TextCNN (Convolutional Neural Network)-based student online learning behavior detection method and TextCNN-based student online learning behavior detection system
A detection method and behavioral technology, applied in digital data information retrieval, biological neural network model, unstructured text data retrieval, etc., can solve problems such as complex structure
Active Publication Date: 2021-09-17
FUZHOU UNIV
View PDF5 Cites 2 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
In order to solve the problem of traditional models ignoring word order and context and complex structure, lai proposed a model of recurrent convolutional neural network (RCNN)
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0060] As shown in the figure, a TextCNN-based online learning behavior detection method for students is characterized in that: the detection method includes the following steps;
[0061] Step S1, log in to the online classroom, and crawl the speech information of the students as learning behavior data;
[0062] Step S2, preprocessing the data obtained by crawling to form preprocessing data;
[0063] Step S3, using the preprocessing data to pre-train the Skip-gram model;
[0064] Step S4, training to obtain the TextCNN classification model;
[0065] Step S5, using the TextCNN classification model to identify the online learning behavior of the students to be tested;
[0066] Step S6: Calculate the course comment activity index and the final score of each student according to the identification result.
[0067] The step S1 adopts the method of combining Selenium and browser driver to crawl the student's learning behavior data, which is specifically: first, enter the account ...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention provides a TextCNN (Convolutional Neural Network)-based student online learning behavior detection method and a TextCNN-based student online learning behavior detection system. The method comprises the following steps: S1, logging in an online classroom, and crawling speaking information of students as learning behavior data; s2, preprocessing the crawled data to form preprocessed data; S3, pre-training a Skip-gram model by using the pre-processed data; s4, obtaining a TextCNN classification model through training; S5, using the TextCNN classification model to identify the online learning behavior of the student to be tested; s6, calculating a course comment active index and a final score of each student according to an recognition result; according to the method, effective and invalid comments in an online classroom comment region are recognized, a new course discussion score evaluation method is designed, an auxiliary evaluation tool is provided for an online learning platform, learning behaviors of students are corrected, the independent thinking ability of the students is cultivated, and MOOC course construction under epidemic situation normalization is promoted.
Description
technical field [0001] The invention relates to the technical field of behavior detection and aims to provide an auxiliary evaluation tool for an online learning platform, in particular to a TextCNN-based online learning behavior detection method and system for students. Background technique [0002] Online courses have become the main form of continuing education for students during the epidemic, and many high-quality courses have been published on MOOCs (MOOCs) in Chinese universities. Course assessments include unit tests, final exams, video study duration, and course discussions. Course discussions are included in the assessment. The original intention is to cultivate students’ ability to think independently, encourage students to ask questions actively, communicate and interact with course teachers, and help the course team to promote course construction. However, taking the number of participating comments as the only criterion for evaluating the grades of course disc...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Applications(China)
IPC IPC(8): G06F16/33G06F16/9535G06F40/289G06K9/62G06N3/04G06Q10/06G06Q50/20
CPCG06F16/9535G06F40/289G06F16/3344G06Q50/205G06Q10/06395G06N3/045G06F18/214
Inventor 董晨洪祺瑜王泽鸿陈羽中张浩熊乾程
Owner FUZHOU UNIV