Analysis of Wakamono Kotoba Emotion Corpus and Its Application in Emotion Estimation
Analysis of Wakamono Kotoba Emotion Corpus and Its Application in Emotion Estimation
复制标题
DOI：
--
复制
发表时间：
2011
期刊：
影响因子：
--
通讯作者：
Kazuyuki Matsumoto;Yusuke Konishi;Hidemichi Sayama;F. Ren
中科院分区：
文献类型：
--
作者：
Kazuyuki Matsumoto;Yusuke Konishi;Hidemichi Sayama;F. Ren
最近，有很多研究旨在从文本中估计情感。日常生活中使用的语言表达的含义因其使用的语境而异。也就是说，它们所包含的信息具有模糊性。尤其是年轻人使用的日语“若之野语”存在语义歧义。这些词通常不包括在现有的词典中，使这些词的意思难以识别。在本研究项目中，我们提出了一种利用统计学习方法（如朴素贝叶斯方法和积累方法）从包含Wakamono Kotoba的句子中估计情感的方法。现有的研究通常集中在以单词或单词N-gram为特征的学习方法上。然而，这种基于词的特征不足以处理若之野琴跋，因为若之野琴跋往往不能被形态学分析识别为一个语义词。本文描述了我们如何构建Wakamono Kotoba情感语料库语言资源用于情感识别，并介绍了我们从统计分析中获得的特征。我们的Wakamono Kotoba情感语料库包括年轻人用来表达情感的日语单词。这些主要是从十几岁到二十几岁的年轻人写的博客中收集的。
Recently, there is a lot of research that aims to estimate emotion from text. The meanings of linguistic expressions used in daily life vary depending on the context in which they are used. That is to say, the information they contain presents ambiguities. Especially the so-called “Wakamono Kotoba,” Japanese language used by young people contains semantic ambiguities. Such words are usually not included in the existing dictionaries, making the meanings of these words difficult to be recognized. In this research project we proposed a method to estimate emotion from sentences that include Wakamono Kotoba by using statistical learning methods such as Naive Bayes method and Accumulation method. The existing research usually focused on learning methods using word or word N-gram as features. However, such word-based features are insufficient to process Wakamono Kotoba because Wakamono Kotoba often cannot be recognized as one semantic word by morphological analysis. In this paper we describe how we constructed the linguistic resource of Wakamono Kotoba emotion corpus to be used for emotion recognition and introduce the features we obtained from statistical analysis. Our Wakamono Kotoba emotion corpus includes Japanese words used by young people to express emotion. These were mainly gathered from Weblogs that were written by young people from their teens to their twenties.