Aiming at the problem of insufficient text feature extraction in the existing short news text classification methods for identifying marketing intentions and difficulty in capturing the semantic information in the text, a short text news marketing recognition method based on the attention mechanism neural network model is proposed. The model uses convolutional neural network to extract local features, and then uses bidirectional long and short-term memory network to extract contextual semantic information, strengthens the learning of features, and introduces a double-layer attention mechanism to calculate feature weights to further obtain influential features between sentences. Finally, perform text classification at the softmax function layer. Through experiments on two standard data sets, the experimental results show that this method has better classification performance, and has a significant improvement in accuracy compared with other models.

针对现有的短新闻文本分类方法在识别营销意图时文本特征提取不足，难以捕捉文本中语义信息的问题，提出了一种基于注意力机制神经网络模型的短文本新闻营销识别方法。该模型利用卷积神经网络提取局部特征，再利用双向长短期记忆网络提取上下文语义信息，加强特征的学习，并引入双层注意力机制计算特征权重，进一步获得有影响力的句子之间的特征。最后在softmax函数层进行文本分类。通过对两个标准数据集的实验，