The manual-based classification method of property complaint documents has been unable to meet the needs of the society,and the existing automatic classification methods related to complaints have insuffi-cient performance in the classification of property complaints.Therefore,this study proposes a property serv-ice complaint classification method JAE-BERT4Com based on MacBERT and joint attention enhancement network.JAE-BERT4Com uses a sample enhancement strategy based on the combination of synonym re-placement and synthetic minority oversampling technology to solve the problem of class imbalance.And a multi-attention joint enhancement network based on MacBERT's hierarchical attention,Transformers'multi-head attention and keyword attention is designed to perform text feature learning and classification.The ex-perimental results show that JAE-BERT4Com can obtain higher accuracy,F1 score and recall rate than the existing models,and has better performance than the existing advanced models.
维普
万方数据