Text sentiment classification is mainly used to determine the positive and negative aspects of sentiment, and obtains practical applications in user selection, information query, and information screening. In order to address the shortcomings of existing Chinese text sentiment classification algorithms, this paper briefly discusses the processing and labeling of the corpus and data collection for the implementation of the classification algorithm framework, based on the discussion of the steps of Chinese text sentiment classification based on semantic understanding and the process of Chinese text sentiment classification based on machine learning. In addition, the design of a hybrid semantic understanding and machine learning based Chinese text sentiment classification algorithm framework is discussed, and the experimental tests on sentiment classification of Chinese text by this paper's algorithm and DF, IG, and SVM are conducted, and the experimental data show that the check-all rate, check-accuracy rate, and F-measurement rate of this paper's algorithm are as high as 87.12% on average. Therefore, it is verified that the hybrid algorithm based on semantic understanding and machine learning is of high practical value in Chinese text sentiment classification.

Xuehang Shao. A Hybrid Semantic Understanding and Machine Learning Based Algorithmic Framework for Chinese Text Sentiment Classification. Machine Learning Theory and Practice (2022), Vol. 3, Issue 3: 27-34. https://doi.org/10.38007/ML.2022.030304.

[1] Tubishat, Mohammad, Idris, et al. Implicit aspect extraction in sentiment analysis: Review, taxonomy, oppportunities, and open challenges. Information Processing & Management: Libraries and Information Retrieval Systems and Communication Networks: An International Journal, 2018, 54(4):545-563. https://doi.org/10.1016/j.ipm.2018.03.008

[2] Lee, Pei-Ju, Ya-Han, et al. Assessing the helpfulness of online hotel reviews: A classification-based approach. Telematics and informatics, 2018, 35(2):436-445. https://doi.org/10.1016/j.tele.2018.01.001

[3] Tubishat, Mohammad, Idris, et al. Implicit aspect extraction in sentiment analysis: Review, taxonomy, oppportunities, and open challenges. Information Processing & Management: Libraries and Information Retrieval Systems and Communication Networks: An International Journal, 2018, 54(4):545-563. https://doi.org/10.1016/j.ipm.2018.03.008

[4] Le C C, Prasad P, Alsadoon A, et al. Text Classification: Naieve Bayes Classifier with Sentiment Lexicon. IAENG Internaitonal journal of computer science, 2019, 46(2PT.141-263):141-148.

[5] Acharya, Vishwanath, Bora, et al. Classification of SDSS photometric data using machine learning on a cloud. Current Science: A Fortnightly Journal of Research, 2018, 115(2):249-257. https://doi.org/10.18520/cs/v115/i2/249-257

[6] Donya, Dezfooli, Seyed-Mohammad, et al. Classification of water quality status based on minimum quality parameters: application of machine learning techniques. Modeling Earth Systems and Environment, 2018, 4(1):311-324. https://doi.org/10.1007/s40808-017-0406-9

[7] Kolkur M S, Kalbande D R, Kharkar V. Machine Learning Approaches to Multi-Class Human Skin Disease Detection. International journal of computational intelligence research, 2018, 14(1):29-39.

[8] Dhar P, Dutta S, Das P, et al. Cross-wavelet aided ECG beat classification using LIBSVM. Computer Methods in Biomechanics & Bio, 2018, 6(3-4):343-352. https://doi.org/10.1080/21681163.2016.1251339

[9] Priyadarshiny, Dhar, Saibal, et al. Cross-wavelet aided ECG beat classification using LIBSVM. Computer methods in biomechanics and biomedical engineering. Imaging & visualization, 2018, 6(3-4):343-352. https://doi.org/10.1080/21681163.2016.1251339

[10] Vasundhara D N, Seetha M. Rough Set based SVM Technique for Spatial Image Classification. International Journal of Computational I, 2019, 14(1):27-40.

[11] Sampaio W, Oliveira F, Filho A, et al. Classification of breast tissues into mass and non-mass by means of the micro-genetic algorithm, phylogenetic trees, LBP and SVM. Computer Methods in Biomechanics & Bio, 2018, 6(3-4):315-330. https://doi.org/10.1080/21681163.2016.1240630

[12] Vala M. Document Classification: A Technical Review. National Journal of System and Information Technology, 2018, 11(1):67-74.

[13] Hamid Y, Journaux L, Lee J A, et al. A novel method for network intrusion detection based on nonlinear SNE and SVM. International journal of artificial intelligence and soft computing, 2018, 6(4):265-286. https://doi.org/10.1504/IJAISC.2018.097280

[14] Chaitanya, Anne, Avdesh, et al. Multiclass patent document classification. Artificial intelligence research, 2018, 7(1):1-14. https://doi.org/10.5430/air.v7n1p1

[15] Brindha N, Visalakshi P. Content Based Video Feature Extraction and Classification Using Perceived Motion Energy Spectrum-SVM Classifier. International Journal of Computing & Information Technology, 2018, 10(1):1-10.

[16] N, Brindha, P, et al. Content Based Video Feature Extraction and Classification Using Perceived Motion Energy Spectrum-SVM Classifier. International journal of computing & information technology, 2018, 10(1):1-10.

[17] Marrugo N, Amaya D, Ramos O. Comparison of Multi-Class Methods of Features Extraction and Classification to Recognize EEGs Related with the Imagination of Two Vowels. International Journal on Communications Antenna and Propagation, 2018, 8(5):398-405. https://doi.org/10.15866/irecap.v8i5.12709

[18] Pampoulou E, Fuller D R. Introduction of a new AAC symbol classification system: the multidimensional quaternary symbol continuum (MQSC). Journal of Enabling Technologies, 2021, 15(4):252-267. https://doi.org/10.1108/JET-04-2021-0024