• Journal of Intelligence and Information Systems
• /
• v.29 no.1
• /
• pp.41-63
• /
• 2023

As the online e-commerce market growing, the need for a recommender system that can provide suitable products or services to customer is emerging. Recently, many studies using the sentiment score of online review have been proposed to improve the limitations of study on recommender systems that utilize only quantitative information. However, this methodology has limitation in extracting specific preference information related to customer within online reviews, making it difficult to improve recommendation performance. To address the limitation of previous studies, this study proposes a novel recommendation methodology that applies deep learning technique and uses various linguistic factors within online reviews to elaborately learn customer preferences. First, the interaction was learned nonlinearly using deep learning technique for the purpose to extract complex interactions between customer and product. And to effectively utilize online review, cognitive contents, affective contents, and linguistic style matching that have an important influence on customer's purchasing decisions among linguistic factors were used. To verify the proposed methodology, an experiment was conducted using online review data in Amazon.com, and the experimental results confirmed the superiority of the proposed model. This study contributed to the theoretical and methodological aspects of recommender system study by proposing a methodology that effectively utilizes characteristics of customer's preferences in online reviews.

• The Journal of Society for e-Business Studies
• /
• v.20 no.1
• /
• pp.217-241
• /
• 2015

One of the challenges in online community management is what level of perceived anonymity can be granted to encourage active participation from members while discouraging unhealthy activities. Few studies developed a scheme of anonymity and investigated how different levels of anonymity influence community activities. This study develops a classification scheme of anonymity encompassing the following three different levels : (1) real name(no anonymity), (2) nickname (partial anonymity), and (3) random assignment of a temporal ID (complete anonymity). Then, it examines how different levels of anonymity influence trust and perceived risk, which in turn affect virtual team performance. A series of laboratory experiments were performed, manipulating the levels of anonymity, in the context of well-structured communities that allow prior interactions among community members. The data was collected from 364 laboratory participants and analyzed using ANOVA and PLS. The results indicate that the difference of anonymity between (2) and (3) had not be significant and the only (1) could not guarantee the anonymity. The impact of anonymity on trust and perceived risk could not be significant in this situation. These findings could contribute to make more beneficial member identification strategies in online community practice.

• The Journal of the Korea Contents Association
• /
• v.21 no.8
• /
• pp.20-31
• /
• 2021

The spread of non-face-to-face culture due to COVID-19 led to innovation in untact services and the increase of non-face-to-face communication through video conference platforms. However, it is difficult to identify nonverbal expressions in synchronous online communication. Moreover, it is hard to interact with people by making eye contact. Despite the positive effects of eye contact, including such as sharing emotions and helping build intimacy, no research has empirically verified the effectiveness of eye contact in synchronous online communication. Thus, the study verified the effectiveness of eye contact in synchronous online communication. Depending on the context of the communication and whether(or not) there is eye contact, six video treatments were used to measure four dependent variables-Continuance Intention to Use, Performance Expectancy, Interactivity, and Personal Connection. The study shows that the communication with eye contact in all contexts was rated higher than the one without eye contact in all measurement variables. This study will help to provide a better user experience in synchronous online communication by verifying the effectiveness of eye contact in synchronous online communication and proposing the need of technology and the direction of the technological development.

• 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
• /
• 2008.06c
• /
• pp.522-526
• /
• 2008

모션 캡쳐 장비는 사람의 자연스러운 행동이나 동작 정보를 정밀하게 얻기 위해 널리 사용되며, 영화나 게임과 같은 콘텐츠에서 자주 활용되고 있다. 하지만 모션 캡쳐 장비가 고가이기 때문에 한번 입력받은 데이터를 모션별로 분할하고 상황에 맞게 재결합하여 사용할 필요가 있으며, 입력 데이터를 모션별로 분할하는 것은 대부분 수동으로 이루어진다. 이 때문에 캡쳐된 데이터를 자동으로 분할하기 위한 연구들이 다양하게 시도되고 있다. 기존의 연구들은 크게 전역적 특성에 대한 고려없이 이웃하는 프레임만을 고려하는 온라인 방식과 데이터를 전역적으로 고려하나 이웃하는 프레임 사이의 관계를 고려하지 않는 오프라인 방식으로 나누어진다. 본 논문에서는 온라인과 오프라인 방식을 병합한 그래프 기반의 모션 분할 방법을 제안한다. 분할을 위해 먼저 모션데이터를 기반으로 그래프를 생성하며, 그래프는 이웃하는 각 프레임사이의 유사도뿐만 아니라 시간축을 기반으로 일정시간내의 프레임들의 유사도를 모두 고려하였다. 이렇게 생성된 그래프를 분할하기 위해 분할된 모션내의 유사도 합을 최소화하고 각 모션간의 유사도는 최대화할 수 있는 normalized cuts을 이용하였다. 실험에서 제안된 방법은 기존의 오프라인 방식 중 하나인 GMM과 온라인 방식 중 하나인 국부최소값 분할 방법보다 좋은 결과를 보였으며, 이는 각 프레임 사이의 유사도뿐만 아니라 일정시간내의 유사도를 전역적으로 고려하기 때문이다.

