PurposeMost studies on algorithm aversion are scenario-based online or laboratory experiments and review type analysis, and few studies apply empirical research methods. Further to this, the research is mainly focused on developed countries, with nearly two-thirds of algorithm aversion and appreciation surveys and experimental studies conducted using American samples. More than 80% of the studies used European or United States participants. However, research in the context of developing countries (e.g. China) may provide different insights.Design/methodology/approachDifferent from traditional empirical research methods, this study combines SEM and ANN two-stage method, which does not only cover the hypothesis testing of the linear relationship in the compensation model, but also captures the nonlinear non-compensation relationship in the neural network model.FindingsAlgorithm transparency, algorithm accuracy, tolerance and surprise degree have a significant negative impact on algorithm aversion, while user perceived algorithm control and expectancy violations have a significant positive impact on algorithm aversion. Algorithm transparency, algorithm accuracy and tolerance significantly negatively impact expectancy violations, while overconfidence significantly positively impacts expectancy violations. Algorithm accuracy significantly positively impacts surprise degree, while overconfidence significantly negatively impacts surprise degree. Timeliness not only has a significant negative impact on algorithm aversion, but also plays a significant moderating role on the impact of expectancy violations and surprise degree on algorithm aversion. In terms of the importance of standardization, expectancy violations are the most important, followed by algorithm accuracy, tolerance, surprise degree, user perceived algorithm control, algorithm transparency, and timeliness. The ANN model can predict algorithm aversion with an accuracy of 85.4%.Originality/valueThis study combines SEM and ANN two-stage method was used to successfully verify the effects of algorithm characteristics, receiver characteristics, recommendation system characteristics and situational factors (expectancy violations, surprise degree) on algorithm aversion. It provides beneficial practical insights for recommendation systems, algorithm developers to optimize algorithms, and users to effectively utilize algorithms.

PurposeCompensatory consumption focuses on the psychological value of products. Special agricultural products have symbolic and social functions that effectively meet psychological needs and stimulate compensatory consumption behavior. The social commerce context not only enriches consumer experience but also influences consumer purchase decisions. This study constructs a model based on the elaboration likelihood model (ELM) and the stimulus-organism-response (SOR) theory to explore the mechanism of compensatory consumption behavior of special agricultural products in a social commerce context.Design/methodology/approachThis study uses a two-stage method of partial least squares structural equation model (PLS-SEM) and fuzzy set qualitative comparative analysis (fsQCA) to analyze 523 valid samples collected through random sampling. PLS-SEM was used to examine the relationships and effects between the variables; fsQCA was used to conduct a cohort analysis between the variables to further reveal the complexity and diversity of compensatory consumption behaviors.FindingsPLS-SEM indicates that product attributes and social affordances influence consumers' triggering of compensatory consumption behavior for control and belongingness needs. fsQCA shows that there are three different modes, and the satisfaction of belongingness or control needs is a necessary condition for triggering compensatory consumption behavior.Originality/valueThere is limited research on compensatory consumption behavior specifically focused on special agricultural products. This study explores the influencing factors and mechanisms of compensatory consumption behavior related to special agricultural products. The occurrence of compensatory consumption behavior is not only influenced by product attributes but also by the social commerce environment. In marketing strategies, it is important to not only consider product characteristics but also pay attention to consumers' social and psychological needs.

Asia Pacific Journal of Tourism Research was created in 1995 and published articles in 1996. This study analyzes the journal using bibliometric methods for 1243 articles published in the journal from 1996 to 2023. It uses several indicators to demonstrate the journal's performance and contributions. The study shows that the most productive country and author are China and Rob Law, respectively. Furthermore, the collaboration, co-citation, and co-occurrence networks are created using Gephi, VOSviewer, and CiteSpace. This study provides a comprehensive overview and APJTR may later focus on topics such as tourist destinations, consumer behavior, smart tourism, and sustainable development.

