AI-enabled talent training for the cross-cultural news communication talent

Abstract

In the context of economic globalization, the demand for cross-cultural news communication talents is increasing. This study aims to analyze and optimize the training strategy of composite international talents (CITs) in news communication in the context of artificial intelligence (AI) to comprehensively improve the quality of talents. To organize the relevant research on AI and cross-cultural second language acquisition, a literature review is conducted. The advantages and disadvantages of the present training mechanism were then systematically summarized by evaluating the current situation of CIT training in news communication. Subsequently, the radial basis function neural network (RBFNN) model was applied to ameliorate the CIT training strategy for news dissemination. The analysis of the CIT talent training strategy for news communication demonstrates that the number of talents predicted by the model remained optimal through the model's iteration over six data lists. The RBFNN model proposed herein also outperforms other models with two experimental data sets. The model registers a recognition accuracy of 70 % and precision of 80 % at the 100th iteration. The recognition accuracy and precision improves significantly to 82.3 % and 83.6 %, respectively, after the 600th iteration. This study can further enhance the effects of CIT training in news communication and can serve as a reference for the digital intelligence of the news communication industry.