• Journal of The Korean Association of Information Education
• /
• v.20 no.5
• /
• pp.433-442
• /
• 2016

The purpose of this paper is to prove the effect of flipped learning on learning motivation in software education. For this study, the experiment was consisted of experimental group and control group for university of education. They learned software education using Scratch programming for 10 weeks. The experimental group was applied to the flipped learning with online software courses. As a result, post motivation in the experimental group was significantly increased compared to the pre learning motivation. Post- learning motivation is also the experimental group were higher learning motivation significantly compared to the control group. It is hoped this flipped learning as an effective learning strategies base expansion in primary and secondary education as well as high education teaching software in the future.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.29 no.1A
• /
• pp.18-30
• /
• 2004

In this paper, the calibration problem of an asynchronous CDMA-based antenna array is studied. A new iterative calibration algorithm for antenna array in the presence of frequency offset error is presented. The algorithm is applicable to a non-linear array and does not require a prior knowledge of the (direction of arrivals) DOAs of the signals of any user, and it only requires the code sequence of a reference user. The algorithm is based on the two step procedures, one for estimating both channel and frequency offset and the other for estimating the unknown array gain and phase. Consequently, estimates of the DOAs, the multi-path impulse response of the reference signal sources, and the carrier frequency offset as well as the calibration of antenna array are provided. The performance of the proposed algorithm is investigated by means of computer simulations and is verified by using field data measured through a custom-built W-CDMA test-bed.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2008.11a
• /
• pp.225-228
• /
• 2008

최근 인터넷 기술의 발달로 인해서 온라인에서 다양한 사회연결망이 출현하였고, 이를 분석하기 위한 연구가 활발히 진행되고 있다. 온라인 사회연결망의 대표적인 예로 블로그 연결망을 들 수 있다. 블로그 연결망에서는 블로그 사용자들이 작성한 게시글들이 다양한 방식을 통하여 다른 사용자들에게 전파된다. 본 논문에서는 이를 게시글이 파급되었다고 부르고, 게시글을 파급한 사용자는 게시글을 소유하고 있는 사용자에게 동화되었다고 부른다. 블로그 내에는 다수의 사용자들에게 컨텐츠를 파급시키는 영향력 있는 사용자들이 존재한다. 본 논문에서는 블로그 연결망에서 파급 파워 유저를 파악하기 위해서 독립 전파 모델을 이용한다. 독립 전파 모델의 수행을 위해서는 사용자들 간의 동화확률을 부여하는 것이 필수적이다. 따라서 본 논문에서는 사용자의 컨텐츠 파워, 재생산 파워의 개념과 이를 계량화 하는 방법을 제안하고, 이 값들을 이용하여 사용자간의 동화확률을 부여하는 방안을 제안한다. 끝으로, 실제 블로그 연결망에서 제안하는 기법과 기존의 기법을 이용하여 파워 유저들을 파악하는 실험을 수행하고, 실험결과를 비교 및 분석한다.

• Proceedings of the KIPE Conference
• /
• 2011.07a
• /
• pp.567-568
• /
• 2011

영구자석 동기 전동기의 센서리스 구동에 있어서 위치와 속도를 정확히 추정하는 것이 중요하다. 정확한 위치와 속도의 추정을 위해서는 정확한 모터 파라미터가 필요한데, 특히나 magnetic saturation에 의한 q-축 인덕턴스의 영향이 가장 크기 때문에 이 논문에서는 매입형 영구자석 동기 전동기(IPMSM)의 센서리스 구동을 위한 q축 인덕턴스 추정에 대한 시뮬레이션 결과와 실험 결과를 나타내었다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2002.04b
• /
• pp.268-270
• /
• 2002

본 논문에서는 온라인 뉴스 기사를 여과하여 사용자에게 관련있는 뉴스기사만을 선별적으로 여과하여 보여주는 정보여과 에이전트를 설계 및 구현하였다. 정보여과의 핵심이라고 할 수 있는 정확한 사용자 프로파일 구축과 정보에 대한 사용자의 적합성 반응인 명시적 피드백과 암시적 피드백을 모두 결합한 피드백을 사용하여 사용자 프로파일을 좀 더 정교하게 구축하는 방법을 기술하였다. 실험을 통하여 사용자의 결합된 적합성 피드백 행동에 기반한 정보여과 에이전트의 성능이 단일의 피드백만을 사용했을 때보다 더 좋은 정확성과 적응성을 지니고 있음을 보여 주었다.