An Analysis Method for Interpretability of CNN Text Classification Model

Peng Ce,Bao Tie

doi:10.3390/fi12120228

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.

Highlights

Text classification refers to automatically classify and mark text sets using a computer according to a certain classification system or standard
After calculation of the convolutional neural network (CNN) text classification model, the category label of the text was obtained, the category label was used as the input of the backtracking analysis model, and the contribution value of the words in the text was calculated through reverse backtracking
The CNN text classification model was iterated for 30 rounds, as shown in Figure 7; the horizontal axis represents the number of iterations, the vertical axis represents the accuracy in the left figure, and the vertical axis represents the loss in the right figure

Summary

Introduction

Text classification refers to automatically classify and mark text sets using a computer according to a certain classification system or standard. Xiaoli Zhao et al proposed a dual-input convolutional neural network structure in response to the phenomenon that more and more depression patients use Weibo as a way of self-expression nowadays This method could take the external features and semantic features of the text as input and compare the accuracy of algorithm classification through SVM and CNN. Fu et al proposed an effective text classification framework This framework is a CNN–BLSTM (Long Short Term Memory) network that mixes character-level and word-level features with different weights through content-based concatenation, which overcomes the difference in semantic relations in Chinese in Chinese word segmentation. In the proposed model attention score is calculated by averaging hidden units (feature maps) generated from long short-term memory (LSTM) We combined this attention score with recurrent convolution-based encoded text features to obtain final sentence representation.

Interpretability Analysis Method

Interpretability Analysis of the Model

Selection and Processing of Data Set

Discussion