期刊
NEUROCOMPUTING
卷 275, 期 -, 页码 2459-2466出版社
ELSEVIER
DOI: 10.1016/j.neucom.2017.11.023
关键词
Twitter sentiment classification; Sentiment analysis; Word embedding; Multi-level learning
资金
- Scientific Research Starting Foundation for High-level Talents of Pingdingshan University [PXY-BSQD2017001]
- Foundation for Fostering the National Foundation of Pingdingshan University [PXY-PYJJ-2018003]
- Educational Commission of Henan Province, China [17A520050]
- National Natural Science Foundation of China [61772378, 61373108]
- National Social Science Foundation of China [11\ZD189]
- High Performance Computing Center of Computer School, Wuhan University
Existing studies learn sentiment-specific word representations to boost the performance of Twitter sentiment classification, via encoding both n-gram and distant supervised tweet sentiment information in learning process. Pioneer efforts explicitly or implicitly assume that all words within a tweet have the same sentiment polarity as that of the whole tweet, which basically ignores the word its own sentiment polarity. To alleviate this problem, we propose to learn sentiment-specific word embedding by exploiting both the lexicon resource and distant supervised information. In particular, we develop a multilevel sentiment-enriched word embedding learning method, which employs a parallel asymmetric neural network to model n-gram, word-level sentiment, and tweet-level sentiment in the learning process. Extensive experiments on standard benchmarks demonstrate our approach outperforms state-of-the-art methods. (C) 2017 Elsevier B.V. All rights reserved.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据