• Journal of Information Technology Applications and Management
• /
• v.29 no.3
• /
• pp.43-55
• /
• 2022

In this study, with the goal of developing a deep learning-based product recommendation model for effective matching of influencers and products, a deep learning model with a collaborative filtering model combined with generalized matrix decomposition(GMF), a collaborative filtering model based on multi-layer perceptron (MLP), and neural collaborative filtering and generalized matrix Factorization (NeuMF), a hybrid model combining GMP and MLP was developed and tested. In particular, we utilize one-class problem free boosting (OCF-B) method to solve the one-class problem that occurs when training is performed only on positive cases using implicit feedback in the deep learning-based collaborative filtering recommendation model. In relation to model selection based on overall experimental results, the MLP model showed highest performance with weighted average precision, weighted average recall, and f1 score were 0.85 in the model (n=3,000, term=15). This study is meaningful in practice as it attempted to commercialize a deep learning-based recommendation system where influencer's promotion data is being accumulated, pactical personalized recommendation service is not yet commercially applied yet.

• Asia-Pacific Journal of Business Venturing and Entrepreneurship
• /
• v.16 no.5
• /
• pp.159-175
• /
• 2021

This study attempted to analyze the relationship between influencer's characteristic factors such as professionalism, authenticity, and interactivity and content quality factors consisting of accuracy, completeness, and diversity on brand attitude and purchase attitude through trust and self-consistency. To reveal the structural relationship between main variables, a survey was conducted on 201 users. An EFA, CFA, and reliability analysis were performed to confirm reliability and validity. And structural equation was conducted to verify hypothesis. The main results are as follows. First, it was found that professionalism and interactivity had a significant positive effect on trust. And, accuracy, completeness, and variety were all found to have a significant positive effect on trust. Second, in the relationship between individual characteristic factors and self-consistency, it was found that professionalism and authenticity had a significant positive effect on self-consistency. In addition, in the relationship between content quality and self-consistency, accuracy, completeness, and diversity were found to have a positive effect on self-consistency along with trust. Third, in the relationship between trust and self-consistency on brand attitude and purchase intention, both trust and self-consistency were found to have a statistically significant positive effect on brand attitude. It was found that only self-consistency and brand attitude had a statistically significant positive effect on purchase intention. These findings showed that when users perceive professionalism and interaction with influencer, trust increases, and professionalism and progress increase self-consistency with influencer. In addition, in the case of content quality, it was found that trust and self-consistency responded positively when perceived content quality through content accuracy, completeness, and diversity. Also, trust and self-consistency increased attitudes toward brands and could influence consumption behavior such as purchase intention. Therefore, for effective marketing performance using influencer's influence in the field of influencer marketing, which has a strong information delivery on products and brands, not only personal characteristics such as professionalism, authenticity, and interactivity, but also quality of content should be considered. The above research results are expected to suggest implications for marketing strategies and practices as one available basic data to exert the expected effect of marketing using influencer.

• Journal of Distribution Science
• /
• v.19 no.9
• /
• pp.101-111
• /
• 2021

Purpose: This study discusses and discovers the important role of fashion product coolness in affecting consumers' perceived value and consumers' value creation behavior. Accordingly, fashion product coolness exerts a direct effect on perceived value while perceived value has a direct impact on value creation. Besides, fashion product coolness has an indirect effect on value creation through perceived value. Research design, data, and methodology: This study adopts the quantitative research approach by cross-sectional technical on a sample of 319 respondents in Vietnam. PLS-SEM has been used to analyze the survey data. Results: The result indicates that the proposed direct and indirect effects are significant. Specifically, utilitarian "coolness" and hedonic "coolness" have positive impacts on perceived value. The perceived value poses an impact on consumers' value creation behavior, including customer lifetime value and influencer value. Finally, the perceived value links utilitarian "coolness", hedonic "coolness" with customer lifetime value and influencer value. Conclusions: Fashion distribution is playing an increasingly important role in the retail sector of the economy. Fashion distribution activities are greatly influenced by the perceived value of consumers. The findings are supposed to strengthen the beliefs of fashion brands and retailers in the promotion of value creation and consumers' perceived value in the field of fashion distribution.

• International Journal of Advanced Culture Technology
• /
• v.10 no.1
• /
• pp.47-54
• /
• 2022

We analyze and compare the structure of the networks of Netflix, Disney+, and OCN, which are forerunners in OTT market, on Twitter. This study employs NodeXL pro as a visualization software package for social network analysis. As a result of the comparison with values of Vertices, Connected Components, Average Geodesic Distance, Average Betweenness Centrality, and Average Closeness Centrality. Netflix has comparative advantages at Vertices, Connected Components, and Average Closeness Centrality, OCN at Average Geodesic Distance, and Disney+ at Average Betweenness Centrality. Netflix has a more appropriate social network for influencer marketing than Disney+ and OCN. Based on the analysis results, the purpose of this study is to explain the structural differences in the social networks of Netflix, Disney+, and OCN in terms of influencer marketing.

