Application research of evolutionary generative model for financial information sentiment retrieval based on interactive genetic algorithm

Financial texts contain rich emotional information, which is of great significance for capturing emotional fluctuations in financial markets, assisting investors in decision-making and implementing financial risk management. However, sentiment information of financial texts requires a lot of domain expert knowledge, and manual retrieval is expensive. In this paper, we propose the application of an evolutionary generative model for sentiment retrieval of financial information based on interactive genetic algorithms from the perspective of user implicit modeling. The uncertain preference estimation of evolutionary individuals is realized. The user preference model is adjusted according to the uncertainty evaluation, and the user preference is dynamically tracked to obtain the fitness value of the evolutionary individual for evolutionary optimization. The experimental results show that the proposed method can implicitly perceive user preferences, reduce user explicit evaluation, reduce user fatigue, and improve the search performance of the algorithm.