Search results

As more firms adopted AI-related services in recent years, AI service failures have increased. However, the potential costs of AI implementation are not well understood, especially the effect of AI service failure events. This study examines the influences of AI service failure events, including their industry, size, timing, and type, on firm value.

This study will conduct an event study of 120 AI service failure events in listed companies to evaluate the costs of such events.

First, AI service failure events have a negative impact on the firm value. Second, small firms experience more share price declines due to AI service failure events than large firms. Third, AI service failure events in more recent years have a more intensively negative impact than those in more distant years. Finally, we identify different types of AI service failure and find that there are order effects on firm value across the service failure event types: accuracy > safety > privacy > fairness.

First, this study is the initial effort to empirically examine market reactions to AI service failure events using the event study method. Second, this study comprehensively considers the effect of contextual influencing factors, including industry type, firm size and event year. Third, this study improves the understanding of AI service failure by proposing a novel classification and disclosing the detailed impacts of different event types, which provides valuable guidance for managers and developers.

This study analyzes the evolution of topics related to COVID-19 on Chinese social media platforms with the aim of identifying changes in netizens' concerns during the different stages of the pandemic.

In total, 793,947 posts were collected from Zhihu, a Chinese Question and Answer website, and Dingxiangyuan, a Chinese online healthcare community, from 31 December, 2019, to 4 August, 2021. Topics were extracted during the prodromal and outbreak stages, and in the abatement–resurgence cycle.

Netizens' concerns varied in different stages. During the prodromal and outbreak stages, netizens showed greater concern about COVID-19 news, the impact of COVID-19 and the prevention and control of COVID-19. During the first round of the abatement and resurgence stage, netizens remained concerned about COVID-19 news and the prevention and control of the pandemic, however, less attention was paid to the impact of COVID-19. During later stages, popularity grew in topics concerning the impact of COVID-19, while netizens engaged more in discussions about international events and the raising of spirits to fight the global pandemic.

This study contributes to the practice by providing a way for the government and policy makers to retrospect the pandemic and thereby make a good preparation to take proper measures to communicate with citizens and address their demands in similar situations in the future.

This study contributes to the literature by applying an adapted version of Fink's (1986) crisis life cycle to create a five-stage evolution model to understand the repeated resurgence of COVID-19 in Mainland China.

Although online reviews have become a key source of information for consumer purchasing decisions, little is known about how the concreteness of language used in these reviews influences perceptions of deception. This study aims to address this important gap by drawing on psycholinguistic research and Language Expectancy Theory to examine how and when the concreteness of online reviews (abstract vs concrete) impacts consumers’ perceived deception.

Two scenario-based experiments were conducted to examine how the concreteness of online reviews (abstract vs concrete) influences consumers’ perceptions of deception, considering the mediating role of psychological distance to online reviews and the moderating effects of Machiavellianism (Mach) and reviewer identity disclosure.

Online reviews that include concrete language lead to lower perceived deception by reducing consumers’ psychological distance from the review. For consumers with higher levels of Mach, online reviews written in abstract (vs concrete) language result in higher perceived deception via psychological distance, while for consumers with lower Mach, online reviews written in concrete (vs abstract) language result in higher perceived deception via psychological distance.

To the best of the authors’ knowledge, this study is one of the first to highlight the relevance of linguistic style (i.e. concrete review vs abstract review) on consumers’ perceived deception toward online reviews in the context of e-commerce.

The framework enables managers of online retailing platforms to identify the most effective strategies to decrease consumers’ perceived deception via the appropriate utilize of linguistic styles of online reviews.

This study contributes to both theory and practice by deepening knowledge of how and when the concreteness of online reviews (abstract vs concrete) affects consumers’ perceived deception and by helping managers of online retailing platforms make the most effective\ strategies for reducing consumers’ perceived deception toward online reviews during online shopping.