Website based sentiment analysis aims to reveal the potential emotional value of non constructive text data, which is very valuable to governments, enterprises and individuals. The purpose of this paper is to study emotion classification based on reverse neural network. In the experiment, we systematically describe the design and implementation of text emotion classification using long memory, short memory and recursive element models. In this paper, a synthesis method based on surface features and deep knowledge is proposed. In addition, LSTM recruitment neural network model is used to improve the classification accuracy to 88%, which is 18% higher than the traditional vector support method based on shallow features.

Shuhua Xu. Recurrent Neural Networks for Sentiment Classification and Recognition. International Journal of Neural Network (2021), Vol. 2, Issue 4: 1-8. https://doi.org/10.38007/NN.2021.020401.

[1] Alghifari M F, Gunawan T S, Kartiwi M. Speech emotion recognition using deep feedforward neural network. Indonesian Journal of Electrical Engineering and Computer Science, 2018, 10(2):554-561. https://doi.org/10.11591/ijeecs.v10.i2.pp554-561

[2] Samadiani N, Huang G, Hu Y, et al. Happy Emotion Recognition From Unconstrained Videos Using 3D Hybrid Deep Features. IEEE Access, 2021, PP(99):1-1. https://doi.org/10.1109/ACCESS.2021.3061744

[3] Shukla S, Jain M. A novel stochastic deep conviction network for emotion recognition in speech signal. Journal of Intelligent and Fuzzy Systems, 2020, 38(2):1-16. https://doi.org/10.3233/JIFS-191753

[4] Veltmeijer E A, Gerritsen C, Hindriks K. Automatic emotion recognition for groups: a review. IEEE Transactions on Affective Computing, 2021, PP(99):1-1. https://doi.org/10.1109/TAFFC.2021.3065726

[5] Aishwarya R. Feature Extraction for Emotion Recognition in Speech with Machine Learning Algorithm. International Journal of Advanced Trends in Computer Science and Engineering, 2020, 9(4):4998-5002. https://doi.org/10.30534/ijatcse/2020/116942020

[6] Mesnyankina K K, Anishchenko S I, Kalinin K B. The Correlation between the Set of Mental Functions and Emotion Recognition Skills Formation in Children with Autism Spectrum Disorder. Autism and Developmental Disorders, 2020, 18(4):13-22. https://doi.org/10.17759/autdd.2020180402

[7] Jain N, Kumar S, Kumar A, et al. Hybrid deep neural networks for face emotion recognition. Pattern Recognition Letters, 2018, 115(NOV.1):101-106. https://doi.org/10.1016/j.patrec.2018.04.010

[8] Kshirsagar P. Face and Emotion Recognition under Complex Illumination Conditions Using Deep Learning with Morphological Processing. Journal of Interdisciplinary Cycle Research, 2021, XIII(VI):324-331.

[9] Albadr M, Tiun S, Ayob M, et al. Speech emotion recognition using optimized genetic algorithm-extreme learning machine. Multimedia Tools and Applications, 2022, 81(17):23963-23989. https://doi.org/10.1007/s11042-022-12747-w

[10] Wieckowski A T, White S W. Attention Modification to Attenuate Facial Emotion Recognition Deficits in Children with Autism: A Pilot Study. Journal of Autism and Developmental Disorders, 2020, 50(1):30-41. https://doi.org/10.1007/s10803-019-04223-6

[11] Schmidt T, Schlindwein M, Lichtner K, et al. Investigating the Relationship between Emotion Recognition Software and Usability Metrics. I-com, 2020, 19(2):139-151. https://doi.org/10.1515/icom-2020-0009

[12] Lotfalinezhad H, Maleki A. Application of multiscale fuzzy entropy features for multilevel subject-dependentemotion recognition. Turkish Journal of Electrical Engineering and Computer Sciences, 2019, 27(6):4070-4081. https://doi.org/10.3906/elk-1805-126

[13] Motomura K, Terasawa Y, Natsume A, et al. Anterior insular cortex stimulation and its effects on emotion recognition. Brain Structure and Function, 2019, 224(6):1-15. https://doi.org/10.1007/s00429-019-01895-9

[14] Nalbant K, BM Kalaycı, Akdemir D, et al. Emotion regulation, emotion recognition, and empathy in adolescents with anorexia nervosa. Eating and Weight Disorders - Studies on Anorexia, Bulimia and Obesity, 2019, 24(5):825-834. https://doi.org/10.1007/s40519-019-00768-8

[15] Ozseven T. A novel feature selection method for speech emotion recognition. Applied Acoustics, 2019, 146(MAR.):320-326. https://doi.org/10.1016/j.apacoust.2018.11.028

[16] Kwak Y J, Lee H S. A Study on Emotion Recognition of Children with ADHD through Computerized Facial Morphing Task. Journal of Special Education & Rehabilitation Science, 2018, 57(4):41-56. https://doi.org/10.23944/Jsers.2018.12.57.4.3

[17] Demircan S, Kahramanli H. Application of ABM to Spectral Features for Emotion Recognition. Mehran University Research Journal of Engineering and Technology, 2018, 37(4):452-462. https://doi.org/10.22581/muet1982.1804.01

[18] Kaya H, Karpov A A. Efficient and effective strategies for cross-corpus acoustic emotion recognition. Neurocomputing, 2018, 275(JAN.31):1028-1034. https://doi.org/10.1016/j.neucom.2017.09.049