目录前言·························································································3第一章绪论················································································41.1研究背景及意义····································································41.2卷积神经网络概述·································································41.3本文的主要工作····································································51.4本文的组织结构····································································5第二章文本情感分析背景知识···························································72.1文本情感分析的研究现状························································72.1.1基于先验知识的分析························································82.1.2基于传统机器学习算法的分析············································92.1.3基于深度学习方法的分析··················································92.2文本情感分析的难点····························································112.3本章小结···········································································11第三章基于卷积神经网络的中文情感分析模型····································133.1文本数据的预处理·······························································133.1.1基于jieba分词工具的中文文本分词···································133.1.2基于NLPIR的分词系统的中文文本分词·····························143.1.3基于word2vec的文本向量化············································143.2卷积神经网络模型·······························································153.2.1训练数据的生成····························································153.2.2卷积神经网络的优势······················································163.2.3卷积神经网络模型的构建················································163.2.4优化算法与损失计算函数················································183.3结合词性标注信息的卷积神经网络结构····································193.4本章小结····...
VIP
