A content-based recommendation algorithm for agricultural science popularization
Chao Guo, Yanzhao Ren, Jingdun Jia, Sha Tao, Xinliang Liu, Wanlin Gao, Limin Yu · 2021
With the development of agricultural science, agricultural science knowledge overload widespread. In order to allow agricultural workers to discover new agricultural science and technology knowledge that suits their preferences, and to enable the agricultural science popularization service system to locate agricultural knowledge to appropriate users. The recommended scheme applied to agricultural science popularization needs to be solved urgently. In this paper, we propose a content-based recommendation algorithm for agricultural science popularization based on convolutional neural network (CNN). Considering the structure and professional fields of agricultural science information, a language model based on labeled latent Dirichlet allocation and a latent factor model with inherent features are constructed in the CNN model. The experimental results on the public database show that compared with the classical methods, it has a better improvement in recommendation evaluation, and it performs well in solving the problem of cold start and data sparsity.