Combination of GRU and CNN Deep Learning Models for Sentiment Analysis on French Customer Reviews Using XLNet Model

被引:7
|
作者
Habbat N. [1 ]
Anoun H. [1 ]
Hassouni L. [2 ]
机构
[1] Université Hassan Ii de Casablanca, Casablanca
[2] Ritm Laboratory, Ced Ensem Higher School of Technology Hassan Ii University, Casablanca
来源
IEEE Engineering Management Review | 2023年 / 51卷 / 01期
关键词
CamemBERT; convolutional neural networks (CNN); deep learning; French reviews; MultiFiT; recurrent neural networks (RNNs); XLNet;
D O I
10.1109/EMR.2022.3208818
中图分类号
学科分类号
摘要
Sentiment analysis is the task of detecting opinions of people from text using techniques of natural language processing. It is critical in assisting businesses in actively improving their company strategy and better understanding client feedback on their products. Recently, the researchers have shown that deep learning models, namely convolutional neural network (CNN), recurrent neural networks (RNNs), and contextualized transformer-based word embeddings, give hopeful results for extracting sentiment from text. Withal, bidirectional RNN utilizes two directions of RNN to better extract long-term dependences, CNN has the benefit of high-level features extracting, and it may not examine a sequence of correlations efficiently. In addition, the transformer-based word embeddings are the computational resources needed to fine-tune to solve the problem of overfitting on small datasets. For that, we propose in this work a combination of different RNNs models [e.g., long short-term memory (LSTM), bidirectional LSTM, and gated recurrent unit (GRU)] and CNN, using different word embeddings (MultiFiT, XLNet, and CamemBERT). The experimental results show that the combination of GRU and CNN with XLNet has an apparent improvement upon the state of the art on three French datasets: 1) French Amazon Customer Reviews, 2) AlloCiné Dataset, and 3) French Twitter Sentiment Analysis, with 96.5%, 90.1%, and 89.6% accuracies in decreasing order, respectively. © 1973-2011 IEEE.
引用
收藏
页码:41 / 51
页数:10
相关论文
共 50 条
  • [31] LSTM-CNN Deep Learning Model for Sentiment Analysis of Dialectal Arabic
    Abu Kwaik, Kathrein
    Saad, Motaz
    Chatzikyriakidis, Stergios
    Dobnik, Simon
    ARABIC LANGUAGE PROCESSING: FROM THEORY TO PRACTICE, ICALP 2019, 2019, 1108 : 108 - 121
  • [32] Sentiment Analysis of Customer Reviews based on Hidden Markov Model
    Soni, Swati
    Sharaff, Aakanksha
    ICARCSET'15: PROCEEDINGS OF THE 2015 INTERNATIONAL CONFERENCE ON ADVANCED RESEARCH IN COMPUTER SCIENCE ENGINEERING & TECHNOLOGY (ICARCSET - 2015), 2015,
  • [33] Sentiment analysis of pilgrims using CNN-LSTM deep learning approach
    Alasmari, Aisha
    Farooqi, Norah
    Alotaibi, Youseef
    PEERJ COMPUTER SCIENCE, 2024, 10
  • [34] A Hybrid DBN-GRU Model for Enhanced Sentiment Analysis in Product Reviews
    Khan, Shaista
    Sekhar, J. Chandra
    Ramu, J.
    El-Ebiary, Yousef A. Baker
    Saravanan, K. Aanandha
    Kumar, Kuchipudi Prasanth
    Waghe, Prajakta Uday
    INTERNATIONAL JOURNAL OF ADVANCED COMPUTER SCIENCE AND APPLICATIONS, 2024, 15 (07) : 901 - 911
  • [35] Sentiment analysis using a deep ensemble learning model
    Başarslan, Muhammet Sinan
    Kayaalp, Fatih
    Multimedia Tools and Applications, 2024, 83 (14) : 42207 - 42231
  • [36] Sentiment analysis using a deep ensemble learning model
    Basarslan, Muhammet Sinan
    Kayaalp, Fatih
    MULTIMEDIA TOOLS AND APPLICATIONS, 2023, 83 (14) : 42207 - 42231
  • [37] Sentiment analysis using a deep ensemble learning model
    Muhammet Sinan Başarslan
    Fatih Kayaalp
    Multimedia Tools and Applications, 2024, 83 : 42207 - 42231
  • [38] Sentiment Analysis on Customer Reviews using Convolutional Neural Network
    Tammina, Srikanth
    Annareddy, Sunil
    2020 INTERNATIONAL CONFERENCE ON COMPUTER COMMUNICATION AND INFORMATICS (ICCCI - 2020), 2020, : 518 - 523
  • [39] Comparative Sentiment Analysis on a Set of Movie Reviews Using Deep Learning Approach
    Chakraborty, Koyel
    Bhattacharyya, Siddhartha
    Bag, Rajib
    Hassanien, Aboul Ella
    INTERNATIONAL CONFERENCE ON ADVANCED MACHINE LEARNING TECHNOLOGIES AND APPLICATIONS (AMLTA2018), 2018, 723 : 311 - 318
  • [40] Sentiment and emotion analysis using pretrained deep learning models
    Davidson Kwamivi Aidam
    Ben-Bright Benuwa
    Stephen Opoku Oppong
    Edward Nwiah
    Journal of Data, Information and Management, 2024, 6 (3): : 277 - 295