Hengyun Li, Lingyan Zhang, Rui (Ami) Guo, Haipeng Ji and Bruce X.B. Yu
This study aims to investigate the promoting effects of the quantity and quality of online review user-generated photos (UGPs) on perceived review usefulness. The research further…
Abstract
Purpose
This study aims to investigate the promoting effects of the quantity and quality of online review user-generated photos (UGPs) on perceived review usefulness. The research further tests the hindering effect of human facial presence in review photos on review usefulness.
Design/methodology/approach
Based on review samples of restaurants in a tourist destination Las Vegas, this study used an integrated method combining a machine learning algorithm and econometric modeling.
Findings
Results indicate that the number of UGPs depicting a restaurant’s food, drink, menu and physical environment has positive impacts on perceived review usefulness. The quality of online review UGPs can also enhance perceived review usefulness, whereas facial presence in these UGPs hinders perceived review usefulness.
Practical implications
Findings suggest that practitioners can implement certain tactics to potentially improve consumers’ willingness to share more UGPs and UGPs with higher quality. Review websites could develop image-processing algorithms for identifying and presenting UGPs containing core attributes in prominent positions on the site.
Originality/value
To the best of the authors’ knowledge, this study is the first to present a comprehensive analytical framework investigating the enhancing or hindering roles of review photo quantity, photo quality and facial presence in online review UGPs on review usefulness. Using the heuristic-systematic model as a theoretical foundation, this study verifies the additivity effect and attenuation effect of UGPs’ visual elements on judgements of online review usefulness. Furthermore, it extends scalable image data analysis by adopting a deep transfer learning algorithm in hospitality and tourism.
Details
Keywords
Because of increasing wealth inequality, China has been confronted with resentment against the rich (referred to hereafter as RAR or Choufu in Chinese), which is a growing concern…
Abstract
Purpose
Because of increasing wealth inequality, China has been confronted with resentment against the rich (referred to hereafter as RAR or Choufu in Chinese), which is a growing concern owing to its potential to foment social conflict. Drawing on social comparison and deonance theories, this paper aims to provide theoretical insights into RAR within the Chinese context and to develop an RAR scale. Following spillover theory, the attitudinal and behavioral outcomes of RAR in organizational settings will be explored.
Design/methodology/approach
This research consists of two studies. Study 1 conceptualizes RAR and develops an RAR scale by using three separate samples. Exploratory and confirmatory factor analyses are conducted to establish scale reliability and validity. Study 2 uses hierarchical linear regression analysis to test whether employees’ RAR attitude spills over from the societal to the organizational setting.
Findings
Results suggest that RAR can be conceptualized as two distinct but related dimensions – emotional RAR and moral RAR. These two forms spill over to the workplace, influencing employees’ work attitudes and behaviors. Emotional RAR relates negatively to life satisfaction and prosocial organizational behaviors and positively to unethical organizational behaviors. Moral RAR relates negatively to pay satisfaction and positively to prosocial behaviors.
Practical implications
This research suggests that RAR has spillover effects from societal to organizational settings and demonstrates that a more robust understanding of employees’ workplace experience requires acknowledging social experiences, such as conflicts beyond the workplace.
Originality/value
This research contributes to the conflict management literature by exploring RAR as a negative attitude that serves to potentially ignite social conflict. It not only develops a theory-grounded, conceptual RAR model and a reliable RAR scale but also for the first time explores RAR attitudinal and behavioral outcomes beyond the social domain. This study serves as a meaningful touchstone for future research to incorporate social attitudes into organizational behavior research.
Details
Keywords
Wei Du, Qiang Yan, Wenping Zhang and Jian Ma
Patent trade recommendations necessitate recommendation interpretability in addition to recommendation accuracy because of patent transaction risks and the technological…
Abstract
Purpose
Patent trade recommendations necessitate recommendation interpretability in addition to recommendation accuracy because of patent transaction risks and the technological complexity of patents. This study designs an interpretable knowledge-aware patent recommendation model (IKPRM) for patent trading. IKPRM first creates a patent knowledge graph (PKG) for patent trade recommendations and then leverages paths in the PKG to achieve recommendation interpretability.
Design/methodology/approach
First, we construct a PKG to integrate online company behaviors and patent information using natural language processing techniques. Second, a bidirectional long short-term memory network (BiLSTM) is utilized with an attention mechanism to establish the connecting paths of a company — patent pair in PKG. Finally, the prediction score of a company — patent pair is calculated by assigning different weights to their connecting paths. The semantic relationships in connecting paths help explain why a candidate patent is recommended.
Findings
Experiments on a real dataset from a patent trading platform verify that IKPRM significantly outperforms baseline methods in terms of hit ratio and normalized discounted cumulative gain (nDCG). The analysis of an online user study verified the interpretability of our recommendations.
Originality/value
A meta-path-based recommendation can achieve certain explainability but suffers from low flexibility when reasoning on heterogeneous information. To bridge this gap, we propose the IKPRM to explain the full paths in the knowledge graph. IKPRM demonstrates good performance and transparency and is a solid foundation for integrating interpretable artificial intelligence into complex tasks such as intelligent recommendations.