makes recommendation by using CF which simultaneously considers ratings, search keywords and detailed information of the products purchased by customers. To extract quantitative patterns from these unstructured data, Doc2vec is applied. As a result of the experiment, the proposed model was found to outperform the conventional recommendation model. In addition, it was confirmed that search keywords and product details had a significant effect on recommendation. This study has academic significance in that it tries to apply the customers' online behavior information to the recommendation system and that it mitigates the cold start problem, which is one of the critical limitations of CF.

• Korean Journal of Culture and Social Issue
• /
• v.29 no.3
• /
• pp.405-427
• /
• 2023

This study aimed to identify demographic variables(gender, age group, occupation, living arrangement, economic level, respiratory and chronic diseases, previous medical history), COVID-19 variables(COVID-19 prevention behavior, frequent use of media to obtain COVID-19 information), and psychological behavioral variables(depression, anxiety, loneliness, and increased drinking). From February to March 2021, an online survey of adults was conducted, and a total of 1,434 data were used for analysis. 260 out of 1,434 people were confirmed to have suicide ideation, the prevalence of suicide ideation among adults during the COVID-19 was 18.1%. Logistic regression analyses indicated elevated odds of suicidal ideation among individuals in their 20s and 30s, those living alone, exhibiting fewer COVID-19 preventive behaviors, consuming COVID-19 information more frequently through media, and reporting higher levels of loneliness. Furthermore, within the group experiencing depression, anxiety, and increased drinking, greater levels of these factors correlated with higher odds of suicidal ideation. Based on the results, implications and significance of the study were discussed.

• Journal of Korean Home Economics Education Association
• /
• v.20 no.4
• /
• pp.19-42
• /
• 2008

The purpose of this study was to develop practical problem-based home economics teaching.learning process plans about a unit 'the youth and consumer life' of middle school eighth-grade Technology and Home Economics by applying blended learning(BL) strategy. According to ADDIE instructional design model, this study was conducted in the following procedure: analysis, design/development, implementation, and evaluation. In the stage of design and development, the selected unit was converted into a practical problem-based unit, and practical problem-based teaching. learning process plans were designed in detail by using BL strategy. An online study room for practical problem-based home economics instruction grounded in BL strategy was prepared by using Edunet(http://community.edunet4u.net/${\sim}$consumer2). Eight-session lesson plans were mapped out, and study aids for students and materials for teachers were prepared. In the implementation stage, the first-session teaching plans that dealt with a minor question 'what preparations should be made to become a wise consumer' were utilized when instruction was provided to 115 eighth graders who were in three different province, and the other one was in a middle school in the city of Daejeon. The experimental teaching was implemented for two weeks in the following procedure: preliminary program, pre-online learning, main instruction and post- online learning. The preliminary program was carried out in a session in the classroom, and pre-online learning was provided before the main instruction was given in a session in the classroom. After the main instruction was completed, post-online learning was offered. In the evaluation stage, a survey was conducted on all the learners and teachers to find out their opinions and suggestions.

• Journal of the Korea Convergence Society
• /
• v.11 no.3
• /
• pp.201-210
• /
• 2020

The study was conducted to predict usage attitudes and behaviors by combining usage motivation and sensitivity, gender, and age in aviation-related social media. Specifically, the purpose of this study was to examine the effects of social media information acceptance, motivation and sensitivity on gender acceptance by gender and age. To this end, we collected data in an even distribution to prevent gender and age bias among adults aged 20 or older online from April 19 to May 3, 2018. As a result, the lower the female and age in the gender and age had a positive effect on the acceptance of social media information. Motivation for use has a positive effect on information acceptance and sensitivity has a negative effect on information acceptance. Through this, it was found that user class such as gender and age, motivation to use, and sensitivity affect information acceptance. In addition, the negative aspects of the sensitivity factor can be identified, and it is expected to be used as basic data in aviation-related social media marketing strategies.

• Proceedings of the Korean Information Science Society Conference
• /
• 2005.11b
• /
• pp.823-825
• /
• 2005

기존의 인터넷과 컴퓨터 등의 발달로 교육현장에서도 많은 WBI (Web-Based Instruct ion)들이 개발되고 사용되고 있으나 교육사이트의 컨텐츠를 살펴보면 대부분이 행동주의 심리학에 근거를 둔 프로그램 형태를 벗어나지 못하고 있어서 학습자에게 의미있는 학습을 유발시키기 보다는 제시된 정보의 기계적 재생에 그치고 있다는 비판을 받고 있다. 이러한 한계를 극복하는 대안으로는 학습자의 외형적이고 기계적인 면보다는 학습자의 인지활동을 강조하는 인지론적 접근이 필요하다고 본다. 인지심리학의 이러한 측면을 잘 반영하는 학습이론으로서 발견학습 이론을 들 수 있다. 발견학습을 적용시킨 모듈부분은 사용자의 편의에 따라 활용하지 않고 그래프의 탐색이 가능하도록 설계되므로 교사 개개인 수업의 형태에 따라 다양하게 적용할 수 있다. 따라서 온라인과 오프라인상의 모든 현장에서 교수-학습지도에 기절할 것이다.

