东篱科研大数据发现系统（DRDS）

位置：成果数据库 > 期刊 > 期刊详情页

基于S VM与RNN的文本情感关键句判定与抽取

ISSN号：1671-9352
期刊名称：《山东大学学报：理学版》
时间：0
分类：TP391[自动化与计算机技术—计算机应用技术;自动化与计算机技术—计算机科学与技术]
作者机构：[1]郑州大学信息工程学院,河南郑州450001
相关基金：国家自然科学基金资助项目（61402419,60970083,61272221）;国家社会科学基金资助项目（14BYY096）;国家高技术研究发展计划（“八六三”计划）项目（2012AA011101）;河南省科技厅科技攻关计划项目（132102210407）;河南省科技厅基础研究项目（142300410231,142300410308）;河南省教育厅科学技术研究重点项目（128520055,138520381）

关键词：情感倾向性, 递归神经网络, 深度学习, 机器学习, RNN, sentiment analysis, recursive neural network, RNN, deep learning, machine learning

中文摘要：

文本的情感倾向在很大程度上依赖于其中情感倾向性较高的关键句，对这些情感关键句正确判定有利于提高整个篇章情感分类的效果。传统的基于规则的情感倾向性分析的优点是情感词表和规则表达准确，缺点是完备性差，而统计的方法则相反。结合使用支持向量机（support vector machine，SVM）与递归神经网络（recursive neural network，RNN）分别构造分类器，然后对整个篇章和单个句子进行情感二元分类，将分类结果进行比较投票后判定出篇章中的情感关键句。句子级情感特征不仅包含情感词、否定词等传统的文法信息，同时加入深度学习领域中词向量的统计信息，而在篇章特征中也抽取出句型、位置等宏观信息。通过参与COAE 2014评测任务1的结果显示，该方法的微平均F1值达到0.388，在同类评测系统中处于最高水平。

英文摘要：

Key sentiment sentences play an important role in predicting the sentiment distribution in texts,and therefore it improves the performance after correctly judging these key sentences.After analyzing the advantages and disadvanta-ges of the state-of-the-art approaches which are mainly based on rules and statistics,it is found that rule-based methods achieve high accuracy but with low coverage,the statistic method is quite the opposite.In this paper,a novel deep learning framework to predict sentiment distributions based on Recursive Neural Network as well as Support Vector Ma-chine was introduced.There are sentiment features including not only grammar information such as sentiment and nega-tive words,but also statistical information like word vector in deep learning.Meanwhile,text features like sentence pat-tern and position were also involved.This method combines SVM and RNN in deep learning to predict sentiment distri-butions in texts,which outperforms other traditional approaches.The result from COAE2014 Task 1 shows that our method achieves a MicroF1 value of 0.388,higher than the average level.

同期刊论文项目