Identification of Local Adverse Drug Reactions in Xinjiang Based on Attention Mechanism and BiLSTM-CNN Hybrid Network

Abstract

Adverse drug reactions (ADR) include adverse reactions which are caused by drug quality problems or improper medication. In order to solve the issues which are triggered by the lack of research on local adverse drug reactions in Xinjiang and the shortcomings of traditional models in dealing with irregular sentences, this paper proposes a method for adverse drug identification in Xinjiang. The method is combined with BiLSTM-CNN hybrid network which is based on attention mechanism. The method analyzes deeply on the network text context feature and the attention pooling mechanism. These measures can reduce the information loss while acquiring the local convolution feature. The integration of attention mechanism, the addition of weight information make it becomes more sensitive to capture the importance of features which brings improvement of the ability to express features. Finally, the experiment was carried out in the Xinjiang Adverse Drug Reaction Data Set. The accuracy rate of this model in Xinjiang local drug adverse reaction identification was 87.27%, the recall rate was 88.87%, and the F value was 87.65%. Compared with the common convolutional neural network and BiLSTM, it achieves better classification results, and has obvious advantages for irregular grammar and long sentence recognition. Experiments showed that the ATT-BiLSTM-CNN model can rapidly improve the recognition performance of local adverse drug reactions in Xinjiang.

Natural Language Description Generation Method of Intelligent Image Internet of Things Based on Attention Mechanism

“…By conducting evaluations, we can dig out some service and catering quality based on these evaluations, so as to make relevant recommendations to other users; hot events that appear in the news can be analyzed by sentiment analysis of users' hot comments, so that the management department can accurately grasp the guidance of public opinion. Avoid the intensification and occurrence of contradictions [24,25].…”