Purpose: This paper aims to identify key service attributes in peer-to-peer (P2P) accommodation from online reviews and formulate service improvement strategies based on the unsatisfactory service encounters mined from the reviews.Design/methodology/approach: The methodology involves topic modelling using latent Dirichlet allocation, sentiment analysis and process analysis based on process chain network (PCN).Findings: The text analytics results showed that negative P2P accommodation experiences are caused by the lack of hot water for shower, poor sleep quality and unpleasant check-in.Research limitations/implications: The PCN analysis shows that the surrogate interactions of the P2P accommodation platform with both the guest and the host impact consumer experiences. This highlights that the key to managing consumer experiences lies in the non-human resources such as information, rather than direct interactions between process entities.Practical implications: The information on the P2P accommodation platform should be in a more interactive format such as video and 360 degrees camera. Hosts should ensure a good condition of the physical products such as water heaters and beds before guests' arrival. Professional videography and handyperson services should be provided by the platform to help hosts deliver a preferred consumer experience. Flexible and strict check-in polices should also be introduced to smoothen the check-in process.Originality/value: This study is built on multi-attribute utility theory. It is also one of the first to study P2P accommodation services from an operations management perspective. It demonstrates how text analytics serves as an additional supplement for service improvement.

Although travel restrictions imposed by countries are gradually lifted, the airline industry rebounds only when customers’ confidence in air travel is restored. Airlines that generate positive customer recommendations during the pandemic can have a competitive advantage in the post-pandemic environment. This article focuses on the prediction of customer recommendations of airlines during the pandemic. The results show that airline ratings established before the pandemic have weak performance, implying that customer recommendations could be based on other factors that are unique to the pandemic. In addition, COVID-19 travel safety of airlines and sentiments hidden in customer reviews are valuable for predicting customer recommendations. The results also confirm that flight duration affects the predictive powers of airline rating established before the pandemic and COVID-19 travel safety rating of airlines. There are important implications for the airline industry. First, airline ratings established before pandemic is not valuable to predict customer recommendations during COVID-19, underpinning the importance of including COVID-19 travel safety measures as part of the airline evaluation criteria in the future. Besides, COVID-19 travel safety is more relevant to customer recommendations in the long-haul markets. When selecting airlines for evaluation, airline rating organizations can give priorities to airlines that offer long-haul flights.

The COVID-19 pandemic has hastened the adoption of autonomous vehicles (AVs) to minimise human-to-human contact. Yet, prior investigations suggest that AVs are accident-prone when they behave differently from humans. It is necessary to design an autonomous vehicle system (AVS) that can take human behaviour into account. This study capitalises on the wealth of data from traffic accidents caused by humans and discovers association rules to improve AVSs. Findings show that fatal accidents likely co-occur with “right near”, “head on” or “lane side swipe” scenarios. They provide important implications for designing traffic scenarios that are critical for training an AVS.

Foodborne illness outbreaks originating in food service establishments (FSEs) are a serious public health concern. There are multiple ways that FSEs can contribute to the propagation of foodborne illnesses. However, not all these risks can be detected by health authorities during official inspections for two reasons. First, health authorities have limited resources, meaning not every FSE can be inspected as often and expediently as necessary. Second, because the food safety and hygiene standards of FSEs are dynamic, the inspection results might represent a snapshot that fails to resemble the current FSE situation. Consequently, it would be helpful to have an early warning system that can allow health authorities to predict the risk levels of FSEs and proactively intervene by demanding that high-risk FSEs take appropriate countermeasures. Considering that customers who feel sick after visiting an FSE may not report their experience to health authorities but instead disclose this information by posting online reviews on social media platforms, this study leverages social media data to predict food safety violations by FSEs. The empirical data for this study derive from two sources: the FSE inspection results from the Department of Health and Mental Hygiene in New York City, which labeled each FSE according to whether it violated food safety regulations, and textual reviews posted by FSE customers on Yelp. Machine learning algorithms were employed to extract textual features from the reviews and construct predictive models. Our results demonstrate that customer reviews posted on social media platforms are valuable for predicting FSE food safety violations. Health authorities can leverage social media data to construct predictive models and deploy them to optimize resource allocation and prioritize interventions to prevent foodborne illness outbreaks originating in FSEs, improving public health. FSE managers can also deploy the models to improve their hygiene standards in response to alerts raised. By taking appropriate countermeasures earlier, they can reduce their risk of financial loss due to negative inspection results.