In recent years, another idea of text modeling based on graph structured data has been continuously developed. Unlike Bert, graph neural network is a graph based deep learning network, which can capture the dependency relationship in a graph through message aggregation between neighboring nodes. It makes up for the problem that traditional deep learning networks can not process graph structure data, and is also increasingly used in text classification tasks. At present, there are still many problems in the text classification methods of graph networks. The graph convolution neural network method based on the global graph can not introduce the time series information contained in the text, and the graph neural network method based on the subgraph can not give different representations to the same word in different sentences. This paper proposes a text classification model based on graph neural network and fine-tuning Bert. Experimental results on multiple test data sets show that our model can learn more abundant text features. Compared with the baseline model, the accuracy is improved by 1.98%, and the F1 value is improved by 2.93%.

Saravanan Saini. Improved Text Classification Algorithm Based on Neural Network. International Journal of Neural Network (2021), Vol. 2, Issue 1: 35-43. https://doi.org/10.38007/NN.2021.020105.

[1] Du J H. Automatic Text Classification Algorithm Based on Gauss Improved Convolutional Neural Network. Journal of Computational Science. (2017) 21(jul.):195-200. https://doi.org/10.1016/j.jocs.2017.06.010

[2] Kruthiventi S, Ayush K, Babu R V. DeepFix: A Fully Convolutional Neural Network for Predicting Human Eye Fixations. IEEE Transactions on Image Processing. (2017) 26(9):4446-4456. https://doi.org/10.1109/TIP.2017.2710620

[3] Acharya U R, Fujita H, Lih O S, et al. Automated Detection of Arrhythmias Using Different Intervals of Tachycardia ECG Segments with Convolutional Neural Network. Information Sciences. (2017) 405:81-90. https://doi.org/10.1016/j.ins.2017.04.012

[4] Mishkin D, Sergievskiy N, Matas J. Systematic Evaluation of Convolution Neural Network Advances On the Imagenet. Computer Vision and Image Understanding. (2017) 161(aug.):11-19. https://doi.org/10.1016/j.cviu.2017.05.007

[5] Kahng M, Andrews P Y, Kalro A, et al. ActiVis: Visual Exploration of Industry-Scale Deep Neural Network Models. IEEE Transactions on Visualization & Computer Graphics. (2018) (99):1-1. https://doi.org/10.1109/TVCG.2017.2744718

[6] Quan H, Srinivasan D, Khosravi A. Short-Term Load and Wind Power Forecasting Using Neural Network-Based Prediction Intervals. IEEE Transactions on Neural Networks & Learning Systems. (2017) 25(2):303-315. https://doi.org/10.1109/TNNLS.2013.2276053

[7] Hou R, Chen C, Shah M. Tube Convolutional Neural Network (T-CNN) for Action Detection in Videos[C]// IEEE Computer Society. IEEE Computer Society. (2017):5823-5832. https://doi.org/10.1109/ICCV.2017.620

[8] Chatterjee S, Sarkar S, Hore S, et al. Particle Swarm Optimization Trained Neural Network for Structural Failure Prediction of Multistoried RC Buildings. Neural Computing & Applications. (2017) 28(8):2005-2016. https://doi.org/10.1007/s00521-016-2190-2

[9] Bangalore P, Tjernberg L B. An Artificial Neural Network Approach for Early Fault Detection of Gearbox Bearings. IEEE Transactions on Smart Grid. (2017) 6(2):980-987. https://doi.org/10.1109/TSG.2014.2386305

[10] Hodo E, Bellekens X, Hamilton A, et al. Threat Analysis of Iot Networks Using Artificial Neural Network Intrusion Detection System. Tetrahedron Letters. (2017) 42(39):6865-6867.

[11] Meng H, Bianchi-Berthouze N, Deng Y, et al. Time-Delay Neural Network for Continuous Emotional Dimension Prediction from Facial Expression Sequences. IEEE Transactions on Cybernetics. (2017) 46(4):916-929. https://doi.org/10.1109/TCYB.2015.2418092

[12] Ansari G J, Shah J H, Farias M, et al. an Optimized Feature Selection Technique in Diversified Natural Scene Text For Classification Using Genetic Algorithm. Ieee Access. (2021) (99):1-1. https://doi.org/10.1109/ACCESS.2021.3071169

[13] Ahmed A. A Novel Statistical Method for Scene Classification Based on Multi-Object Categorization and Logistic Regression. Sensors. (2020) 20(14). https://doi.org/10.3390/s20143871

[14] Fadzal A N, Puteh M, Rahman N A. Ant Colony Algorithm for Text Classification in Multicore-Multithread Environment. Indonesian Journal of Electrical Engineering and Computer Science. (2020) 18(3):1359. https://doi.org/10.11591/ijeecs.v18.i3.pp1359-1366

[15] Hamid Z, Khafaji H K. A General Algorithm of Association Rule-Based Machine Learning Dedicated for Text Classification. Journal of Physics Conference Series. (2021) 1773(1):012011. https://doi.org/10.1088/1742-6596/1773/1/012011

[16] Hindi K E, Shawar B A, Aljulaidan R, et al. Improved Distance Functions for Instance-Based Text Classification. Computational Intelligence and Neuroscience. (2020) (2020) (2):1-10. https://doi.org/10.1155/2020/4717984

[17] Alsammak I, Sahib H, Itwee W H. An Enhanced Performance of K-Nearest Neighbor (K-NN) Classifier to Meet New Big Data Necessities. IOP Conference Series: Materials Science and Engineering. (2020) 928(3):032013 (15pp). https://doi.org/10.1088/1757-899X/928/3/032013

[18] Samarthrao K V, Rohokale V M. Enhancement of Email Spam Detection Using Improved Deep Learning Algorithms for Cyber Security. Journal of Computer Security, (2021) (1):1-34.