With the widespread of fake online reviews, the detection of fake reviews has become a hot research issue. Despite the efforts of existing studies on fake review detection, the issues of imbalanced data and feature pruning still lack sufficient attention. To address these gaps, the present study proposes an ensemble model for the detection of fake online reviews. The model consists of four steps, and the first three steps are proposed to optimize the base classifiers: (i) Data resampling: We propose a novel way to address the data imbalance problem by combining the resampling and the grid search technique. (ii) Feature pruning: We propose an ablation study to drop unimportant features. (iii) Parameters optimization: We apply the grid search algorithm to determine suitable values of the relevant parameters for each base classifier. (iv) Classifier ensembling: We apply majority voting and stacking strategies to integrate the optimized base classifiers. The proposed data resampling method is also applied for the meta-classifier in the stacking ensemble model. This study produces advances in terms of combining different methods or algorithms into a model and the results show that the proposed ensemble model outperforms some existing techniques, thereby providing a new way to solve the data imbalance and feature pruning issues in the field of fake review detection.

In recent years, research on green consumption has grown at an exponential rate. Because this field of study has seen such rapid growth, research hotspots have been constantly changing, making it difficult for scholars to keep track of the most current hotspots and trends related to the topic of green consumption. In this study, we employed Citespace, COOC1.9, and SPSS 20 to map knowledge in the field of green consumption and to identify current research preferences, cooperative networks among countries and institutions, and collaborative networks among authors. A total of 2194 papers from the period of 2016–2022, sourced from the Web of Science, were collected as our data sample. The results show that the topic of green consumption has caught the attention of researchers around the world, particularly in some countries with high levels of economic development, for instance, in China, USA, and England. In addition, although there are numerous scholars who have focused on the study of green consumption, currently, there are few efficient and productive authors. Collaborative networks among authors, and cooperative networks among institutions and countries, are all still immature and need to be further strengthened. A principal component analysis (PCA) showed that the existing literature focuses on the following three topics: (1) consumer green behavior, (2) corporate green production, and (3) green marketing in social media. In addition, we conducted a multidimensional scaling (MDS) analysis to verify our results. Finally, we offer some suggestions intended to inform and enrich the field for future researchers.

Creative ads are applied widely in new product marketing. The present research explores the impact of creative ads (divergent vs. relevant ads) on purchase intention for really new products and incrementally new products. A series of studies concludes that (1) divergent ads are more effective for promoting incrementally new products, (2) relevant ads are more effective for promoting really new products, (3) self-referencing mediates the joint effect of creative ads and product newness on purchase intention, and (4) there is an inverted U-shaped relationship between self-referencing and purchase intention for new products. Theoretically, the authors argue that a moderate amount of self-referencing is particularly desirable—that is, there is a “Goldilocks region” that produces an optimal level of persuasion. They provide guidance to creative ad managers to help them reach the “Goldilocks region” when advertising new products.

Purpose: Despite the increasing trend of integrating artificial intelligence (AI) into organizational workforces, there remains a lack of understanding regarding how employee–AI interaction shapes employee service performance. The objective of this study is to investigate the impacts of employee–AI interaction fluency on in-role and out-of-role employee service performance in different delivery service (smart helmet services vs in-vehicle AI services) contexts.Design/methodology/approach: Drawing on mind perception theory and self-efficacy theory, a research model that reflected the impacts of employee–AI interaction fluency on employee service performance was developed. This research model was then tested through two empirical studies using data collected from frontline employees in the delivery service industry.Findings: The present study found that employee–AI interaction fluency acts both directly on employee service performance as well as indirectly via mind perceptions. Specifically, in the smart helmet service context, employee–AI interaction fluency affects in-role employee service performance via both perceived empathy and competence. By contrast, this impact shifts to out-of-role employee service performance in the in-vehicle AI service context, where perceived competence fully mediates the relationship between interaction fluency and service performance. In addition, the impact of employee–AI interaction fluency on perceived competence will be diminished among frontline employees with high levels of self-efficacy.Practical implications: This study offers valuable insights for AI device developers and managers aiming to improve both in-role and extra-role employee service performance through the lens of employee–AI interactions. In contexts with a high degree of employee–AI collaboration, such as smart helmet services, it is crucial to emphasize the empathy and competence of AI to boost in-role employee service performance. In contrast, in contexts with a lower level of employee–AI partnership, like in-vehicle AI services, the focus should be primarily on enhancing the competence of AI.Originality/value: The present paper reveals the critical role of employee–AI interaction fluency in shaping both in-role and out-of-role employee service performance in the smart helmet and in-vehicle AI service contexts. Moreover, this study also validated the significant negative moderating role of self-efficacy in the relationship between interaction fluency and employee service performance.