• The Journal of Information Systems
• /
• v.27 no.4
• /
• pp.71-96
• /
• 2018

Purpose Recently, social interest in the convergence research is at its peak. However, contrary to the keen interest in convergence research, an infrastructure that makes it easier to recruit researchers from other fields is not yet well established, which is why researchers are having considerable difficulty in carrying out real convergence research. In this study, we implemented a researcher recommendation system that helps researchers who want to collaborate easily recruit researchers from other fields, and we expect it to serve as a springboard for growth in the convergence research field. Design/methodology/approach In this study, we implemented a system that recommends proper researchers when users enter keyword in the field of research that they want to collaborate using word embedding techniques, word2vec. In addition, we also implemented function of keyword suggestions by using keywords drawn from LDA Topicmodeling Algorithm. Finally, the UI of the researcher recommendation system was completed by utilizing the collaborative messenger Slack to facilitate immediate exchange of information with the recommended researchers and to accommodate various applications for collaboration. Findings In this study, we validated the completed researcher recommendation system by ensuring that the list of researchers recommended by entering a specific keyword is accurate and that words learned as a similar word with a particular researcher match the researcher's field of research. The results showed 85.89% accuracy in the former, and in the latter case, mostly, the words drawn as similar words were found to match the researcher's field of research, leading to excellent performance of the researcher recommendation system.

• Journal of Digital Convergence
• /
• v.14 no.1
• /
• pp.413-425
• /
• 2016

This study investigated what effects the relational benefits perceived by the customers of solely operated beauty salons have on customer satisfaction, recommendation intention, and defection intention through the convergence of cosmetology and business management. For this, a total of 322 customers of solely operated beauty salons were chosen as final valid samples. For data analysis, frequency analysis, reliability analysis, confirmatory factor analysis, and correlation analysis were performed using SPSS 15.0 and AMOS 18. For a hypothesis test, lastly, path analysis was conducted using structural equation modeling. The study results found the following: First, among the relational benefits perceived by the customers of solely operated beauty salons, confidence benefits and social benefits had a positive effect on customer satisfaction. Second, the relational benefits perceived by the customers of solely operated beauty salons had a positive effect on recommendation intention. Third, confidence benefits and social benefits had a negative effect on defection intention. Fourth, customer satisfaction had a positive effect on recommendation intention. Fifth, customer satisfaction had a negative effect on defection intention. Sixth, in relationship between the relational benefits perceived by the customers of solely operated beauty salons and recommendation/defection intention, customer satisfaction revealed partial mediating effects.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.19 no.6
• /
• pp.1387-1392
• /
• 2015

SCS(Social Curation Service) is a service system to help sale and consumption with intelligent information about consumer's favor which is got from the combination of social service and internet shopping mall. This paper develops and analyzes some algorithms for catching the customer's preference tendency in SCS system. The developed algorithms are implemented to verify it's efficiency.

• Journal of Intelligence and Information Systems
• /
• v.16 no.4
• /
• pp.159-172
• /
• 2010