Purpose Although user stickiness has been studied for several years in the field of live e-commerce, little attention has been paid to the effects of streamer attributes on user stickiness in this field. Rooted in the stimulus-organism-response (S-O-R) theory, this study investigated how streamer attributes influence user stickiness. Design/methodology/approach The authors obtained 496 valid samples from Chinese live e-commerce users and explored the formation of user stickiness using partial least squares-structural equation modeling (PLS-SEM). Artificial neural network (ANN) was used to capture linear and non-linear relationships and analyze the normalized importance ranking of significant variables, supplementing the PLS-SEM results. Findings The authors found that attractiveness and similarity positively impacted parasocial interaction (PSI). Expertise and trustworthiness positively impacted perceived information quality. Moreover, streamer-brand preference mediated the relationship between PSI and user stickiness, as well as the relationship between perceived information quality and user stickiness. Compared to PLS-SEM, the predictive ability of ANN was more robust. Further, the results of PLS-SEM and ANN both showed that attractiveness was the strongest predictor of user stickiness. Originality/value This study explained how streamer attributes affect user stickiness and provided a reference value for future research on user behavior in live e-commerce. The exploration of the linear and non-linear relationships between variables based on ANN supplements existing research. Moreover, the results of this study have implications for practitioners on how to improve user stickiness and contribute to the development of the livestreaming industry.

The increased use of AI in business has spurred an explosion in algorithm aversion research. The absence of scientific measurement instruments has caused the empirical research on the structural dimensions and measurement scales of algorithm aversion to stagnate, and the field is currently just in the exploratory stages of investigation. The results of experimental research and polls on algorithm aversion and appreciation may not be as broadly applicable as they may be because roughly two thirds of them used U.S. samples. Thus, extending from previous research, this work applies grounded theory to investigate the dimensionality of the structural dimensions of algorithm aversion using data from Chinese user interviews as well as the MicroBlog, Zhihu, and CSDN corpus. The scale was tested through the processes of questionnaire, exploratory factor analysis, and validation factor analysis to construct the scale of algorithmic aversion. The study finds five dimensions of algorithm aversion: Algorithm power gameplay, Algorithm user lock-in, Algorithm cognitive bias, Algorithm recommendation preference, and Recommendation algorithm adoption. The scale has a good level of validity and reliability and comprises 22 items. The findings of this study will support theoretical underpinnings for AI marketing and practical research on algorithm aversion in recommendation systems.

The emerging e-commerce is increasingly influenced by consumers' sense of mobile shopping presence. Understanding correlation and match rules across spatial and temporal scene cues, as well as corresponding behavioral responses from mobile shopping, has become a new hot topic in the behavioral implementation intention theory. This study proposes a model incorporating time submissiveness, perceived visual-spatial crowding, psychological cost, and satisfaction to investigate the influencing mechanism and configuration paths of consumers' mobile shopping implementation intention. To test the relations, we used a structural equation model (SEM) and fuzzy-set qualitative comparative analysis (fsQCA). The SEM model showed that both psychological cost and satisfaction exerted a positive impact on mobile shopping implementation intention. Time submissiveness and perceived visual-spatial crowding exerted a significant impact on mobile shopping implementation intention through the mediation of psychological cost and satisfaction. The fsQCA method examined the antecedents resulting in high and non-high implementation intention. This study better provides theoretical and practical inspiration for mobile consumers' psychological characteristics and presence experience exploration.

Contextual cues can stimulate consumers' memory, increase their attention, and promote their purchase behaviour. Nevertheless, the dynamic mechanism of online shopping behaviour implementation intention in intricate social contexts has not been investigated comprehensively. Based on the theory of implementation intention, this study constructs a research framework from the standpoint of dual contextual cues of businesses and consumers, designs corresponding models by using system dynamics method, and validates its efficacy and sensitivity to elucidate the dynamic implementation intention mechanism of consumers' social shopping behaviour. The purchase implementation intention of consumers is influenced by not only their psychological changes but also businesses, showing a fluctuating upward trend over time. Consumers' implementation intention is highly sensitive to quality and safety cues and prospective memory of businesses degree. This study expands the viewpoint of contextual cues theory from the perspective of duality, upgrades the systematic mechanism of contextual cues and implementation intention, and finally offers relevant suggestions for businesses to promote consumer purchase behaviour.

