Sentiment analysis becomes one of the most active research hotspots in the field of natural language processing tasks in recent years. However, the inability to fully and effectively use emotional information is a problem in present deep learning models. A single Chinese character has different meanings in different words, and the character embeddings are combined with the word embeddings to extract more precise meaning information. In this paper, a single Chinese character and word are used as input units to train. Based on BLSTM, the attention mechanism based on vocabulary semantics in food field is introduced to realize distance-related sequence semantic feature extraction. CNN is used to realize semantic sentiment classification of sequence semantic features. Therefore, a model based on multi-neural network for sentiment information extraction and analysis is proposed. Experiments show that the model has excellent characteristics in sentiment analysis and obtains high accuracy and F value.

情感分析已成为近年来自然语言处理任务领域最活跃的研究热点之一。但是，在目前的深度学习模型中，无法完全有效地使用情感信息是一个问题。单个汉字在不同的单词中具有不同的含义，并且将字符嵌入与单词嵌入相结合以提取更精确的含义信息。本文将单个汉字和单词作为训练的输入单位。引入基于BLSTM的食品领域词汇语义注意机制，实现距离相关序列语义特征提取。CNN用于实现序列语义特征的语义情感分类。因此，提出了一种基于多神经网络的情感信息提取与分析模型。实验表明，该模型在情感分析中具有优良的特性，具有较高的准确性和F值。