Purpose-The purpose of this paper is to develop a probabilistic uncertain linguistic(PUL)TODIM method based on the generalized Choquet integral,with respect to the interdependencies between criteria,for the selection of the best alternate in the context of multiple criteria group decision-making(MCGDM).Design/methodology/approach-Owing to decision makers(DMs)do not always show completely rational and may have the preference of bounded rational behavior,this may affect the result of the MCGDM.At the same time,criteria interaction is a focused issue in MCGDM.Hence,a novel TODIM method based on the generalized Choquet integral selects the best alternate using PUL evaluation,where the generalized Choquet integral is used to calculate the weight of criterion.The generalized PUL distance measure between two probabilistic uncertain linguistic elements(PULEs)is calculated and the perceived dominance degree matrices for each alternate relative to other alternates are obtained.Furthermore,the comprehensive perceived dominance degree of each alternate can be calculated to get the ranking.Findings-Potential application of the PUL-TODIM method is demonstrated through an evaluation example with sensitivity and comparative analysis.Originality/value-As per author’s concern,there are no TODIM methods with probabilistic uncertain linguistic sets(PULTSs)to solve MCGDM problems under uncertainty.Compared with the result of existing methods,the final judgment value of alternates using the extended TODIM methodology is highly corroborated,which proves its potential in solving MCGDM problems under qualitative and quantitative environments.
Purpose-In the new era of highly developed Internet information,the prediction of the development trend of network public opinion has a very important reference significance for monitoring and control of public opinion by relevant government departments.Design/methodology/approach-Aiming at the complex and nonlinear characteristics of the network public opinion,considering the accuracy and stability of the applicable model,a network public opinion prediction model based on the bald eagle algorithm optimized radial basis function neural network(BES-RBF)is proposed.Empirical research is conducted with Baidu indexes such as“COVID-19”,“Winter Olympic Games”,“The 100th Anniversary of the Founding of the Party”and“Aerospace”as samples of network public opinion.Findings-The experimental results show that the model proposed in this paper can better describe the development trend of different network public opinion information,has good stability in predictive performance and can provide a good decision-making reference for government public opinion control departments.Originality/value-A method for optimizing the central value,weight,width and other parameters of the radial basis function neural network with the bald eagle algorithm is given,and it is applied to network public opinion trend prediction.The example verifies that the prediction algorithm has higher accuracy and better stability.
