【摘要】 针对目前情感分析中的循环神经网络模型缺乏对情感词的关注的问题,提出一种基于循环神经网络的情感词注意力模型,通过引入注意力机制,在情感分类时着重考虑文本中的情感词的影响.在NLPCC 2014情感分析数据集及IMDB影评数据集上进行试验,结果表明:该模型能够提高情感分析的效果.更多还原

【Abstract】 Aim at the overlook of emotional words in the present recurrent neural network model used for sentiment analysis,we propose an emotional word attention model based on recurrent neural network.By introducing the attention mechanism,the model can pay more attention to the emotional words in the text sentiment classification.Experiments are conducted on the NLPCC 2014 sentiment analysis dataset and IMDB movie review dataset,the results show that our model can improve the sentiment analysis effect.更多还原