Artificial intelligence (AI) technology is playing an increasingly important role in achieving precision marketing. AI word‐of‐mouth system marketing focuses most on the entry point of consumers—the key information that leads consumers to buy. Based on consumer behaviour theory and information communication theory, this study constructs a research model of the influence of positive and negative online word of mouth on consumer purchase behaviour from the AI word‐of‐mouth system's four dimensions: professional degree, information quality, information quantity and information intensity. The results show that in the analysis of perceived risk, whether for positive or negative online word of mouth, consumers pay more attention to the number of information features than information quality and information intensity. In the purchase behaviour analysis, consumers are most concerned about information quality and information intensity. Perceived risk plays a mediating role in the influence of AI word of mouth on purchasing behaviour.

To solve the problems of large data sparsity and lack of negative samples in most point of interest (POI) recommendation methods, a POI recommendation method based on deep learning in location-based social networks is proposed. Firstly, a bidirectional long-short-term memory (Bi-LSTM) attention mechanism is designed to give different weights to different parts of the current sequence according to users’ long-term and short-term preferences. Then, the POI recommendation model is constructed, the sequence state data of the encoder is input into Bi-LSTM-Attention to get the attention representation of the current POI check-in sequence, and the Top- N recommendation list is generated after the decoder processing. Finally, a negative sampling method is proposed to obtain an effective negative sample set, which is used to improve the calculation of the Bayesian personalized ranking loss function. The proposed method is demonstrated experimentally on Foursquare and Gowalla datasets. The experimental results show that the proposed method has better accuracy, recall, and F1 value than other comparison methods.

No abstract

No abstract

As unexpected events such as natural disasters, the COVID-19 pandemic, and overseas containment have caused inevitable shocks to the energy industrial chain and supply chain, the current global energy crisis is intensifying, and different countries and regions have adopted different strategies according to the characteristics of their own national resource endowments in order to cope with energy security. Maintaining the security of the coal industrial chain and supply chain is a prerequisite for energy security to be effectively ensured, considering the main position of coal in China’s energy. Therefore, in the face of multiple uncertain risk factors under today’s momentous changes, this paper constructs an industrial coal chain and supply chain resilience evaluation indicator system from the perspective of resilience, based on four representational capabilities of resilience, namely preparedness, absorptive capacity, recovery capacity, and adaptability, in order to profoundly understand and enhance the resilience of the coal industrial chain and supply chain. An integrated method combining Interval Type-2 Fuzzy Prospect Theory and Technique for Order Preference by Similarity to an Ideal Solution (Interval Type-2F-PT-TOPSIS) is proposed for evaluating the resilience level of the coal industrial chain and supply chain. In the case of Shaanxi Province in China, it was found that the worst level of resilience of the coal industrial chain and supply chain in Shaanxi Province was in 2018, and the best was in 2021. Finally, based on the evaluation results, recommendations are provided to the key nodes of the industrial chain and supply chain in Shaanxi Province with a view to improving their resilience levels to cope with uncertain risks.