Research on performance evaluation of scientific research staff based on entropy weight - TOPSIS method

The aim of this study is to explore in depth the complexity of performance evaluation for university researchers and the challenges they face, especially in the current context of scientific research system reform. To ensure the fairness, rationality, and effectiveness of performance evaluation has become a common concern for universities and researchers, multiple factors need to be considered, such as total performance allocation, type and quantity of achievements, individual score, subject differences, length of service and position level, talent cultivation, new project initiation, and award level. The different combinations and weight settings of these factors will have a significant impact on the performance evaluation results. To address these issues, a mathematical model based on entropy weight method and TOPSIS comprehensive evaluation method is proposed. This model quantitatively analyzes the multidimensional indicators of researchers and comprehensively considers various factors mentioned above. Among them, the entropy weight method is used to determine the weights of each indicator, while the TOPSIS rule is used to calculate the performance scores of each researcher. The advantage of this model lies in its objectivity and impartiality, which can avoid the interference of human factors on the evaluation results. In order to verify the feasibility and effectiveness of the model, empirical research was conducted. Firstly, relevant data on research personnel from a certain university was collected, including paper publications, project applications, award status, etc. Then, the model was used to process these data and obtain the performance scores of each researcher. Finally, by comparing the results obtained from the model with the actual situation, it was found that the model has high accuracy and reliability. In addition to model validation, sensitivity analysis was also conducted on the model. By changing the parameter values in the model, the changes in the output results of the model were observed. The results indicate that the model has strong adaptability to parameter changes and can maintain stable performance in different situations. In terms of team selection and individual performance allocation, a weighted average algorithm was established to calculate with appropriate weights and obtain reasonable and fair results. The advantage of this algorithm lies in its simplicity and strong operability, which can be easily applied in practical work.