Learning Domain-Sensitive and Sentiment-Aware Word Embeddings

被引:0
|
作者
Shi, Bei [1 ]
Fu, Zihao [1 ]
Bing, Lidong [2 ]
Lam, Wai [1 ]
机构
[1] Chinese Univ Hong Kong, Dept Syst Engn & Engn Management, Hong Kong, Peoples R China
[2] Tencent AI Lab, Shenzhen, Peoples R China
关键词
CLASSIFICATION;
D O I
暂无
中图分类号
TP39 [计算机的应用];
学科分类号
081203 ; 0835 ;
摘要
Word embeddings have been widely used in sentiment classification because of their efficacy for semantic representations of words. Given reviews from different domains, some existing methods for word embeddings exploit sentiment information, but they cannot produce domain-sensitive embeddings. On the other hand, some other existing methods can generate domain-sensitive word embeddings, but they cannot distinguish words with similar contexts but opposite sentiment polarity. We propose a new method for learning domain-sensitive and sentiment-aware embeddings that simultaneously capture the information of sentiment semantics and domain sensitivity of individual words. Our method can automatically determine and produce domain-common embeddings and domain-specific embeddings. The differentiation of domain-common and domain-specific words enables the advantage of data augmentation of common semantics from multiple domains and capture the varied semantics of specific words from different domains at the same time. Experimental results show that our model provides an effective way to learn domain-sensitive and sentiment-aware word embeddings which benefit sentiment classification at both sentence level and lexicon term level.
引用
收藏
页码:2494 / 2504
页数:11
相关论文
共 50 条
  • [41] Sentiment-aware multimodal pre-training for multimodal sentiment analysis
    Ye, Junjie
    Zhou, Jie
    Tian, Junfeng
    Wang, Rui
    Zhou, Jingyi
    Gui, Tao
    Zhang, Qi
    Huang, Xuanjing
    KNOWLEDGE-BASED SYSTEMS, 2022, 258
  • [42] Sentiment-Aware Emoji Insertion Via Sequence Tagging
    Lin, Fuqiang
    Ma, Xingkong
    Min, Erxue
    Liu, Bo
    Song, Yiping
    IEEE MULTIMEDIA, 2021, 28 (02) : 40 - 48
  • [43] A Domain-Sensitive Threshold Derivation Method
    Mori, Allan
    Vale, Gustavo
    Cirilo, Elder
    Figueiredo, Eduardo
    PROCEEDINGS OF THE XV BRAZILIAN SYMPOSIUM ON INFORMATION SYSTEMS, SBSI 2019: Complexity on Modern Information Systems, 2019,
  • [44] Unsupervised Ontology- and Sentiment-Aware Review Summarization
    Le, Nhat X. T.
    Young, Neal
    Hristidis, Vagelis
    WEB INFORMATION SYSTEMS ENGINEERING - WISE 2019, 2019, 11881 : 747 - 762
  • [45] SentiMedQAer: A Transfer Learning-Based Sentiment-Aware Model for Biomedical Question Answering
    Zhu, Xian
    Chen, Yuanyuan
    Gu, Yueming
    Xiao, Zhifeng
    FRONTIERS IN NEUROROBOTICS, 2022, 16
  • [46] DomainDrop: Suppressing Domain-Sensitive Channels for Domain Generalization
    Guo, Jintao
    Qi, Lei
    Shi, Yinghuan
    2023 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2023), 2023, : 19057 - 19067
  • [47] FuncSA: Function Words-Guided Sentiment-Aware Attention for Chinese Sentiment Analysis
    Wang, Jiajia
    Zan, Hongying
    Han, Yingjie
    Cao, Juan
    NATURAL LANGUAGE PROCESSING AND CHINESE COMPUTING, NLPCC 2022, PT I, 2022, 13551 : 539 - 550
  • [48] Refining Word Embeddings with Sentiment Information for Sentiment Analysis
    Kasri M.
    Birjali M.
    Nabil M.
    Beni-Hssane A.
    El-Ansari A.
    El Fissaoui M.
    Journal of ICT Standardization, 2022, 10 (03): : 353 - 382
  • [49] Cross-Domain Sentiment Classification with Word Embeddings and Canonical Correlation Analysis
    Ngo Xuan Bach
    Vu Thanh Hai
    Tu Minh Phuong
    PROCEEDINGS OF THE SEVENTH SYMPOSIUM ON INFORMATION AND COMMUNICATION TECHNOLOGY (SOICT 2016), 2016, : 159 - 166
  • [50] Word Embeddings for Arabic Sentiment Analysis
    Altowayan, A. Aziz
    Tao, Lixin
    2016 IEEE INTERNATIONAL CONFERENCE ON BIG DATA (BIG DATA), 2016, : 3820 - 3825