Under the COVID-19, fresh food e-commerce has acquired new sales channels through live shopping, and the use of live broadcasts has become a hot spot in management and practice. However, there is little empirical evidence of the influence of live streaming on sales. This study combines the perspective of People-Goods-Scene and the push-pull theory, and proposes a two-stage method for forecasting sales volumes using structural equation models and artificial neural networks. It was found that the number of page views was the strongest predictor of live broadcast sales, while the numbers of interactive comments, live broadcasts with goods, and videos with goods, together with clean labels were weakly predictive. A comprehensive neural network model showed an accuracy of 83.76% in the prediction of live broadcast sales. These research results provide a theoretical basis for the prediction of fresh food shopping behavior in live-broadcast e-commerce from the perspectives of the consumers and the goods yard and provide ideas for the design of live broadcast content and optimization of user experience.

PurposeContextual cues have become a hot research topic in the field of mobile consumer behavior, owing to the continuous rise of digital marketing. However, the complex online shopping scene makes it challenging to directly identify the association between the characteristics of contextual cues and consumer behavior. Presently, few studies have only systematically extracted and refined the types and characteristics of contextual cues. The purpose of this study is to explore the types and mechanisms of contextual cues in online shopping scenarios.Design/methodology/approachThis study uses the word2vec algorithm, grounded theory and co-occurrence cluster method, along with online shopping word-of-mouth (WOM) text and consumer behavior theory, in order to explore different types of contextual cues and its efficiency from 5,619 comment corpus.FindingsThis study puts forward the following conclusions. (1) From the perspective of online shopping, contextual cues comprise aesthetic perception cues, value perception cues, trust-dependent cues, time perception cues, memory attention cues, spatial perception cues, attribute cues and relationship cues. (2) Based on the online shopping scenarios, contextual cues and their interaction effects exert an effect on consumer satisfaction, recommendation, purchase and return behavior.Originality/valueThe study conclusions are helpful to further reveal the deep association between contextual cues and consumer behavior in the process of online shopping, thus providing practical and theoretical enlightenment for enterprises to not only effectively reshape the scene but also promote the consumers' active purchase behavior.

In this study, we examined the spatial difference of environmental regulation intensity in 30 provinces (autonomous regions and municipalities directly under the central government) of China. It was found that there were significant differences in environmental regulation intensity in the four regions, with a decreasing trend of “west–central–northeast–east” on the whole. Applying the Theil index showed that intra-regional differences accounted for more than 85% of the overall differences in environmental regulation intensity. Goble Moran’s I index was used to verify the spatial correlation of China’s environmental regulation. It was found that the p-value of Goble Moran’s I index was less than 10% in 7 years from 2010 to 2019. It was verified that the environmental regulation intensity in China has had a spatial correlation. In addition, a positive spatial correlation between the environmental regulation intensity in each province was found, indicating that an increase in the environmental regulation intensity of one province will lead to an increase in the intensity of environmental regulation in neighboring provinces. Finally, through the construction of a spatial Markov model to test the spillover effect of environmental regulation intensity in China, it was found that the local environmental regulation intensity will change to different degrees when there are spatial differences in the intensity of environmental regulation in neighboring provinces. This research will be helpful for provincial governments to formulate appropriate environmental regulation targets based on regional characteristics, which is of great significance for China’s and other countries’ green economic development and other countries to solve the contradiction between environmental pollution and economic development.

Vehicle re-identification (Re-ID) is urgently demanded to alleviate thepressure caused by the increasingly onerous task of urban traffic management. Multiple challenges hamper the applications of vision-based vehicle Re-ID methods: (1) The appearances of different vehicles of the same brand/model are often similar; However, (2) the appearances of the same vehicle differ significantly from different viewpoints. Previous methods mainly use manually annotated multi-attribute datasets to assist the network in getting detailed cues and in inferencing multi-view to improve the vehicle Re-ID performance. However, finely labeled vehicle datasets are usually unattainable in real application scenarios. Hence, we propose a Discriminative-Region Attention and Orthogonal-View Generation (DRA-OVG) model, which only requires identity (ID) labels to conquer the multiple challenges of vehicle Re-ID.The proposed DRA model can automatically extract the discriminative region features, which can distinguish similar vehicles. And the OVG model can generate multi-view features based on the input view features to reduce the impact of viewpoint mismatches. Finally, the distance between vehicle appearances is presented by the discriminative region features and multi-view features together. Therefore, the significance of pairwise distance measure between vehicles is enhanced in acomplete feature space. Extensive experiments substantiate the effectiveness of each proposed ingredient, and experimental results indicate that our approach achieves remarkable improvements over the state- of-the-art vehicle Re-ID methods on VehicleID and VeRi-776 datasets.