• The Journal of the Korea Contents Association
• /
• v.21 no.3
• /
• pp.270-281
• /
• 2021

The emergence of social media and technical development of smart phone allows media users to produce, share and spread a variety of contents, which results in a big change in their media usage pattern. Among those changes, the most prominent one is Youtube's powerful growth. Creators' enthusiastic content productions and users' active sharing actions are caused of the growth. Recently, creators give a powerful effect on users as social media influencer, and the practice of influencer marketing has been focused. This current study is examined the effects of parasocial interaction and relationship on brand attitude and purchase intention. Specially, parasical interaction is divided into identification, interest, and experience parasocial interaction, and the divisions of relationship are trustworthy, friendship, understanding, and commitment. As a result, interest and trustworthy are significant predictors of brand attitude. Also, experience parasocial interaction is negative and friendship is positive predictors of purchase intention. Theoretical and practical implication are discussed.

• International journal of advanced smart convergence
• /
• v.11 no.2
• /
• pp.95-101
• /
• 2022

The development of the 4th industry has increased social media, and the rise of COVID-19 has stimulated non-face-to-face services. People's consumption patterns are also changing a lot due to non-face-to-face services. In this paper, food content keywords are derived through social network-based semantic network analysis, emotions are analyzed, and keywords applied to food recommendation platforms are input. We collected food, influencer, and corona keyword analysis data through Textom. A lot of research has been done through online reviews of existing influencer content. However, there is a lack of research on keyword sentiment analysis provided by influencers rather than consumers and research perspectives. This paper uploads language and topics derived through online reviews of existing publications and subscribers, and goes beyond the limits used in marketing methods. By analyzing keywords that influencers suggest when uploading content, you can apply data that applies them to food recommendation platforms and applications.

• The Journal of the Convergence on Culture Technology
• /
• v.8 no.2
• /
• pp.309-314
• /
• 2022

The purpose of this study is to examine how the characteristics of virtual influencer, which are rapidly emerging in recent years, affect consumers. To this end, the change in information accecptance intention was examined using the perceived attractiveness and social distance of consumers toward virtual influencers as independent variables. I found the more attractive consumers feel about virtual influencer and the closer they perceive social distance, the higher the intention to accept information. However, when virtual influencer was perceived as attractive, there was no difference in information acceptance intention according to social distance. On the other side, even if the virtual influencer was perceived as less attractive, the information acceptance intention was higher when the social distance was perceived as close than when it was not. Based on these results, I provided implications for the marketing strategy of virtual influencers.

• Journal of the Korea Convergence Society
• /
• v.13 no.1
• /
• pp.201-213
• /
• 2022

This study attempted to identify the influencing factors of Taobao Online Live Commerce influencer's attributes on Taobao Live Platform users' post-purchase satisfaction, repurchase intention and flow, and addiction. Through previous studies, researchers set the live commerce influencer attributes into four categories: expertise, attractiveness, interactivity, and aesthetics, and examined the effects of these attributes on consumers' repurchase intentions, flow and addiction. As a result of the study, it was confirmed that among the attributes of Live Commerce influencer, professionalism, interactivity, and aesthetics had a significant effect on the utilitarian shopping value in consumer satisfaction, and four attributes, including attractiveness, had a positive effect on the hedonic shopping value. In consumer satisfaction, hedonic shopping value had a positive effect on utilitarian shopping value satisfaction. In addition, it was found that consumers' satisfaction after purchase affects repurchase intention and immersion. The effect of flow on repurchase intention and addiction was also confirmed. It is hoped that this study will help revitalize influencer marketing in the growing live commerce market and provide basic data to contribute to establishing marketing strategies.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.4
• /
• pp.169-181
• /
• 2022

Currently, due to the activation of SNS live broadcasting, online services based on influencer live broadcasting are becoming a major consumption trend around the world. This study aims to verify the relationship between service quality, customer satisfaction, product characteristics, and acceptance intention for influencer broadcasting based on nfluencer broadcasting experiences in an Internet environment. This study conducted a survey of users who experienced live broadcasting on social media in Taiwan from June 29 to August 30, 2020, and a total of 253 copies were used for empirical analysis. The collected data were analyzed through SPSS 25.0. The results of the empirical analysis are summarized as follows. First, it was found that the service quality factors (reliability, tangibility, responsiveness, certainty, and empathy) of Taiwan's influencer live broadcast had a significant effect on live broadcast satisfaction. Second, it was found that the product characteristics of Taiwan's influencer live broadcasting had a significant effect on product satisfaction. Third, it was found that live broadcasting satisfaction and product satisfaction had a significant effect on the acceptance intention of new brands in Taiwan's influencer live broadcasting. This study will provide useful data for establishing efficient marketing strategies to improve live and product satisfaction and increase acceptance of new brands by identifying service quality factors and product characteristics of Taiwan's influencer Live Broadcasting.

• Asia-Pacific Journal of Business Venturing and Entrepreneurship
• /
• v.15 no.2
• /
• pp.171-181
• /
• 2020

As expanding marketing channels via social media, a small number of ordinary people have played a role in the information disseminator on social media. Therefore, this study aims to propose efficient social media marketing operation strategies by analyzing the influence relationship from various prospective on beauty channel social media marketing This study examined how beauty channel social media experience affects satisfaction and purchase intend. The components of social media experience were divided into entertainment, interaction, trendiness, usefulness for analysis. Social media experience was confirmed as a factor having significant effect on satisfaction and purchase intend. As a result, the social media experience had a significant effect on the satisfaction and purchase intend and the influence relationship of social media experience on each component was found to be entertainment, usefulness. Also, the expertise of beauty influencers had a significant influence on satisfaction and purchase intend. It is expected that the study results would be available as important data for beauty influencer-based marketing. This study attempted to search for a marketing stratege plan for efficient consumer management and derive and suggest practical implications.