Lin Xiao’s research while affiliated with Nanjing University of Aeronautics and Astronautics and other places

In contemporary organizational research, when dealing with large heterogeneous datasets and complex relationships, statistical modeling focused on developing substantive explanations typically results in low predictive accuracy. In contrast, machine learning (ML) exhibits remarkable strength for prediction, but suffers from an unexplainable analytical process and output—thus ML is often known as a “black box” approach. The recent development of explainable machine learning (XML) integrates high predictive accuracy with explainability, which combines the advantages inherent in both statistical modeling and ML paradigms. This paper compares XML with statistical modeling and the traditional ML approaches, focusing on an advanced application of XML known as evolving fuzzy system (EFS), which enhances model transparency by clarifying the unique contribution of each modeled predictor. In an illustrative study, we demonstrate two EFS-based XML models and conduct comparative analyses among XML, ML, and statistical models with a commonly-used database in organizational research. Our study offers a thorough description of analysis procedures for implementing XML in organizational research, along with best-practice recommendations for each step as well as Python code to aid future research using XML. Finally, we discuss the benefits of XML for organizational research and its potential development.

As a rapidly developing topic, online reviews have aroused great interest among researchers. Although the existing research can help to explain issues related to online reviews, the scattered and diversified nature of previous research hinders an overall understanding of this area. Based on bibliometrics, this study analyzes 3089 primary articles and 100,783 secondary articles published between 2003 and 2022. We comprehensively and objectively describe the development status of online reviews, show the evolutionary process of the knowledge structure of online reviews, and suggest research directions based on the analysis results. This article validates and expands previous literature reviews, helps scholars understand relevant knowledge about online reviews, and contributes to the development of online reviews.

Compared with traditional e-commerce, the advanced technology of live streaming e-commerce provides more dynamic information cues to enable viewers to make better decisions. Drawing on the information foraging theory (IFT) and elaboration likelihood model (ELM), we construct a synthetic model by considering how live streaming information cues influence viewers’ decision making via two distinct routes (central and peripheral). Using the technology of web crawling and text mining, Douyin’s live streaming data were collected, transformed, and then analyzed by fixed-effect regression. The results indicated that product interpretation duration, popularity cue, and herding information are significantly associated with sales performance in live streaming e-commerce. This study enriches our knowledge about live streaming e-commerce, extends the application of IFT and ELM in the individuals’ information foraging and processing by using objective data in the live streaming e-commerce context, and offers practical suggestions to live streaming e-commerce practitioners.

Short-form video has attracted users’ attention and been widely adopted for entertainment. Recently, short-form video has also been used for advertising. However, how short-form video for advertisement influences consumer engagement behavior remains unclear. This study aims to explore key features of short-form video advertisements that influence consumer engagement behavior. Through analyzing data obtained from social media platform TikTok, we discovered that four key features of short-form video—performance expectancy, entertainment, tie strength, and sales approach—are significantly related to consumer engagement behavior. In addition, the results showed that product type moderated the relationship of these effects on consumer engagement behavior. This study is one of the first to investigate the influence of short-form video advertisement features on consumer engagement behavior; thus, it contributes to the social media advertisement literature. It extends consumer engagement behavior research by applying a combination of uses and gratifications theory and signal theory. It also highlights the significance of product type in advertising literature. The use of big data and text analysis contributes from a methodological perspective to social media research. This study also provides practical and managerial implications for sellers and marketers on how to attract consumers to engage in videos and how to make data-driven decisions.

With the rapid development of information technology, microblog sentiment analysis (MSA) has become a popular research topic extensively examined in the literature. Microblogging messages are usually short, unstructured, contain less information, creating a significant challenge for the application of traditional content-based methods. In this study, the authors propose a novel method, MSA-USSR, in which user similarity information and interaction-based social relations information are combined to build sentiment relationships between microblogging data. They make use of these microblog–microblog sentiment relations to train the sentiment polarity classification classifier. Two Sina-Weibo datasets were utilized to verify the proposed model. The experimental results show that the proposed method has a better sentiment classification accuracy and F1-score than the content-based support vector machine (SVM) method and the state-of-the-art supervised model known as SANT.

[The full text is available on request] Considering the ubiquitous use of AI in digital business today, the significant negative or detrimental consequences of AI to individuals, organizations and society remain to be examined and are worthy of further research attention. The purpose of this mini-track is to report on the state-of-the-art research and practice in an important research area that deals with the dark sides of AI. Three papers are published in this mini-track, which all went through a rigorous review by at least two experts prior to acceptance for publications .

Despite the popularity of online health services (OHSs) among patients in recent years, academic research on this phenomenon is limited. Drawing on the valence framework, the authors proposed a model to explore both the most important facilitators of OHS use intention from the perceived value perspective and inhibitors of OHS use intention from the perceived risk perspective. Data were collected from 407 OHS users through an online survey. Results showed that the inhibitors of OHS use intention include privacy risk and social risk, while facilitators include social support value, convenience value, and utilitarian value. These findings enrich the OHS literature by revealing both the inhibitors and facilitators of OHS use intention. This study also provides practical implications for platforms offering OHS in relation to effectively attracting users.