The recommender system is one of the possible solutions to assist customers in finding the items they would like to purchase. To date, a variety of recommendation techniques have been developed. One of the most successful recommendation techniques is Collaborative Filtering (CF) that has been used in a number of different applications such as recommending Web pages, movies, music, articles and products. CF identifies customers whose tastes are similar to those of a given customer, and recommends items those customers have liked in the past. Numerous CF algorithms have been developed to increase the performance of recommender systems. Broadly, there are memory-based CF algorithms, model-based CF algorithms, and hybrid CF algorithms which combine CF with content-based techniques or other recommender systems. While many researchers have focused their efforts in improving CF performance, the theoretical justification of CF algorithms is lacking. That is, we do not know many things about how CF is done. Furthermore, the relative performances of CF algorithms are known to be domain and data dependent. It is very time-consuming and expensive to implement and launce a CF recommender system, and also the system unsuited for the given domain provides customers with poor quality recommendations that make them easily annoyed. Therefore, predicting the performances of CF algorithms in advance is practically important and needed. In this study, we propose an efficient approach to predict the performance of CF. Social Network Analysis (SNA) and Artificial Neural Network (ANN) are applied to develop our prediction model. CF can be modeled as a social network in which customers are nodes and purchase relationships between customers are links. SNA facilitates an exploration of the topological properties of the network structure that are implicit in data for CF recommendations. An ANN model is developed through an analysis of network topology, such as network density, inclusiveness, clustering coefficient, network centralization, and Krackhardt's efficiency. While network density, expressed as a proportion of the maximum possible number of links, captures the density of the whole network, the clustering coefficient captures the degree to which the overall network contains localized pockets of dense connectivity. Inclusiveness refers to the number of nodes which are included within the various connected parts of the social network. Centralization reflects the extent to which connections are concentrated in a small number of nodes rather than distributed equally among all nodes. Krackhardt's efficiency characterizes how dense the social network is beyond that barely needed to keep the social group even indirectly connected to one another. We use these social network measures as input variables of the ANN model. As an output variable, we use the recommendation accuracy measured by F1-measure. In order to evaluate the effectiveness of the ANN model, sales transaction data from H department store, one of the well-known department stores in Korea, was used. Total 396 experimental samples were gathered, and we used 40%, 40%, and 20% of them, for training, test, and validation, respectively. The 5-fold cross validation was also conducted to enhance the reliability of our experiments. The input variable measuring process consists of following three steps; analysis of customer similarities, construction of a social network, and analysis of social network patterns. We used Net Miner 3 and UCINET 6.0 for SNA, and Clementine 11.1 for ANN modeling. The experiments reported that the ANN model has 92.61% estimated accuracy and 0.0049 RMSE. Thus, we can know that our prediction model helps decide whether CF is useful for a given application with certain data characteristics.

• Journal of Gifted/Talented Education
• /
• v.22 no.1
• /
• pp.173-196
• /
• 2012

The relationship of the teacher's recommendation and performance in gifted programs for the selected student by teacher's observations and nominations was analyzed in this study. The teacher's recommendation for 9 students selected by teacher's observations and nominations in institute of Science gifted Education of C National University of Education was analyzed for this purpose. The students were categorized into 4 groups depending on the description style and contents of the teacher's recommendation and 1 student was selected from each group for analysis. It was shown that the student, a1 who was described with cognitive characteristics of the gifted in episode style in the teacher's recommendation showed the aggressive task adherence and problem solving ability. The student, a2 who was described with emotional and social characteristics in episode style attended at the class in active attitude, but the student solved the problem by the assistance of the colleagues or the teacher. The student, b1 who was listed superficially in the teacher's recommendation showed the excellent problem solving ability based on the task adherence, experiment design ability and experiment manipulation ability. The student, b2 who was listed in superficially in the teacher's recommendation attended at the class in positive and upright attitude, but the task solving was lagged behind. It is concluded from the above results that the description on the cognitive area is necessary for the teacher's recommendation to have the usefulness in selecting gifted students.

• Korean Journal of Child Studies
• /
• v.20 no.2
• /
• pp.257-268
• /
• 1999

This analysis of the history and programs of family education centers (Familienbildungsst${\ddot{a}}$tte) in Germany generated suggestions for designing Korean family life education programs. Familienbildungsst${\ddot{a}}$tte started around 1900 and changed over time due to varying social and political situations. Rapid social change and the sudden economic crash in Korea produced many family problems, such as broken families and family related conflict. As the Korean family can no longer provide traditional psychological and economic support, some social institution is required to provide intervention and encouragement to both special needs families and normal families. This study generated suggestions for designing and managing Korean family life social centers.

• Journal of Internet Computing and Services
• /
• v.14 no.2
• /
• pp.35-43
• /
• 2013

As the number of podcast users consistently increases which is rising as a new media along with the generalization of SNS and smart devices, the necessity for advanced search service is on the rise. This study designed and implemented a system which recommends a podcast to the users who search podcast by using their social network information. Suggested social network-based podcast search system (PODSSO) collects necessary podcast information only, analyzes social network of the users and makes the users have reliable and interested podcast search results.

