{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,19]],"date-time":"2026-02-19T15:44:12Z","timestamp":1771515852866,"version":"3.50.1"},"reference-count":20,"publisher":"MDPI AG","issue":"12","license":[{"start":{"date-parts":[[2020,12,13]],"date-time":"2020-12-13T00:00:00Z","timestamp":1607817600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Future Internet"],"abstract":"<jats:p>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.<\/jats:p>","DOI":"10.3390\/fi12120228","type":"journal-article","created":{"date-parts":[[2020,12,13]],"date-time":"2020-12-13T20:56:57Z","timestamp":1607893017000},"page":"228","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":22,"title":["An Analysis Method for Interpretability of CNN Text Classification Model"],"prefix":"10.3390","volume":"12","author":[{"given":"Peng","family":"Ce","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology, Jilin University, Changchun 130012, China"}]},{"given":"Bao","family":"Tie","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Jilin University, Changchun 130012, China"}]}],"member":"1968","published-online":{"date-parts":[[2020,12,13]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Li, Y., Wang, X., and Xu, P. (2018). Chinese Text Classification Model Based on Deep Learning. Future Internet, 10.","DOI":"10.3390\/fi10110113"},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Kim, Y. (2014). Convolutional neural networks for sentence classification. arXiv.","DOI":"10.3115\/v1\/D14-1181"},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Kim, H., and Jeong, Y.-S. (2019). Sentiment Classification Using Convolutional Neural Networks. Appl. Sci., 9.","DOI":"10.3390\/app9112347"},{"key":"ref_4","first-page":"279","article-title":"High Utility Neural Networks for Text Classification","volume":"48","author":"Wu","year":"2020","journal-title":"Tien Tzu Hsueh Pao\/Acta Eletronica Sin."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"216","DOI":"10.1016\/j.ins.2018.09.001","article-title":"An analysis of hierarchical text classification using word embeddings","volume":"471","author":"Stein","year":"2019","journal-title":"Inf. Sci."},{"key":"ref_6","first-page":"599","article-title":"Multi-representational convolutional neural networks for text classification","volume":"35","author":"Jin","year":"2019","journal-title":"Neural Comput. Appl."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Wang, L., and Zhang, B. (2020, January 16\u201321). Fault Text Classification Based on Convolutional Neural Network. Proceedings of the 2020 IEEE 7th International Conference on Industrial Engineering and Applications (ICIEA), Bangkok, Thailand.","DOI":"10.1109\/ICIEA49774.2020.9101960"},{"key":"ref_8","unstructured":"Zou, B., Li, M., Wang, H., Song, X., Xie, W., and Lu, Z. (2017). Text Feature Extraction and Classification Based on Convolutional Neural Network (CNN), Springer. Data Science; ICPCSEE 2017; Communications in Computer and Information Science."},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Zhao, X., Lin, S., and Huang, Z. (2018, January 21\u201323). Text Classification of Micro-blog\u2019s \u201cTree Hole\u201d Based on Convolutional Neural Network. Proceedings of the 2018 International Conference on Algorithms, Computing and Artificial Intelligence (ACAI\u201918), Sanya, China.","DOI":"10.1145\/3302425.3302501"},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Fu, L., Yin, Z., Wang, X., and Liu, Y. (2018, January 15\u201317). A Hybrid Algorithm for Text Classification Based on CNN-BLSTM with Attention. Proceedings of the 2018 International Conference on Asian Language Processing (IALP), Bandung, Indonesia.","DOI":"10.1109\/IALP.2018.8629219"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"120","DOI":"10.1049\/cje.2018.11.004","article-title":"A Text Sentiment Classification Modeling Method Based on Coordinated CNN-LSTM-Attention Model","volume":"28","author":"Zhang","year":"2019","journal-title":"Chin. J. Electron."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Chen, K., Tian, L., Ding, H., Cai, M., Sun, L., Liang, S., and Huo, Q. (2017, January 9\u201315). A Compact CNN-DBLSTM Based Character Model for Online Handwritten Chinese Text Recognition. Proceedings of the 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR), Kyoto, Japan.","DOI":"10.1109\/ICDAR.2017.177"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Usama, M., Ahmad, B., Singh, A.P., and Ahmad, P. (2019, January 14\u201316). Recurrent Convolutional Attention Neural Model for Sentiment Classification of short text. Proceedings of the 2019 International Conference on Cutting-Edge Technologies in Engineering, Icon-CuTE, Uttar Pradesh, India.","DOI":"10.1109\/ICon-CuTE47290.2019.8991445"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"She, X., and Zhang, D. (2018, January 8\u20139). Text Classification Based on Hybrid CNN-LSTM Hybrid Model. Proceedings of the 2018 11th International Symposium on Computational Intelligence and Design, ISCID, Hangzhou, China.","DOI":"10.1109\/ISCID.2018.10144"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Guo, L., Zhang, D., Wang, l., Wang, H., and Cui, B. (2018, January 22\u201325). CRAN: A hybrid CNN-RNN attention-based model for text classification. Proceedings of the 37th International Conference, ER 2018, Xi\u2019an, China.","DOI":"10.1007\/978-3-030-00847-5_42"},{"key":"ref_16","first-page":"39","article-title":"Interpretability for Deep Learning","volume":"26","author":"Fei","year":"2019","journal-title":"Aero Weapon."},{"key":"ref_17","first-page":"2902","article-title":"Sentiment classification model based on word embedding and CNN","volume":"33","author":"Huiping","year":"2016","journal-title":"Appl. Res. Comput."},{"key":"ref_18","unstructured":"Simonyan, K., Vedaldi, A., and Zisserman, A. (2013). Deep Inside Con-volutional Networks: Visualising Image Classification Models and Saliency Maps. arXiv."},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Dosovitskiy, A., and Brox, T. (2016, January 27\u201330). Inverting Visual Representations with Convolutional Networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recog-nition, LasVegas, NV, USA.","DOI":"10.1109\/CVPR.2016.522"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Selvaraju, R.R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., and Batra, D. (2017, January 22\u201329). Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization. Proceedings of the 2017 IEEE International Conference on Computer Vision (ICCV), Venice, Italy.","DOI":"10.1109\/ICCV.2017.74"}],"container-title":["Future Internet"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1999-5903\/12\/12\/228\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T10:44:32Z","timestamp":1760179472000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1999-5903\/12\/12\/228"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,12,13]]},"references-count":20,"journal-issue":{"issue":"12","published-online":{"date-parts":[[2020,12]]}},"alternative-id":["fi12120228"],"URL":"https:\/\/doi.org\/10.3390\/fi12120228","relation":{},"ISSN":["1999-5903"],"issn-type":[{"value":"1999-5903","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,12,13]]}}}