Purpose This study aims to propose a deep learning-based fake review detection model by combining authors' linguistic features and semantic information of reviews. Design/methodology/approach This study used 358,071 review data of Yelp to develop fake review detection model. We employed linguistic inquiry and word count (LIWC) to extract 24 linguistic features of authors. Then we used deep learning architectures such as multilayer perceptron(MLP), long short-term memory(LSTM) and transformer to learn linguistic features and semantic features for fake review detection. Findings The results of our study show that detection models using both linguistic and semantic features outperformed other models using single type of features. In addition, this study confirmed that differences in linguistic features between fake reviewer and authentic reviewer are significant. That is, we found that linguistic features complement semantic information of reviews and further enhance predictive power of fake detection model.

Purpose In this paper, we propose the method to extend topic modeling techniques in order to derive data-based research hypotheses when establishing research hypotheses for social sciences, As a concept in contrast to the existing deductive hypothesis establishment methodology for the social science research, the topic modeling technique was expanded to enable the so-called inductive hypothesis establishment methodology, and an analysis case of the Seongsan Ilchulbong online review based on the proposed methodology was presented. Design/methodology/approach In this paper, an extension architecture and extension algorithm in the form of extending the existing topic modeling were proposed. The extended architecture and algorithm include data processing method based on topic ratio in document, correlation analysis and regression analysis of processed data for topics derived by existing topic modeling. In addition, in this paper, an analysis case of the online review of Seongsan Ilchulbong Peak was presented by applying the extended topic modeling algorithm. An exploratory analysis was performed on the Seongsan Ilchulbong online reviews through the basic text analysis. The data was transformed into 5-point scale to enable correlation and regression analysis based on the topic ratio in each online review. A regression analysis was performed using the derived topics as the independent variable and the review rating as the dependent variable, and hypotheses could be derived based on this, which enable the so-called inductive hypothesis establishment. Findings This paper is meaningful in that it confirmed the possibility of deriving a causal model and setting an inductive hypothesis through an extended analysis of topic modeling.

Purpose The purpose of this study is to select the electronic architecture concept of the powertrain domain of the electronic platform to be applied to electric vehicles after 2025. Previously, the automotive electrical and electronic architecture was determined only by trend analysis, but the purpose was to determine the scenario based on the data and select it with clear evaluation indicators. Design/methodology/approach This study identified the function to be applied to the powertrain domain of next-generation electric vehicle, estimated the controller, defined the function feature list, organized the scenario candidates with the controller list and function feature list, and selected the final architecture scenario. Findings According to the research results, the powertrain domain of electric vehicles was selected as the architectural concept to apply the DCU (Domain Control Unit) and VCU (Vehicle Control Unit) integrated architecture to next-generation electric vehicles. Although it is disadvantageous or equivalent in terms of cost, it was found to be excellent in most indicators such as stability, security, and hardware demand.

Purpose Recently, hyper-realistic virtual influencers have received much attention in the field of corporate marketing. However, there is a lack of research that suggests specific processes affecting behavioral intentions through trust and attachment between virtual influencers and consumers. In addition, previous studies have failed to consider the characteristics of hyper-realistic virtual influencers. Therefore, this study investigates the effects of trust and attachment to hyper-realistic virtual influencers on consumers' behavioral intentions based on the trust-building model. Design/methodology/approach Based on the previous research, seven antecedent factors for trust-building were derived: Reality, Attractiveness, Awareness, Interactivity, Professionalism, Social Presence, and Predictability. Next, the survey was conducted on Chinese people who had experienced interacting with hyper-realistic virtual influencers on social network services within the last 3 months at the time of data collection. A total of 326 respondents were used for the final analysis and hypotheses were tested using a structural equation model technique. Findings The results of this study are as follows. First, this study confirmed that reality, attractiveness, awareness, social presence, and predictability as antecedent factors for trust-building of hyper-realistic virtual influencers have a positive effect on trust. Second, this study confirmed that trust in hyper-realistic virtual influencers has a significant positive effect on attachment. Lastly, this study confirmed that trust and attachment to the hyper-realistic virtual influencer significantly and positively affect relationship retention and purchase intentions.

Purpose This study aims to introduce a Smart-Platform for solving numerous problems in urban cities and improving citizens' convenience. This Smart-Platform is achieved by studying the City Data Hub technology to build and spread a Smart City Data Hub . Design/methodology/approach In this study, we analyzed the functions in detail and interlocking flows specific to the published City Data Hub module and designed a Smart-Platform with additional UI-based functions to improve users' convenience based on our previous experience. Findings The City Data Hub will provide a modular data hub platform functionality for application by different stakeholders. However, further research on detailed functionality and experience in interworking legacy systems will be required to apply the platform realistically. Therefore, we judged that this Smart-Platform, which supplements the City Data Hub with additional functions, would be useful for utilizing the City Data Hub in the future. Through the demonstration of the platform designed, it is also necessary to explore the direction of continuous development for the future.