PurposeThe purpose of this paper is to assess the influence mechanism of the word-of-mouth reputation of influencers.Design/methodology/approachThis study explored word-of-mouth reputation from four characteristics of information source of influencers: credibility, professionalism, interactivity and attractiveness. The grounded theory was used to extract the characteristic indicators of influencers and used questionnaire surveys to obtain 218 valid samples. The fuzzy-set qualitative comparative analysis (fsQCA) was used for the configuration analysis.FindingsThe results revealed the following: (1) a causal asymmetric correlation exists between the driving mechanism of high word-of-mouth reputation and non-high word-of-mouth reputation; (2) influencers matching high word-of-mouth reputation comprises potential, developmental and almighty types, whereas live streaming influencer matching non-high word-of-mouth reputation comprises elementary and groping types; and (3) all factors must be combined to play a role, and neutral permutations of two solutions were found among the three overall solutions to attain high word-of-mouth reputation; (4) the combination of high user activity and high exposure is the core configuration that results in high word-of-mouth reputation.Practical implicationsThis study provides recommendation for consumers, live streamers, brand and e-commerce platform on how to promote the sustainable and healthy development of influencer marketing.Originality/valueThis study focused on elucidating how the characteristics of information source affect the word-of-mouth reputation of influencers and have a reference value for the research on word-of-mouth reputation in the context of live commerce.

Triggering shopping desire with scenes has become an important means of merchants’ marketing. However, there are few studies on the association mechanism between cognitive-emotional interaction responses and implementation intentions in different scenarios. A total of 390 valid samples were obtained through questionnaire surveys, using the fuzzy-set qualitative comparative analysis method（fsQCA）, Based on the SOR model, from the perspective of multiple concurrent causality, the impact mechanism of the seven conditions of visual perception cues, quality safety cues and time cues, and the interaction configuration effects of perceived pleasure and perceived trust on implementation intentions was explored. It was found that: A single antecedent condition is not a necessary condition for the high/non-high implementation intentions of mobile shopping behaviors; The driving mechanism to realize the high implementation intentions of mobile shopping behaviors includes an overall solution, divided into 4 paths, revealing that the perception of high privacy protection is the core condition leading to the high implementation intentions of mobile shopping behaviors; The driving mechanism of non-high implementation intentions of mobile shopping behaviors has six paths, and there is a causal asymmetric relationship with the driving mechanism of high implementation intentions. The research conclusions enrich and develop the relevant theories of contextual clues, and provide specific suggestions and measures for e-commerce companies’ precise marketing and user experience improvement.

Convolutional neural networks (CNNs) have been achieving remarkable results in medical image segmentation. However, for accurate segmentation of subcortical brain structure in MR images, it is still a challenge due to the ambiguous boundaries, the complex structures, and the various shapes, which limits their clinical application. In this paper, we focus on utilizing multi-scale image contexts and attention mechanisms to improve networks’ ability to learn discriminative feature representation for accurate segmentation and present a novel FCNN architecture called multis-scale guided squeeze-and-excitation network (MSGSE-Net). In particular, we first propose the multi-scale guided squeeze-and-excitation (MSGSE) attention module which can progressively and selectively aggregate discriminative features. In contrast to existing attention modules, the MSGSE module performs an adaptive recalibration that features at different locations of the feature map are recalibrated under the guidance of multi-scale contexts. Then multi-scale spatial attention supervision is adopted to enhance the intra-class homogeneity and inter-class distinction of the attention weights. Moreover, we propose a novel entropy-weighted Dice loss (EDL) to force the network to focus on the ambiguous voxels around the boundaries of subcortical structures. We evaluate the proposed method on two challenging benchmark datasets (the IBSR dataset and the MALC dataset). The experimental results show that our model consistently yields better segmentation performance than several state-of-the-art methods and improves the segmentation Dice score by 1.6% at most compared with baseline method U-Net. Our code is available at https://github.com/neulxlx/MSGSE-Net.

