• Journal of Information Technology Applications and Management
• /
• 제21권4_spc호
• /
• pp.361-379
• /
• 2014

With the rapid increase of social network usage, there are emerging trends of adopting social information among online users in building recommendation system. This study aims to investigate whether the additional usage of social information can improve recommendation performance in recommendation system and how much the improvement can be different according to the product involvement level. As an experiment result, social information does not affect positively to the recommendation accuracy but affect significantly to the recommendation quality. Also social information contributed more sensitively to the improvement of recommendation quality in high product involvement domain.

• 한국의류학회지
• /
• 제48권3호
• /
• pp.485-500
• /
• 2024

This study was conducted to examine the effects of consumer evaluations on size recommendation services based on body information on consumer responses and the moderating effect of the level of information search. To analyze the research model, a total of 200 data were collected from August 18 to 24, 2022, targeting consumers who had experience with using size recommendation services based on body information. As a result of the research model analysis, it was confirmed that the compatibility, reliability, and convenience of the size recommendation services based on body information influenced attitude, which, in turn, influenced usage intention. In addition, In the case of the group subject to a low level of information search, the path through which compatibility and reliability influenced attitude was significant, but that of convenience was not. In the group featuring a high level of information search, the path through which reliability and convenience influenced attitude was significant, but that of compatibility was not. This study is meaningful in that it expanded research related to size recommendation services to the field of consumer behavior.

• 지식경영연구
• /
• 제16권3호
• /
• pp.149-169
• /
• 2015

In this study, we try to understand the role of online social recommendation and the similarity of preferences between the recommender and the recommendee on consumer decisions in the framework of the two stage purchase decision-making process. Applying construal level theory to our context, we expect that the role of social recommendation and the similarity of preferences would vary over the stages in the two-stage decision making process. To test our hypotheses, we collected the data through an incentive compatible experiment, and analyzed the data with nested logit model. As a result, we found that the role of online social recommendation varies over the stages. Consumers take recommendation from similar others at the stage of consideration set formation, but no longer consider it at the stage of final choice. Consumers take recommendation from dissimilar others at the stage of consideration set formation. At the stage of final choice, however, consumers avoid choosing the option recommended by dissimilar others. The results of our study enrich the understanding about the role of social recommendation, and have implication to marketing practitioners who attempt to make online social recommendation system more efficient.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제14권9호
• /
• pp.3730-3744
• /
• 2020

This study proposes a deep learning-based evolutionary recommendation model for heterogeneous big data integration, for which collaborative filtering and a neural-network algorithm are employed. The proposed model is used to apply an individual's importance or sensory level to formulate a recommendation using the decision-making feedback. The evolutionary recommendation model is based on the Deep Neural Network (DNN), which is useful for analyzing and evaluating the feedback data among various neural-network algorithms, and the DNN is combined with collaborative filtering. The designed model is used to extract health information from data collected by the Korea National Health and Nutrition Examination Survey, and the collaborative filtering-based recommendation model was compared with the deep learning-based evolutionary recommendation model to evaluate its performance. The RMSE is used to evaluate the performance of the proposed model. According to the comparative analysis, the accuracy of the deep learning-based evolutionary recommendation model is superior to that of the collaborative filtering-based recommendation model.

• 한국병원경영학회지
• /
• 제15권1호
• /
• pp.49-69
• /
• 2010

The major purpose of this study is to find out relevant factors affecting utilization of Long Term Care Hospitals since the Elderly Long Term Care Insurance System was adopted in Korea. The sample hospitals of this study are 5 long term care hospitals located in 4 big cities and 1 local area. The research data were collected with structured questionnaire from 247 patients and patients' protectors in 5 sample hospitals. Analyzing methods are descriptive statistics, factor analysis and multiple regression with SPSS(version 12.0). Major results of this study are as follows. 1) Utilization and recommendation of patients is affected significantly by the level of hospital facilities (0.043), fee level(0.026), level of staff (0.000), and discomfort of services(0.001). 2) Level of staff is very positively correlated with utilization and recommendation of patients. 3) Discomport of services is very negatively correlated with utilization and recommendation of patients. On the basis of results this study conclude that the management of Long Term Care Hospitals is required conclude to improve the level of staff and facilities and to solve discomport problems of services for patients' marketing. And also more in-depth study on the utilization factors of long term care hospital in Korea is required.

• 한국컴퓨터정보학회논문지
• /
• 제15권8호
• /
• pp.51-58
• /
• 2010

프로그래밍 교육은 학습자 개개인의 특성에 맞는 수준별 단계별 학습이 필요하다. 추천시스템은 개인화서비스를 위해 사용되는 방법의 하나로, 본 연구에서는 추천시스템을 사용하여 웹기반 프로그래밍 교육 환경에서 학습자 개개인에 적합한 학습을 추천할 수 있는 방법을 제공한다. 제안하는 수준별 프로그래밍 학습을 위한 추천시스템은 학습주제별 학습수준 기반 학습자 프로파일과 학습주제사이의 연관성 프로파일을 이용한 협업 필터링을 사용하여 특정 학습자의 학습수준과 학습범위에 적절한 프로그래밍 문제를 제공하도록 한다. 그 결과 프로그래밍 언어 교육과정에서 발생하는 수준별 단계별 학습에 맞는 프로그래밍 문제 제공의 어려움을 해결하여, 학습자의 프로그래밍 능력 향상의 결과를 얻을 수 있었다. 더 나아가 기존 협업필터링 방법을 사용하는 경우와 비교해 볼 때 추천 성능향상 및 분석 시간 감소를 통해 추천시스템의 한계점 중의 하나인 확장성을 해결할 수 있는 방법을 제시한다.

