Purpose: The latest mobile technology may shape consumers' motivations by allowing them to order a variety of foods using smartphone apps. Following the stimulus–organism–response (SOR) framework and using a mixed methods approach, this study investigates the impacts of different components of mobile dining on customers' perceived value, which leads to actual purchase intentions. Furthermore, this study examines the moderating effect of the restaurant type.Design/methodology/approach: Data were collected via an online questionnaire survey from 351 individuals in the city of Jakarta (Indonesia) who actually used mobile apps to order food online. Data analysis was carried out using structural equation modeling.Findings: The findings reveal that source credibility, review valence, the navigation system, food quality and service quality significantly impact customers' perceived value. Customers' perceived value, in turn, positively affects their purchase intentions. The findings also reveal that the impacts of review valence, the navigation system, food quality and service quality on customers' perceived value depend on the different levels of restaurants.Originality/value: This study is among the first in the mobile commerce research that studies the impacts of mobile electronic word-of-mouth (eWOM), system quality and overall restaurant image on dining choices by considering actual mobile shoppers. Second, this study extends the SOR model to examine the impact of the mobile environment-based characteristics on the perceived value that leads to purchase intentions. Third, the current study examines whether the relationships that are discussed early on differ based on the restaurant type. The findings of this study could help practitioners achieve a deeper understanding of diners' behaviors due to the perceived benefits of mobile dining.

Purpose: The purpose of this paper is to develop a model to examine how different technological and cognitive cues related to mobile food ordering applications (MFOAs) impact diners' intentions to use MFOAs continuously. The moderating role of national household demographics was also assessed in the online-to-offline (O2O) food delivery services (FDS) context.Design/methodology/approach: Drawing insights from the uses and gratification (U&G) theory, an online sample survey of 968 valid respondents who had ordered or purchased food through delivery apps during the COVID-19 outbreak in China was used for the analysis. The proposed model was empirically tested using structural equation modeling.Findings: The results revealed that cues in MFOAs (i.e. ease of use, convenience, price saving orientation, the listing of various food choices, exploring restaurant patterns, and compatibility) directly influenced diners' e-satisfaction and that intention to use continuously is triggered by e-satisfaction during the COVID-19 crisis. Moreover, this study found that collectivist household diners emphasized ease of use, convenience, and compatibility. Comparatively, individualistic household diners placed more importance upon price saving orientation and listing of various food choices during the pandemic.Originality/value: The authors offer a new insight into customers' dining choices by extending the scope of O2O services in the food industry. The findings contribute to understanding diners' purchase decision-making processes regarding MFOAs' O2O-FDS during the COVID-19 crisis. The multi-group comparison via national household demographics also provides a new perspective regarding different dining preferences toward O2O-FDS.

Biomedical-named entity recognition (bNER) is critical in biomedical informatics. It identifies biomedical entities with special meanings, such as people, places, and organizations, as predefined semantic types in electronic health records (EHR). bNER is essential for discovering novel knowledge using computational methods and Information Technology. Early bNER systems were configured manually to include domain-specific features and rules. However, these systems were limited in handling the complexity of the biomedical text. Recent advances in deep learning (DL) have led to the development of more powerful bNER systems. DL-based bNER systems can learn the patterns of biomedical text automatically, making them more robust and efficient than traditional rule-based systems. This paper reviews the healthcare domain of bNER, using DL techniques and artificial intelligence in clinical records, for mining treatment prediction. bNER-based tools are categorized systematically and represent the distribution of input, context, and tag (encoder/decoder). Furthermore, to create a labeled dataset for our machine learning sentiment analyzer to analyze the sentiment of a set of tweets, we used a manual coding approach and the multi-task learning method to bias the training signals with domain knowledge inductively. To conclude, we discuss the challenges facing bNER systems and future directions in the healthcare field.