• Journal of Distribution Science
• /
• v.13 no.3
• /
• pp.41-49
• /
• 2015

Purpose - Universities are placing a greater emphasis on relationship management as a source of competitive advantage due to increasingly competitive environments and social changes. The purpose of this study is to analyze the relationships among education service quality, relationship quality, and relationship performance from the perspective of service distribution. In other words, this study is focused on the role of education service quality with regard to relationship management. In this study, education service quality is divided into lecture, job assistance, student-faculty interaction, student-student interaction, facility welfare, and scholarship welfare quality components; relationship quality is composed of satisfaction and commitment; and relationship performance is divided into recommendation and defection intentions. Research design, data, and methodology - This study aims to identify how the various elements of education service quality affect satisfaction. Further, it aims to test the relationships among satisfaction, commitment, recommendation intentions, and defection intentions. Distribution and marketing students were randomly selected for the experiment. Out of the 380 administered questionnaires, a total of 361 respondents provided complete and usable data. The sample consisted of 232 males (64.3%) and 129 females (35.7%). The variables of the proposed model were measured through assessments that were measured on a 5-point Likert scale. Using Lisrel 8.7, a structural model was analyzed and the path coefficients were estimated. Results - The overall fit of the model was acceptable (χ2=1121.8 (df=603, P=0.00), GFI=0.967, NFI=0.974, CFI=0.981, RMR=0.021). The results generally supported the hypothesized relationships of the proposed model, except for Hypothesis 1. First, lecture, job assistance, student-faculty interaction, student-student interaction, and facility welfare quality were revealed to have positive effects on satisfaction. In particular, lecture and facility welfare quality had the strongest effects on satisfaction. However, scholarship welfare quality did not significantly affect satisfaction; this means that Hypothesis 3-2 was not supported. Second, satisfaction was positively related to commitment and recommendation intentions but it was negatively related to defection intentions. Third, commitment was positively related to recommendation intentions but it was negatively related to defection intentions. Conclusions - This study emphasizes the influence of education service quality on satisfaction in the long-term. In addition, this research has the following implications for university relationship management. First, the findings suggest that the various dimensions of education service quality have differing effects on satisfaction. In particular, lecture and facility welfare quality are found to be the most important factors in increasing the level of satisfaction. Therefore, university managers need to prioritize enhancing lecture quality and upgrading educational facilities. Second, satisfaction also improves through job assistance systems and opportunities for social interactions. Therefore, university managers should reinforce their job skills programs and should provide opportunities for social relationships to develop. Finally, it is important for university managers to take a relationship approach to maximizing relationship performance. Therefore, university managers should work to increase student recommendations and prevent their defections based on satisfaction and commitment.

• Culinary science and hospitality research
• /
• v.21 no.1
• /
• pp.210-224
• /
• 2015

The purpose of this study is to identify the effects of involvement in temple food on overall satisfaction, recommendation, and revisit intention. From June 15 to August 30, 2014, for those who have participated in temple stay at four temples in South Korea, the self-administered survey was conducted. Of a total of 400 questionnaires, 289 were employed for the analyses, which accounted for 72% of response rate. Results shows that the involvement in temple food positively influenced experience driven by motivation in temple stay. Considering a particular research topic of temple stay, it implies that the involvement in temple food plays a key role in affecting emotional and social value relating to experience in temple stay. Entertaining, educational, aesthetic, deviated factors created by this experience will contribute to making special memories and feeling great enjoyment. In addition, emotional and social value by temple food have a positive effect on recommendation and revisit intention through experience satisfaction. Furthermore, experiential factor was significant to overall satisfaction, revisit and recommendation intention. Social and emotional value according to involvement in temple food, in terms of conclusions in this study, influenced a reduction of stress and improvement of enjoyment. These values relating to involvement in temple food, therefore, are assumed to be the causal relationship with experiential factor and satisfaction in temple stay and subsequently will be regarded as determinants in defining temple food as a heathy dish.

• KIISE Transactions on Computing Practices
• /
• v.22 no.8
• /
• pp.375-380
• /
• 2016

The proliferation of online social networking services (OSNSs) and smartphones has enabled people to easily make friends with a large number of users in the online communities, and interact with each other. This leads to an increase in the usage rate of OSNSs. However, individuals who have immersed into their digital lives, prioritizing the virtual world against the real one, become more and more isolated in the physical world. Thus, their socialization processes that are undertaken only through lots of face-to-face interactions and trial-and-errors are apt to be neglected via 'Add Friend' kind of functions in OSNSs. In this paper, we present a friend recommendation system based on the on/off-line contextual information for the OSNS users to have more serendipitous offline interactions. In order to accomplish this, we modeled both offline information (i.e., place visit history) collected from a user's smartphone on a 3D tensor, and online social data (i.e., friend relationships) from Facebook on a matrix. We then recommended like-minded people and encouraged their offline interactions. We evaluated the users' satisfaction based on a real-world dataset collected from 43 users (12 on-campus users and 31 users randomly selected from Facebook friends of on-campus users).