• 패션비즈니스
• /
• 제15권1호
• /
• pp.129-144
• /
• 2011

The purpose of this study was to investigate the influence of purchasing behavior on brand attitude, shopping satisfaction, and recommendation of herbal cosmetics consumer. Through judgment sampling method, selected 304 survey questionnaires were used for final analysis from herbal cosmetics consumer. With the collected data, t-test, one-way ANOVA, and multiple regression analysis were performed by SPSS 14.0. The results of the analysis were summarized as follows. First, level of education no significant difference on purchasing behavior, but age, marital status, average income, and job type showed significant difference on purchasing behavior. Second, level of education and average income no significant difference on brand attitude, shopping satisfaction, and recommendation, but age, marital status, and job type showed significant difference on brand attitude, shopping satisfaction, and recommendation. Third, the reasonable purchase, conformity purchase, and conspicuous purchase impacts positively(+) influence, but impulse purchase impacts negatively(+) influence on brand attitude. Fourth, the rational purchase and conspicuous purchase impacts positively(+) influence on shopping satisfaction. Fifth, the conformity purchase and conspicuous purchase impacts positively(+) influence on recommendation.

• Journal of Information Technology Applications and Management
• /
• 제21권4호
• /
• pp.203-223
• /
• 2014

This study proposes a novel context-aware recommender system, which is designed to recommend the items according to the customer's responses to the previously recommended item. In specific, our proposed system predicts the user's emotional state from his or her responses (such as facial expressions and movements) to the previous recommended item, and then it recommends the items that are similar to the previous one when his or her emotional state is estimated as positive. If the customer's emotional state on the previously recommended item is regarded as negative, the system recommends the items that have characteristics opposite to the previous item. Our proposed system consists of two sub modules-(1) emotion prediction module, and (2) responsive recommendation module. Emotion prediction module contains the emotion prediction model that predicts a customer's arousal level-a physiological and psychological state of being awake or reactive to stimuli-using the customer's reaction data including facial expressions and body movements, which can be measured using Microsoft's Kinect Sensor. Responsive recommendation module generates a recommendation list by using the results from the first module-emotion prediction module. If a customer shows a high level of arousal on the previously recommended item, the module recommends the items that are most similar to the previous item. Otherwise, it recommends the items that are most dissimilar to the previous one. In order to validate the performance and usefulness of the proposed recommender system, we conducted empirical validation. In total, 30 undergraduate students participated in the experiment. We used 100 trailers of Korean movies that had been released from 2009 to 2012 as the items for recommendation. For the experiment, we manually constructed Korean movie trailer DB which contains the fields such as release date, genre, director, writer, and actors. In order to check if the recommendation using customers' responses outperforms the recommendation using their demographic information, we compared them. The performance of the recommendation was measured using two metrics-satisfaction and arousal levels. Experimental results showed that the recommendation using customers' responses (i.e. our proposed system) outperformed the recommendation using their demographic information with statistical significance.

• 정보과학회 컴퓨팅의 실제 논문지
• /
• 제24권2호
• /
• pp.93-98
• /
• 2018

추천시스템은 기업의 매출을 최대화 하기 위해, 사용자에게 관심도가 높은 제품을 제공해준다. 행렬 분해법은 추천시스템에서 자주 사용되는 방법으로 불완전한 사용자-제품 평점 행렬을 기반으로 한다. 하지만 제품과 사용자의 수가 점점 많아지면서, 데이터의 희소성문제로 인해 정확한 추천이 힘들어졌다. 이러한 문제점을 극복하기 위해, 제품과 관련된 텍스트 데이터를 사용하는 행렬 분해법 알고리즘이 최근에 제시되었다. 이런 행렬 분해법 알고리즘 중, 단어 수준 컨볼루션 뉴럴 네트워크를 사용하는 방법이 단어수준 특징들을 추출하여 텍스트 데이터를 효과적으로 반영한다. 하지만 단어수준 컨볼루션 뉴럴 네트워크에서는 학습해야 하는 파라미터의 수가 많다는 문제점이 있다. 그러므로 본 논문에서는 텍스트 데이터로부터 문자 수준 특징들을 뽑아 내기 위해 문자 수준 컨볼루션 뉴럴 네트워크를 사용하는 행렬분해법을 제안한다. 또한 제안하는 행렬 분해법의 성능을 검증하기 위해 실제 데이터를 이용하여 실험을 진행하였다.

• 한국컴퓨터정보학회논문지
• /
• 제16권7호
• /
• pp.127-135
• /
• 2011

이러닝 시스템에서 학습자에게 적합한 콘텐츠 선택을 돕기 위한 콘텐츠 추천 시스템은 필수적이다. 학습자의 선호도를 통한 콘텐츠 추천은 협업 필터링 추천 방법과 내용 기반 추천 방법이 가장 많이 사용되고 있다. 그러나 기존추천 방법들은 학습자의 학습수준을 고려하지 않고 다른 사용자의 선호도를 기반으로 학습 콘텐츠를 추천한다. 따라서 상대적으로 콘텐츠를 학습한 학습자가 적은 경우 추천의 효율성이 떨어지고, 새로운 아이템이 추가될 경우 추천이 쉽지 않은 단점이 있다. 이 문제를 해결하기 위해 우리는 학습 콘텐츠의 유사도와 난이도에 기반한 콘텐츠 추천 방법을 제안한다. 학습 콘텐츠의 두 특성을 반영한 추천함수에 의해 선행학습 성취도가 낮은 학습자에게는 난이도가 낮고 유사도가 높은 콘텐츠를 추천하고, 성취도가 높은 학습자에게는 난이도가 높고 유사도가 낮은 콘텐츠를 추천한다. 이와 같이 다른 학습자의 선호도와는 무관하게 학습자의 성취도에 따라 가장 적합한 콘텐츠를 추천할 수 있다.