Purpose The purpose of this study was to investigate the experience cues of chatbot services provided to existing customers familiar with the e-commerce environment, and to examine the effect of chatbot service's experience cues on customer experience and chatbot trust. Design/methodology/approach This study was conducted on consumers who experienced chatbot services in an e-commerce environment, the final 299 copies of valid data were obtained, and the research hypothesis was verified using PLS as a structural equation model. Findings As a result of the analysis, it was found that functional cues that cause customer experiences using chatbot services had a positive effect on cognitive and emotional experiences, human cues had a positive effect on cognitive, emotional and relational experiences, and customer experiences had a positive effect on chatbot trust.

Purpose The purpose of this study is to develop a virtual try-on deep learning model that can efficiently learn front and back clothes images. It is expected that the application of virtual try-on clothing service in the fashion and textile industry field will be vitalization. Design/methodology/approach The data used in this study used 232,355 clothes and product images. The image data input to the model is divided into 5 categories: original clothing image and wearer image, clothing segmentation, wearer's body Densepose heatmap, wearer's clothing-agnosting. We advanced the HR-VITON model in the way of Mixed-Precison, Gradient Accumulation, and sharing model weights. Findings As a result of this study, we demonstrated that the weight-shared MP-GA HR-VITON model can efficiently learn front and back fashion images. As a result, this proposed model quantitatively improves the quality of the generated image compared to the existing technique, and natural fitting is possible in both front and back images. SSIM was 0.8385 and 0.9204 in CP-VTON and the proposed model, LPIPS 0.2133 and 0.0642, FID 74.5421 and 11.8463, and KID 0.064 and 0.006. Using the deep learning model of this study, it is possible to naturally fit one color clothes, but when there are complex pictures and logos as shown in <Figure 6>, an unnatural pattern occurred in the generated image. If it is advanced based on the transformer, this problem may also be improved.

Purpose This study analyzed the topic of game review contents and how the characteristics of game reviews affect the reviews helpfulness. In addition, this study explore the content of game reviews according to the game's sales strategy such as early access strategy and releasing without early access. Design/methodology/approach We collected a list of 3,572 action genre games released in 2020. 58,336 online reviews were collected by random sampling 50 reviews in each games, and topic modeling was performed on those reviews. We dynamized the results of topic modeling and analyzed the effect on review helpfulness with multiple regression analysis. Findings The results of analysis indicate that the longer the review is or the shorter the time it is written, the more helpful the review is. In addition the topic with positive and negative review has a significant effect on the review helpfulness. As a result of exploratory analysis, games from early access had relatively fewer reviews of story-related topics than games that were released without early access. These findings can present direct guidelines for collecting specific opinions from customers in the game industry when releasing games.

Purpose Previous research on customer engagement in SNS marketing has mainly addressed the conceptualization of type of word-of-mouth messages. However, there is a lack of researches about the effect of the brand-page characteristics on the type of word-of-mouth messages. Therefore, this study examined the effect of brand-page characteristics in terms of the type of word-of-mouth messages as the main objective and the effect of the type of word-of-mouth messages in terms of the brand loyalty as the secondary objective in the context of Facebook. Design/methodology/approach The empirical research was based on a poll done through 400 research candidates in the Facebook and the final 342 responses were collected and used in statistical data analysis. The adaptability, trust, and validity to measurement model were verified and the structural relationship in the research model was analyzed through these 342 responses. The collected data verified hypotheses established using the SPSS statistical package and structural equation model using AMOS. Findings The results showed that the BP-information provision had a non-significant effect on the factual word-of-mouth message and a significant effect on the evaluative word-of-mouth message. The BP-reliability had a significant effect on the factual word-of-mouth message and the evaluative word-of-mouth message. The BP-entertainment had a significant effect on the factual word-of-mouth message and the evaluative word-of-mouth effect. The BP-interaction had a non-significant effect on the factual word-of-mouth message and the evaluative word-of-mouth message. Finally, the factual word-of-mouth message and the evaluative word-of-mouth message had a significant effect on the brand loyalty.

Purpose In the current environment of online shopping, the cost for consumers to obtain the information they need is decreasing, and the price of products is becoming more transparent, leading to increased price competition among enterprises for similar products. Given the widespread usage of limited-time promotion as a marketing method for enterprises in the context of e-commerce, it is great meaning to study and reveal the internal influence mechanism of limited-time promotion on consumers' impulsive consumption. Design/methodology/approach Based on the S-O-R theory, this study constructs a model of consumers' impulsive consumption in the context of e-commerce from the perspective of perceived price discount, with evoking sense and pleasure as mediating variables and perceived time pressure as moderating variables. Findings The results show that perceived price discount has a significant positive impact on evoking sense and pleasure. Evoking sense has a significant positive impact on pleasure. Both evoking sense and pleasure have a significant positive impact on consumers' impulsive consumption. Meanwhile, perceived time pressure plays a significant moderating role between perceived price discount and evoking sense, between perceived price discount and pleasure, and between evoking sense and consumers' impulsive consumption. Finally, based on the above findings, this study provides effective suggestions for e-commerce participants in the formulation of limited-time promotion strategies.