The impact of cover image authenticity and aesthetics on users’ product-knowing and content-reading willingness in social shopping community

Building CNN-Based Models for Image Aesthetic Score Prediction Using an Ensemble

In this paper, we propose a framework that constructs two types of image aesthetic assessment (IAA) models with different CNN architectures and improves the performance of image aesthetic score (AS) prediction by the ensemble. Moreover, the attention regions of the models to the images are extracted to analyze the consistency with the subjects in the images. The experimental results verify that the proposed method is effective for improving the AS prediction. The average F1 of the ensemble improves 5.4% over the model of type A, and 33.1% over the model of type B. Moreover, it is found that the AS classification models trained on the XiheAA dataset seem to learn the latent photography principles, although it cannot be said that they learn the aesthetic sense.

Exploring the Impact of Online and Offline Channel Advantages on Brand Relationship Performance: The Mediating Role of Consumer Perceived Value

As omnichannel shopping behavior becomes increasingly popular among consumers, how to leverage the respective advantages and synergies of online and offline channels to retain customers for a long time is an urgent issue for retailers to solve. The purpose of this study is to explore the key advantages of online and offline channels influencing the omnichannel shopping experience in the decision-making process, and investigate their impact on consumer perceived value and brand relationship performance, as well as the interaction effect of online channel advantages and offline channel advantages. This study identifies the key advantages of online channels (search convenience, customer-generated information richness, and social connection) and offline channels (direct product experience, sales-staff assistance, and servicescape aesthetics) through a qualitative study and relevant literature review. Then, the proposed research framework was tested using the structural model equation in AMOS and hierarchical regression techniques in SPSS utilizing data from 347 shoppers. The results show that all variables except customer-generated information richness have positive impact on consumer perceived value. Other than search convenience and customer-generated information richness, consumer perceived value mediates the effect of other variables on brand relationship performance. Additionally, the interaction effect of online and offline channel advantages positively impacts consumer perceived value.

Effects of Social Media Usage on Consumers' Purchase Intention in Social Commerce: A Cross-Cultural Empirical Analysis

Social commerce has produced enormous economic benefits as well as challenges for organizations, individuals, and industries. However, social media usage does not necessarily generate users' intention to purchase on social commerce websites. How social media usage influences users' purchase intention on social commerce websites still deserves more scholarly attention and this seems particularly important when social commerce transcends borders and countries. Taking an interdisciplinary perspective, the current study adopted a survey research method and identified the roles of social media usage in arousing users' purchase intention on social commerce websites in a culturally diversified environment. The data was collected from 2,058 international students coming from 135 countries and was analyzed using MPLUS based structural equation modeling. The research unveils the pathway whereby social media usage serves to generate users' purchase intention on social commerce websites. Importantly, users' cultural intelligence has been found to play a significant role mediating the effects of social media usage on users' intention. Further, cultural distance was found to attenuate the effects of social media usage on cultural intelligence. Based on the research findings, the study suggests that social commerce practitioners should be fully aware of the enabling roles of social media and cultural intelligence as well as the deterring role of cultural distance when arousing customers' purchasing intention in cross-cultural business operations. Any measures facilitated by social media usage to improve international consumers' cultural intelligence and mitigate the negative effects of cultural distance are supposed to be effective to enhance their purchasing intention. Accordingly, the study confirms the mutually melt and integrative relationships between information technology advancement and business prosperity in cross-cultural environment, which eventually contribute to sustainable development of society.

Exploring Metrics to Establish an Optimal Model for Image Aesthetic Assessment and Analysis

To establish an optimal model for photo aesthetic assessment, in this paper, an internal metric called the disentanglement-measure (D-measure) is introduced, which reflects the disentanglement degree of the final layer FC (full connection) nodes of convolutional neural network (CNN). By combining the F-measure with the D-measure to obtain an FD measure, an algorithm of determining the optimal model from many photo score prediction models generated by CNN-based repetitively self-revised learning (RSRL) is proposed. Furthermore, the aesthetics features of the model regarding the first fixation perspective (FFP) and the assessment interest region (AIR) are defined by means of the feature maps so as to analyze the consistency with human aesthetics. The experimental results show that the proposed method is helpful in improving the efficiency of determining the optimal model. Moreover, extracting the FFP and AIR of the models to the image is useful in understanding the internal properties of these models related to the human aesthetics and validating the external performances of the aesthetic assessment.