Learning Sentiment-Specific Word Embedding for Twitter Sentiment Classification
Learning Sentiment-Specific Word Embedding for Twitter Sentiment Classification
复制标题
DOI：
10.3115/v1/p14-1146
复制
发表时间：
2014-06
期刊：
影响因子：
--
通讯作者：
Duyu Tang;Furu Wei;Nan Yang;M. Zhou;Ting Liu;Bing Qin
中科院分区：
文献类型：
--
作者：
Duyu Tang;Furu Wei;Nan Yang;M. Zhou;Ting Liu;Bing Qin
在本文中，我们提出了一种学习Twitter情感分类的词嵌入方法。现有的大多数学习连续词表示的算法通常只对词的句法上下文进行建模，而忽略了文本的情感。这对于情感分析来说是有问题的，因为它们通常将具有相似句法上下文但相反情感极性（例如好和坏）的词映射到相邻词向量。我们通过学习特定情感词嵌入（SSWE）来解决这个问题，SSWE在单词的连续表示中编码情感信息。具体来说，我们开发了三个神经网络，以有效地将文本（例如句子或推文）的情感极性监督纳入其损失函数。为了获得大规模的训练语料库，我们从大量的远距离监督的推文中学习情感特定的词嵌入，这些推文由积极和消极的表情符号组成。将SSWE应用于SemEval 2013中的基准Twitter情感分类数据集的实验表明：（1）SSWE特征在性能最好的系统中与手工制作的特征进行了匹配;（2）通过将SSWE与现有特征集连接，性能得到了进一步提高。
We present a method that learns word embedding for Twitter sentiment classification in this paper. Most existing algorithms for learning continuous word representations typically only model the syntactic context of words but ignore the sentiment of text. This is problematic for sentiment analysis as they usually map words with similar syntactic context but opposite sentiment polarity, such as good and bad, to neighboring word vectors. We address this issue by learning sentimentspecific word embedding (SSWE), which encodes sentiment information in the continuous representation of words. Specifically, we develop three neural networks to effectively incorporate the supervision from sentiment polarity of text (e.g. sentences or tweets) in their loss functions. To obtain large scale training corpora, we learn the sentiment-specific word embedding from massive distant-supervised tweets collected by positive and negative emoticons. Experiments on applying SSWE to a benchmark Twitter sentiment classification dataset in SemEval 2013 show that (1) the SSWE feature performs comparably with hand-crafted features in the top-performed system; (2) the performance is further improved by concatenating SSWE with existing feature set.