Notice of Retraction: Graph Neural Network Recommendation Model Based on Long- and Short-Term Interests

The recommendation system [1] can quickly find the information that users are interested in from the complex information and recommend it to the user, and it has been widely used in web-based services. However, the current mainstream recommendation models [16] all have the problem of sparse data [2] and ignoring the long-term and short-term interests of users. In response to these problems, we propose a graph neural network recommendation model (LSGNR) based on long-term and short-term user interest modeling. In the experiment, we used the public data set to verify and analyze the algorithm of LSGNR model. We performed an experimental comparison with the current mainstream five recommendation models. Experimental results show that the performance of the proposed algorithm is generally better than the current mainstream recommendation methods [17], and it is improved by more than 10
^%
compared with other models under the two evaluation indicators.