IDEAS home Printed from https://ideas.repec.org/a/gam/jftint/v12y2020i12p228-d461398.html
   My bibliography  Save this article

An Analysis Method for Interpretability of CNN Text Classification Model

Author

Listed:
  • Peng Ce

    (School of Computer Science and Technology, Jilin University, Changchun 130012, China)

  • Bao Tie

    (School of Computer Science and Technology, Jilin University, Changchun 130012, China)

Abstract

With continuous development of artificial intelligence, text classification has gradually changed from a knowledge-based method to a method based on statistics and machine learning. Among them, it is a very important and efficient way to classify text based on the convolutional neural network (CNN) model. Text data are a kind of sequence data, while time sequentiality of the general text data is relatively weak, so text classification is usually less relevant to the sequential structure of the full text. Therefore, CNN-based text classification has gradually become a research hotspot when dealing with issues of text classification. For machine learning, especially deep learning, model interpretability has increasingly become the focus of academic research and industrial applications, and also become a key issue for further development and application of deep learning technology. Therefore, we recommend using the backtracking analysis method to conduct in-depth research on deep learning models. This paper proposes an analysis method for interpretability of a CNN text classification model. The method proposed by us can perform multi-angle analysis on the discriminant results of multi-classified text and multi-label classification tasks through backtracking analysis on model prediction results. Finally, the analysis results of the model can be displayed using visualization technology from multiple dimensions based on interpretability. The representative data set IMDB (Internet Movie Database) in text classification is verified by examples, and the results show that the model can be effectively analyzed when using our method.

Suggested Citation

  • Peng Ce & Bao Tie, 2020. "An Analysis Method for Interpretability of CNN Text Classification Model," Future Internet, MDPI, vol. 12(12), pages 1-14, December.
  • Handle: RePEc:gam:jftint:v:12:y:2020:i:12:p:228-:d:461398
    as

    Download full text from publisher

    File URL: https://www.mdpi.com/1999-5903/12/12/228/pdf
    Download Restriction: no

    File URL: https://www.mdpi.com/1999-5903/12/12/228/
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Yue Li & Xutao Wang & Pengjian Xu, 2018. "Chinese Text Classification Model Based on Deep Learning," Future Internet, MDPI, vol. 10(11), pages 1-12, November.
    Full references (including those not matched with items on IDEAS)

    Citations

    Citations are extracted by the CitEc Project, subscribe to its RSS feed for this item.
    as


    Cited by:

    1. Xinlu Li & Yuanyuan Lei & Shengwei Ji, 2022. "BERT- and BiLSTM-Based Sentiment Analysis of Online Chinese Buzzwords," Future Internet, MDPI, vol. 14(11), pages 1-15, November.

    Most related items

    These are the items that most often cite the same works as this one and are cited by the same works as this one.
    1. Wenkuan Li & Peiyu Liu & Qiuyue Zhang & Wenfeng Liu, 2019. "An Improved Approach for Text Sentiment Classification Based on a Deep Neural Network via a Sentiment Attention Mechanism," Future Internet, MDPI, vol. 11(4), pages 1-15, April.

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:gam:jftint:v:12:y:2020:i:12:p:228-:d:461398. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    If CitEc recognized a bibliographic reference but did not link an item in RePEc to it, you can help with this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: MDPI Indexing Manager (email available below). General contact details of provider: https://www.mdpi.com .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.