Visual presentation is a critical factor in ascertaining the purchase decision and behavior of mobile consumers. However, whether a simple or a complex interface is more effective in promoting purchase intentions remains inconclusive. This study combines task-technology fit (TTF) theory and technology acceptance model (TAM) to propose a comprehensive model suitable for mobile shopping circumstances to investigate the mechanism of implementation intentions of online shopping under visual and technical stimulation. We obtained 504 valid samples through questionnaire surveys and used structural equation modeling (SEM) and fuzzy-set qualitative comparative analysis (fsQCA) methods to elucidate the complex causal patterns of implementation intentions of online shopping. The SEM results revealed that security precautions and user experience directly affected the implementation intentions of online shopping behavior, while interface visual complexity, visual search efficiency, and mobile payment indirectly affected the implementation intentions of online shopping. In addition, the fsQCA results revealed a causal asymmetric relationship between the driving mechanism of high and non-high implementation intentions of online shopping. All factors must be combined to play a role, and there exist three overall solutions to attain high implementation intentions of online shopping. Among them, we found neutral permutations of one solution, suggesting that the combination of high visual search efficiency and high security precautions is the core configuration that results in high implementation intentions of online shopping. Overall, this study broadens the application perspective of TTF and TAM, and provides certain practical enlightenment for e-commerce enterprise marketing.

Purpose The paper aims to clarify the importance of the psychological processing of contextual cues in the mining of individual attention resources. In recent years, the research of more open spatial perspective, such as spatial and scene perception, has gradually turned to the recognition of contextual cues, accumulating rich literature and becoming a hotspot of interdisciplinary research. Nevertheless, besides the fields of psychology and neuroscience, researchers in other fields lack systematic knowledge of contextual cues. The purpose of this study is to expand the research field of contextual cues. Design/methodology/approach We retrieved 494 papers on contextual cues from SCI/SSCI core database of the Web of Science in 1992–2019. Then, we used several bibliometric and sophisticated network analysis tools, such as HistCite, CiteSpace, VOSviewe and Pajek, to identify the time-and-space knowledge map, research hotspots, evolution process, emerging trends and primary path of contextual cues. Findings The paper found the core scholars, major journals, research institutions, and the popularity of citation to be closely related to the research of contextual cues. In addition, we constructed a co-word network of contextual cues, confirming the concept of behavior implementation intentions and filling in the research gap in the field of behavior science. Then, the quantitative analysis of the burst literature on contextual cues revealed that the research on it that focused more on multi-objective cues. Furthermore, an analysis of the main path helped researchers clearly understand and grasp in the development trend and evolution track of contextual cues. Originality/value Given academic research usually lags behind management practice, our systematic review of the literature to a certain extent make a bridge between theory and practice.

执行意向在行为科学领域发挥着至关重要的预测价值,如何把握网络文化消费者行为规律成为当前热点课题.文章基于执行意向理论,以网络文化消费网民群体为研究对象,探索网络情景下文化消费行为执行意向的影响机制.实证研究结果表明:感知价值、参照群体、用户信任与执行意向均存在显著正相关,且感知价值为首要因素,信息质量对执行意向的影响不显著.调节效应分析发现,时间压力在感知价值、信息质量、用户信任对执行意向的影响中均存在调节作用,时间压力在参照群体对执行意向的影响中不存在调节作用.

中国跨境电商平台的生态演化与共生理念打破了品牌的区域性竞争关系,以客户为中心的品牌重塑与品牌信誉正影响着中国消费者群体的全球购买决策,探究其对来源国品牌依恋的形成机制具有重要现实价值.本研究应用组态思维和fsQCA方法,以网易考拉24个品牌为案例研究对象,探索中国消费者对来源国品牌依恋的因果复杂性问题.研究发现:(1)高品牌依恋的驱动路径分为4条,揭示了不同的条件组态可以产生多种实现高品牌依恋的路径.其中,路径1、路径2为高口碑和高情感倾向的联动匹配;路径3为高品牌国际影响力、高卷入度和高口碑的联动匹配;路径4为高品牌国际影响力、高卷入度和高群体认同的联动匹配.(2)非高品牌依恋的驱动路径分为4条,且与高品牌依恋的驱动机制存在因果非对称关系.本研究结论有助于拓展品牌信誉与价值共创匹配的品牌管理视角,为跨境电商企业如何有效促进品牌依恋提供了理论与实践启示.