• The Journal of the Korea Contents Association
• /
• v.6 no.3
• /
• pp.75-84
• /
• 2006

The internet has the capabilities of supporting and facilitating several forms of consumer interaction including one-to-one, one to many, or many-to-many interactions. Especially, previous studies revealed that the Online Word-of-Mouth communication is widely used as a source of customer's information seeking and purchase decision making. Even with this importance of the Online Word-of-Mouth communication on internet, few research has systematically addressed the issue. This study investigates the effect of interpersonal communication on consumers' information search activities and develops a model that depicts the key antecedents and mediating variables of interpersonal communication in internet shopping environment. The results are as follows: First, choice uncertainty, perceived risk, and knowledge uncertainty play an important role for perceived usefulness. Second, perceived usefulness has directly affected interactive communication of consumers' communication style. Thus, it is essential for internet companies to find ways to encourage their customers to engage in word-of-mouth communication.

• Journal of The Korean Association of Information Education
• /
• v.17 no.1
• /
• pp.1-8
• /
• 2013

SNS is a social networking service that removes the barrier between cyber spaces and the real world and helps people who have common interests to have a two-way communication, manage their interpersonal relationships and share information. The domestic and international SNS markets have attained a steady growth, and their growth is being more accelerated in recent days. However, studies on SNS have just examined adults, and it's required to research the use of SNS and cyber behaviors via SNS among elementary and middle school students. This study attempted to analyze the relationship of the use of SNS, motivation of using SNS, the use of active SNS functions, SNS-dependent tendency and SNS awareness to cyber behaviors via SNS among elementary and middle school students. As a result, regardless of gender and grade, stealing private information was the most frequent activity and the frequency of 'contacting strangers' activity increased most rapidly with the usage time and grade. SNS dependency turned out to be the most highly correlated with the negative cyber behavior. Moreover, the difference of gender was not significant to the overall negative cyber behavior, whereas that of grade was.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.20 no.3
• /
• pp.422-427
• /
• 2010

Korean Game industry, especially MMORPG(Massively Multiplayer Online Game) has been rapidly expanding in these days. But As game industry is growing, lots of online game security incidents have also been increasing and getting prevailing. One of the most critical security incidents is 'Game Bots', which are programs to play MMORPG instead of human players. If player let the game bots play for them, they can get a lot of benefic game elements (experience points, items, etc.) without any effort, and it is considered unfair to other players. Plenty of game companies try to prevent bots, but it does not work well. In this paper, we propose a behavior pattern model for detecting bots. We analyzed behaviors of human players as well as bots and identified six game features to build the model to differentiate game bots from human players. Based on these features, we made a Naive Bayesian classifier to reasoning the game bot or not. To evaluated our method, we used 10 game bot data and 6 human Player data. As a result, we classify Game bot and human player with 88% accuracy.

• Asia-Pacific Journal of Business Venturing and Entrepreneurship
• /
• v.15 no.2
• /
• pp.1-18
• /
• 2020

This study is to identify the influence of major variables that affect the participation intention of securities type crowdfunding investors and how participation intention and perceived behavioral control affect investors' herd behavior including indirect effect analysis based on the theory of planned behavior. The ultimate purpose of this study is to understand the investment behavior of securities type crowdfunding investors and to help the relevant parties to develop various policies and business plans to revitalize the system and protect investors. An online survey was conducted on people who are interested or have experience in securities type crowdfunding to receive a total of 276 responses. Excluding outliers, a total of 261 responses were taken into account for the final analysis. For the data analysis, structural equation model analysis using SPSS 22.0 and Amos 22.0 statistical package was conducted. As a result, two of the major variables of the theory of planned behavior-attitude and subjective norm-have been found to have a positive effect on the participation intention of securities type crowdfunding investors. And after analyzing the indirect effect, the participation intention was found to play a mediating role between attitude, subjective norm and herd behavior. However, the perceived behavioral control presented as a major variable of behavioral intention in the theory of planned behavior showed that the effect on participation intention was statistically insignificant. Instead, it was found to have a direct positive effect on herd behavior. This is significant because it empirically confirmed that even if investors perceive securities type crowdfunding as easy to participate, perceived behavioral control does not seem to have a significant impact on participation intention because securities type crowdfunding is an investment in an early-stage business with a high risk of loss. On the other hand, the study has great significance in that it empirically confirmed that domestic securities type crowdfunding investors perceive the funding progress information provided by the platform as a signal and imitate many other investors, showing herd behavior when they actually make an investment. It is expected that this study will provide meaningful insights for the policy making of crowdfunding supervisory offices and platform operators by empirically identifying major variables that influence the participation intentions and herd behavior of domestic securities type crowdfunding investors.

• Journal of Information Management
• /
• v.24 no.2
• /
• pp.36-53
• /
• 1993

Nowadays we usually act based on information in order to act effectively, we should enlarge our access to information of course, we have several methods to choose from, but commercial databases are the most advantageous. One reason is that everyone has equal access to commercial databases. As a result, people or companies who use commercial database information skillfully have a distince advantage over those who don't commercial database services in japan have been changing rapidly since their birth more than twenty years ago. For example, the distribution mode of databases is changing : from the original batch(off line) to on-line and most recently to the coexistence of batch and on line with the advent of CD-ROM. It is important for us to keep up with the new trends in databases, and to utilize them effectively as a tool in the information age.