CAJ | 학술논문

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。
문본적정감경향재흔대정도상의뢰우기중정감경향성교고적관건구，대저사정감관건구정학판정유리우제고정개편장정감분류적효과。전통적기우규칙적정감경향성분석적우점시정감사표화규칙표체준학，결점시완비성차，이통계적방법칙상반。결합사용지지향량궤（support vector machine，SVM）여체귀신경망락（recursive neural network，RNN）분별구조분류기，연후대정개편장화단개구자진행정감이원분류，장분류결과진행비교투표후판정출편장중적정감관건구。구자급정감특정불부포함정감사、부정사등전통적문법신식，동시가입심도학습영역중사향량적통계신식，이재편장특정중야추취출구형、위치등굉관신식。통과삼여COAE 2014평측임무1적결과현시，해방법적미평균F1치체도0.388，재동류평측계통중처우최고수평。
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.