Sentiment Analysis using Word2vec-CNN-BiLSTM Classification

被引:10
|
作者
Yue, Wang [1 ]
Li, Lei [2 ]
机构
[1] Hosei Univ, Grad Sch Sci Engn, Li Lab, 3-7-2 Kajinocho, Koganei, Tokyo 1848584, Japan
[2] Hosei Univ, Dept Sci & Engn, 3-7-2 Kajinocho, Koganei, Tokyo 1848584, Japan
关键词
sentiment analysis; CNN; BiLSTM; Word2vec; text classification;
D O I
10.1109/SNAMS52053.2020.9336549
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Traditional neural network based short text classification algorithms for sentiment classification is easy to find the errors. In order to solve this problem, the Word Vector Model (Word2vec), Bidirectional Long-term and Short-term Memory networks (BiLSTM) and convolutional neural network (CNN) are combined. The experiment shows that the accuracy of CNN-BiLSTM model associated with Word2vec word embedding achieved 91.48%. This proves that the hybrid network model performs better than the single structure neural network in short text.
引用
收藏
页码:35 / 39
页数:5
相关论文
共 50 条
  • [21] Sentiment Lexicon Expansion using Word2vec and fastText for Sentiment Prediction in Tamil texts
    Thavareesan, Sajeetha
    Mahesan, Sinnathamby
    MERCON 2020: 6TH INTERNATIONAL MULTIDISCIPLINARY MORATUWA ENGINEERING RESEARCH CONFERENCE (MERCON), 2020, : 272 - 276
  • [22] Sentiment Classification of Reviews on Automobile Websites by Combining Word2Vec and Dependency Parsing
    Liu, Feifei
    Wei, Fang
    Yu, Ke
    Wu, Xiaofei
    SMART COMPUTING AND COMMUNICATION, SMARTCOM 2017, 2018, 10699 : 206 - 221
  • [23] Effective Method for Sentiment Lexical Dictionary Enrichment based on Word2Vec for Sentiment Analysis
    Alshari, Eissa M.
    Azman, Azreen
    Doraisamy, Shyamala
    Mustapha, Norwati
    Alkeshr, Mostafa
    2018 FOURTH INTERNATIONAL CONFERENCE ON INFORMATION RETRIEVAL AND KNOWLEDGE MANAGEMENT (CAMP), 2018, : 177 - 181
  • [24] SENTI2VEC: AN EFFECTIVE FEATURE EXTRACTION TECHNIQUE FOR SENTIMENT ANALYSIS BASED ON WORD2VEC
    Alshari, Eissa M.
    Azman, Azreen
    Doraisamy, Shyamala
    Mustapha, Norwati
    Alksher, Mostafa
    MALAYSIAN JOURNAL OF COMPUTER SCIENCE, 2020, 33 (03) : 240 - 251
  • [25] Deep Learning Framework bused on Word2Vec and CNN for Users Interests Classification
    Ombabi, Abubakr H.
    Lazzez, Onsa
    Ouarda, Wael
    Alimi, Adel M.
    PROCEEDINGS OF 2017 SUDAN CONFERENCE ON COMPUTER SCIENCE AND INFORMATION TECHNOLOGY (SCCSIT), 2017, : 36 - 42
  • [26] Sentimental Short Sentences Classification by Using CNN Deep Learning Model with Fine Tuned Word2Vec
    Sharma, Amit Kumar
    Chaurasia, Sandeep
    Srivastava, Devesh Kumar
    INTERNATIONAL CONFERENCE ON COMPUTATIONAL INTELLIGENCE AND DATA SCIENCE, 2020, 167 : 1139 - 1147
  • [27] An Optimized Deep ConvNet Sentiment Classification Model with Word Embedding and BiLSTM Technique
    Ranjan, Roop
    Daniel, A. K.
    ADCAIJ-ADVANCES IN DISTRIBUTED COMPUTING AND ARTIFICIAL INTELLIGENCE JOURNAL, 2022, 11 (03): : 309 - 329
  • [28] GloVe-CNN-BiLSTM Model for Sentiment Analysis on Text Reviews
    Li, Xiaoyan
    Raga, Rodolfo C.
    Shi, Xuemei
    JOURNAL OF SENSORS, 2022, 2022
  • [29] Sentiment Analysis Based on Weighted Word2vec and Att-LSTM
    Yuan, Huanhuan
    Wang, Yongli
    Feng, Xia
    Sun, Shurong
    PROCEEDINGS OF 2018 THE 2ND INTERNATIONAL CONFERENCE ON COMPUTER SCIENCE AND ARTIFICIAL INTELLIGENCE (CSAI 2018) / 2018 THE 10TH INTERNATIONAL CONFERENCE ON INFORMATION AND MULTIMEDIA TECHNOLOGY (ICIMT 2018), 2018, : 420 - 424
  • [30] Sentiment Analysis of Consumer Web Reviews Based on CNN-BiLSTM
    Niu, Tao
    Shi, Xingfen
    JOURNAL OF CIRCUITS SYSTEMS AND COMPUTERS, 2025,