Research Article
Extraction Method of Emotional Elements of Online Learning Text Information Based on Natural Language Processing Technology
@INPROCEEDINGS{10.1007/978-3-031-21161-4_41, author={Haolin Song and Dawei Song and Yankun Zhen}, title={Extraction Method of Emotional Elements of Online Learning Text Information Based on Natural Language Processing Technology}, proceedings={e-Learning, e-Education, and Online Training. 8th EAI International Conference, eLEOT 2022, Harbin, China, July 9--10, 2022, Proceedings, Part I}, proceedings_a={ELEOT}, year={2023}, month={3}, keywords={Natural language processing Online learning Text information Emotional elements Emotion extraction Neural network}, doi={10.1007/978-3-031-21161-4_41} }- Haolin Song
Dawei Song
Yankun Zhen
Year: 2023
Extraction Method of Emotional Elements of Online Learning Text Information Based on Natural Language Processing Technology
ELEOT
Springer
DOI: 10.1007/978-3-031-21161-4_41
Abstract
The current methods of extracting emotional elements of text information generally adopt the principle of template matching, the algorithm is complex. Due to the limitations of the selected template, the network learning text information emotion elements cannot be comprehensively extracted, so the extraction accuracy and efficiency are low. In order to solve the above problems, this paper studies the emotional element extraction method of online learning text information based on natural language processing technology. Preprocess the online learning text information and find new words; Split the preprocessed text into sentences to generate transaction items; Frequent noun items are mined by association rules, irrelevant nouns are filtered by filtering algorithm, and the emotional elements of text information are extracted; Using the credibility analysis algorithm to judge the emotional polarity of text, and using the RNN neural network algorithm in natural language processing technology, the emotional elements of online learning text information are extracted. The test data show that the extraction time of the proposed feature extraction method is reduced by at least 35%, and the extraction accuracy of the method is improved to 80%, and the extraction result is more reliable.
