Drawing on the theory of planned behaviour and the risk-taking theory, the objective of this research is to investigate how attitude toward algorithms, attitude toward humans, and willingness to take risks affect user intention to follow in the situation where recommendations from algorithms and human experts contradict. Set in the context of investment decision-making, a 2 (attitude toward algorithms: algorithm aversion vs. algorithm appreciation) x 2 (attitude toward human experts: unfavourable vs. favourable) x 2 (willingness to take risks: low vs. high) quasi-experiment was conducted online (N = 804) where contradictory recommendations were presented from algorithms and human sources. Favourable attitudes toward algorithms and human experts promoted the intention to follow algorithm-generated and human-generated recommendations, respectively. A high willingness to take risks increased the intention to follow regardless of the source of the recommendations. Moreover, willingness to take risks moderated the relationship between attitude toward algorithms and the intention to follow the algorithm-generated recommendation as well as that between attitude toward humans and the intention to follow the human-generated recommendation. While the literature has shed light on how individuals evaluate recommendations from algorithms and humans separately, this is one of the earliest efforts to study the situation where algorithms contradict humans.

Clinical decision-making in the context of asynchronous ‘store-and-forward’ telemedicine can be susceptible to the cognitive shortcut of anchoring bias. This paper aims to (1) examine the effect of cognitive style, cognitive ability, and information breadth on anchoring bias in telemedicine, (2) validate the effectiveness of a composite debiasing strategy, (3) investigate how the extent of debiasing is affected by cognitive style, cognitive ability, and information breadth. A pre-test–post-test experiment was conducted among 72 medical students with a composite debiasing strategy as an intervention. Results indicated that information breadth increased individuals’ susceptibility to anchoring bias. The composite debiasing strategy was successful in reducing anchoring bias. The debiasing effect was particularly pronounced among individuals with high cognitive ability. Furthermore, cognitive style interacted with cognitive ability to affect the reduction in anchoring bias. The debiasing worked best for high cognitive ability and intuitive cognitive style. The paper draws on the literature on cognitive psychology and clinical decision-making to contribute as one of the earliest efforts to study anchoring bias in telemedicine.

This paper explores the dynamics of justification in the wake of a rumor outbreak on social media. Specifically, it examines the extent to which the five types of justification—descriptive argumentation, presumptive argumentation, evidentialism, truth skepticism, and epistemological skepticism—manifested in different voices including pro-rumor, anti-rumor, and doubts before and after fact-checking. Content analysis was employed on 1,911 tweets related to a rumor outbreak. Non-parametric cross-tabulation was used to uncover nuances in information sharing before and after fact-checking. Augmenting the literature which suggests the online community's susceptibility to hoaxes, the paper offers a silver lining: users are responsible enough to correct rumors during the later phase of a rumor lifecycle. This sense of public-spiritedness can be harnessed by knowledge management practitioners and public relations professionals for crowdsourced rumor refutation.

With the emergence of opinion spam, scholars in recent years have been investigating how to distinguish between authentic and fake online reviews. In this research area however, constructing ground truth has been a tricky problem. When labeled datasets of authentic and fake reviews are unavailable, it becomes impossible to systematically investigate differences between the two. In light of this problem, the goal of this paper is three-fold: (1) To review existing approaches of developing ground truth, (2) To present an improved methodological template to construct ground truth, and (3) To conduct a quality-check of the newly constructed ground truth. The existing approaches are dissected to identify several peculiarities. The new approach invests in mitigating pitfalls in the current approaches. In the newly constructed ground truth, authentic reviews were found to be not easily distinguishable from fake reviews. Finally, new research directions are identified with the hope that scholars would be able to stay ahead in their relentless race against spammers.

This article uses linguistic analysis to help users discern the authenticity of online reviews. Two related studies were conducted using hotel reviews as the test case for investigation. The first study analyzed 1,800 authentic and fictitious reviews based on the linguistic cues of comprehensibility, specificity, exaggeration, and negligence. The analysis involved classification algorithms followed by feature selection and statistical tests. A filtered set of variables that helped discern review authenticity was identified. The second study incorporated these variables to develop a guideline that aimed to inform humans how to distinguish between authentic and fictitious reviews. The guideline was used as an intervention in an experimental setup that involved 240 participants. The intervention improved human ability to identify fictitious reviews amid authentic ones.

This article examines review helpfulness as a function of reviewer reputation, review rating, and review depth. In drawing data from the popular review platform A mazon, results indicate that review helpfulness is positively related to reviewer profile and review depth but is negatively related to review rating. Users seem to have a proclivity for reviews contributed by reviewers with a positive track record. They also appreciate reviews with lambasting comments and those with adequate depth. By highlighting its implications for theory and practice, the article concludes with limitations and areas for further research.

The authors investigate the interplay between answer quality and answer speed across question types in community question‐answering sites (CQAs). The research questions addressed are the following: (a) How do answer quality and answer speed vary across question types? (b) How do the relationships between answer quality and answer speed vary across question types? (c) How do the best quality answers and the fastest answers differ in terms of answer quality and answer speed across question types? (d) How do trends in answer quality vary over time across question types? From the posting of 3,000 questions in six CQAs, 5,356 answers were harvested and analyzed. There was a significant difference in answer quality and answer speed across question types, and there were generally no significant relationships between answer quality and answer speed. The best quality answers had better overall answer quality than the fastest answers but generally took longer to arrive. In addition, although the trend in answer quality had been mostly random across all question types, the quality of answers appeared to improve gradually when given time. By highlighting the subtle nuances in answer quality and answer speed across question types, this study is an attempt to explore a territory of CQA research that has hitherto been relatively uncharted.