At present, association rules have been widely used in prediction, personalized recommendation, risk analysis and other fields. However, it has been pointed out that the traditional framework to evaluate association rules, based on Support and Confidence as measures of importance and accuracy, has several drawbacks. Some papers presented several new evaluation methods; the most typical methods are Lift, Improvement, Validity, Conviction, Chi-square analysis, etc. Here, this paper first analyzes the advantages and disadvantages of common measurement indicators of association rules and then puts forward four new measure indicators (i.e., Bi-support, Bi-lift, Bi-improvement, and Bi-confidence) based on the analysis. At last, this paper proposes a novel Bi-directional interestingness measure framework to improve the traditional one. In conclusion, the bi-directional interestingness measure framework (Bi-support and Bi-confidence framework) is superior to the traditional ones in the aspects of the objective criterion, comprehensive definition, and practical application.

Introduction: Understanding the relationship between tourists’ consumption behavior and their willingness to substitute consumption in unusual environments can promote tourists’ sustainable consumption behavior. This study explores the internal relationship between tourists’ willingness to engage in sustainable consumption behavior and the substitution of tourism consumption willingness in an unusual environment and the related factors. Methods: Through qualitative and quantitative mixed research, this study first invited 32 interviewees related to the tourism industry to conduct in-depth and focus group interviews and extracted a research model based on the push-pull theoretical model (PPM) through three rounds of coding of grounded theory. Then, through questionnaire design, pre-release, and formal release, 268 valid questionnaires were collected using a convenience sampling method, and the hypothesis and its mediating effect were verified using a structural equation model. Results: Further quantitative analysis and verification showed that being in an unusual environment had a positive effect on tourists’ perception of crisis awareness, safety risk, and willingness to engage in sustainable consumption behavior. However, the results did not support the unusual environment positively affecting the substitution of tourism consumption willingness, the psychological transformation cost, and the fixed consumption habit negatively affecting the substitution of tourism consumption willingness. In this study, two mediating variables were used to verify the indirect effect of being in an unusual environment and the substitution of tourism consumption willingness. The results showed that the mediating effect was significant. Conclusion: This study explored an action mechanism model aimed at guiding tourists’ willingness for sustainable consumption, based on the environment and consumption behavior, and provided relevant countermeasures for the government and business decision-makers, enterprises, and investors in the tourism sector.

The advent of mobile scenario-based consumption popularizes and gradually maturates the application of point of interest (POI) recommendation services based on geographical location. However, the insufficient fusion of heterogeneous data in the current POI recommendation services leads to poor recommendation quality. In this paper, we propose a novel hybrid POI recommendation model (NHRM) based on user characteristics and spatial-temporal factors to enhance the recommendation effect. The proposed model contains three sub-models. The first model considers user preferences, forgetting characteristics, user influence, and trajectories. The second model studies the impact of the correlation between the locations of POIs and calculates the check-in probability of POI with the two-dimensional kernel density estimation method. The third model analyzes the influence of category of POI. Consequently, the above results were combined and top-K POIs were recommended to target users. The experimental results on Yelp and Meituan data sets showed that the recommendation performance of our method is superior to some other methods, and the problems of cold-start and data sparsity are alleviated to a certain extent.

To achieve the goal of carbon neutrality, many countries have established regional carbon emission trading markets and tried to build a low-carbon economic system. At present, the implementation of carbon emission trading and low-carbon economic systems faces many challenges such as manipulation, corruption, opacity, lack of trust, and lack of data tracking means. The application of blockchain technology can perfectly solve the above problems. However, the data recorded on a blockchain are often multi-type and heterogeneous, and users at different levels such as regulators, enterprises, and consumers have different requirements for data types and granularity. This requires a quick and trustworthy method for monitoring the carbon footprint of enterprises and products. In this paper, the carbon footprint traceability of enterprises and products is taken as an application scenario, and the distributed traceability concept of “traceability off the chain and verification on the chain” is adopted. By reconstructing the pointer of the file structure of the distributed storage, an interactive traceability structure supporting type filtering is constructed, which enables fast retrieval and locating of carbon emission data in the mixed data on the chain. The experimental results show that using the interactive traceability structure that supports type filtering for traceability not only releases the computing power of full nodes but also greatly improves the traceability efficiency of the long-span transaction chain. The proposed carbon footprint traceability system can rapidly trace and track data on an enterprise’s and a product’s carbon footprint, as well as meet the needs of users at all levels for traceability. It also offers more advantages when handling large amounts of data requests.

Social conflicts occur frequently during the social transition period and the polarization of public opinion happens occasionally. By introducing the social preference theory, the target of this paper is to reveal the micro-interaction mechanism of public opinion polarization. Firstly, we divide the social preferences of Internet users (network nodes) into three categories: egoistic, altruistic, and fair preferences, and adopt the revenue function to define the benefits obtained by individuals with different preferences among their interaction process so as to analyze their decision-making behaviors driven by the revenue. Secondly, the revenue function is used to judge the exit rules of nodes in a network, and then a dynamic network of spreading public opinion with the node (individual) exit mechanism is built based on a BA scale-free network. Subsequently, the influences of different social preferences, as well as individual revenue on the effect of public opinion polarization, are analyzed through simulation experiments. The simulation results show that (1) Different social preferences demonstrate different influences on the evolution of public opinions, (2) Individuals tend to interact with ones with different preferences, (3) The network with a single preference or a high aggregation is more likely to form public opinion polarization. Finally, the practicability and effectiveness of the proposed model are verified by a real case.