Association rules mining is an important topic in the domain of data mining and knowledge discovering. Some papers have presented several interestingness measure methods; the most typical areSupport,Confidence,Lift,Improve, and so forth. But their limitations are obvious, like no objective criterion, lack of statistical base, disability of defining negative relationship, and so forth. This paper proposes three new methods,Bi-lift, Bi-improve, andBi-confidence, forLift, Improve, and Confidence, respectively. Then, on the basis of utility function and the executing cost of rules, we propose interestingness function based on profit (IFBP) considering subjective preferences and characteristics of specific application object. Finally, a novel measure framework is proposed to improve the traditional one through experimental analysis. In conclusion, the new methods and measure framework are prior to the traditional ones in the aspects of objective criterion, comprehensive definition, and practical application.
In the era of mobile internet, information dissemination has made a new leap in speed and in breadth. With the outbreak of the coronavirus disease 2019 (COVID-19), the COVID-19 rumor diffusion that is not limited by time and by space often becomes extremely complex and fickle. It is also normal that a piece of unsubstantiated news about COVID-19 could develop to many versions. We focus on the stagnant role and information variants in the process of rumor diffusion about COVID-19, and through the study of variability and silence in the dissemination, which combines the effects of stagnation phenomenon and information variation on the whole communication system in the circulation of rumors about COVID-19, based on the classic rumor SIR (Susceptible Infected Recovered) model, we introduce a new concept of “variation” and “oyster”. The stability of the new model is analyzed by the mean field equation, and the threshold of COVID-19 rumor propagation is obtained later. According to the results of the simulation experiment, whether in the small world network or in the scale-free network, the increase of the immure and the silent probability of the variation can effectively reduce the speed of rumor diffusion about COVID-19 and is conducive to the dissemination of the truth in the whole population. Studies have also shown that increasing the silence rate of variation can reduce COVID-19 rumor transmission more quickly than the immunization rate. The interesting discovery is that at the same time, a higher rumor infection rate can bring more rumors about COVID-19 but does not always maintain a high number of the variation which could reduce variant tendency of rumors. The more information diffuses in the social group, the more consistent the version and content of the information will be, which proves that the more adequate each individual information is, the slower and less likely rumors about COVID-19 spread. This consequence tells us that the government needs to guide the public to the truth. Announcing the true information publicly could instantly contain the COVID-19 rumor diffusion well rather than making them hidden or voiceless.
High-dimensional and unbalanced data anomaly detection is common. Effective anomaly detection is essential for problem or disaster early warning and maintaining system reliability. A significant research issue related to the data analysis of the sensor is the detection of anomalies. The anomaly detection is essentially an unbalanced sequence binary classification. The data of this type contains characteristics of large scale, high complex computation, unbalanced data distribution, and sequence relationship among data. This paper uses long short-term memory networks (LSTMs) combined with historical sequence data; also, it integrates the synthetic minority oversampling technique (SMOTE) algorithm and K-nearest neighbors (kNN), and it designs and constructs an anomaly detection network model based on kNN-SMOTE-LSTM in accordance with the data characteristic of being unbalanced. This model can continuously filter out and securely generate samples to improve the performance of the model through kNN discriminant classifier and avoid the blindness and limitations of the SMOTE algorithm in generating new samples. The experiments demonstrated that the structured kNN-SMOTE-LSTM model can significantly improve the performance of the unbalanced sequence binary classification.
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.
The realization of China’s “double carbon” goal is of great significance to the world environment and China’s economy and society. Through the establishment of the “government–enterprise–public” evolutionary game model, this paper explores the interaction between government policy guidance, low-carbon technology R&D behavior of enterprises, and public purchase of carbon label products, as well as the micro-driving path, aiming to provide suggestions for the implementation of the “double carbon” policy and carbon label system in China. The results show that the choice of government, enterprises, and public strategies is closely related to their own costs and benefits. Public sentiment can effectively urge the government to actively fulfill its responsibilities. Effective government policy guidance plays a key role in low-carbon technology R&D behavior of enterprises. There is an interaction between low-carbon technology R&D behavior of enterprises and public purchase of carbon label products.
To solve the problems exposed by the application of blockchain technology under complex scenarios, such as fraudulent use of data, hard to store huge amounts of data, and low traceability efficiency under an ultra-huge number of traceability requests, this paper constructs an image-based interactive traceability structure by using images as an enhancement. By adding pointers to raw image files, a specific file structure is formed for traceability, and the traceability process is separated from the verification process, therefore realizing the distributed traceability of “traceability off the chain and verification on the chain”. The experimental results show that, compared with the traditional blockchain traceability mode, the interactive traceability structure can reduce the data retrieval pressure and greatly improve the traceability efficiency of a specific transaction chain. With the growth of the span of the transaction chain, the traceability efficiency advantage of the interactive traceability structure becomes more obvious.
Purpose In social marketing, sharing reward program (SRP) is a common way to improve the marketing effect. However, few studies have explored the impact of consumers’ self-presentation and face consciousness on enterprise SRP. This study aims to explore the influence of these two factors on the optimal SRP. Methods A Stackelberg game between enterprises, sharers and potential consumers is developed to study the impact of sharers’ face consciousness on enterprise’s SRP. In order to discuss the impact of face consciousness on SRP in detail, we introduced status identity of commodity information, sharer’s self-presentation preference and commodity price as exogenous variables in the research. Results The results have shown that when the face consciousness of sharers is high, enterprises are advised to adopt the strategy of low reward and low requirement. But when the face consciousness is low, it would be better for them adopt the strategy of high reward and high requirement. In addition, with the low face consciousness, the optimal SRP is also affected by the relationship between the price of goods and the number of WeChat friends of sharers. Conclusion The results suggest that when enterprises make incentive policies, considering consumers’ self-presentation preference and face consciousness, the profit level can be effectively improved.
Objective: To explore the law of opinion dissemination and individual opinion evolution at the micro level, this paper analyzes the influence of variation and oyster on communication from the perspective of network structure.Methods: In this paper, we introduce the concepts of “variation” and “oyster”, build a multi-layer coupled network environment combined with the ISOVR model, and conduct simulation experiments of network information dissemination based on the bounded trust model.Results: The experimental results reveal that the extent and scope of variation’s spread in the network are more dependent on the trust of nodes themselves, and decreasing the trust of nodes significantly reduces the rate and peak value of variation. Changing the silence coefficient of variation does not effectively change the direction of rumor propagation, which indicates that rumor has a strong propagation ability after mutation.Conclusion: The insights of this paper on the dissemination of public opinions include: 1) pay attention to people with high trust levels, such as opinion leaders; 2) clarify the misinformation in time to prevent further spread of rumors.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.