Research on the Evaluation of Deeply Intelligent Classroom Teaching and Learning in Colleges and Universities Based on Data Analysis
In the context of the era of modern information technology to promote the digital transformation of education, it is also imperative to explore the intelligence of classroom teaching evaluation. This paper proposes a Bayesian probabilistic model based on PyMC3, weights it, and introduces the princip...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Sciendo
2024-01-01
|
| Series: | Applied Mathematics and Nonlinear Sciences |
| Subjects: | |
| Online Access: | https://doi.org/10.2478/amns-2024-0255 |
| _version_ | 1797303098580926464 |
|---|---|
| author | Liang Fenglan Shen Weiwei Chen Le |
| author_facet | Liang Fenglan Shen Weiwei Chen Le |
| author_sort | Liang Fenglan |
| collection | DOAJ |
| description | In the context of the era of modern information technology to promote the digital transformation of education, it is also imperative to explore the intelligence of classroom teaching evaluation. This paper proposes a Bayesian probabilistic model based on PyMC3, weights it, and introduces the principle of incremental learning, which greatly reduces the error of the plain Bayesian algorithm in collecting and processing data teaching evaluation data. The Bayesian algorithm is used to classify and filter original classroom teaching evaluation data. The data analysis part of this paper examines the intelligent classroom, the teacher’s lecture scoring, and the student’s grades. With the help of the weighted plain Bayesian algorithm, the level of student participation in the traditional lecture mode and intelligent classroom were determined respectively, from which the classroom acceptance level and the probability of high or low evaluation of teaching were calculated. From the data collection, it can be seen that the full attendance rate of students in three months reached 54%, and the average satisfaction score of the algorithm on the teacher’s instruction reached 0.53. Therefore, the plain Bayesian algorithm used in this paper can effectively analyze the teaching evaluation data and accurately visualize the data association between student classroom engagement and teaching evaluation. |
| first_indexed | 2024-03-07T23:48:04Z |
| format | Article |
| id | doaj.art-53e49b13becb40dab698efae49ec62d7 |
| institution | Directory Open Access Journal |
| issn | 2444-8656 |
| language | English |
| last_indexed | 2024-03-07T23:48:04Z |
| publishDate | 2024-01-01 |
| publisher | Sciendo |
| record_format | Article |
| series | Applied Mathematics and Nonlinear Sciences |
| spelling | doaj.art-53e49b13becb40dab698efae49ec62d72024-02-19T09:03:36ZengSciendoApplied Mathematics and Nonlinear Sciences2444-86562024-01-019110.2478/amns-2024-0255Research on the Evaluation of Deeply Intelligent Classroom Teaching and Learning in Colleges and Universities Based on Data AnalysisLiang Fenglan0Shen Weiwei1Chen Le21School of Information Engineering, Suqian University, Suqian, Jiangsu, 223800, China.1School of Information Engineering, Suqian University, Suqian, Jiangsu, 223800, China.1School of Information Engineering, Suqian University, Suqian, Jiangsu, 223800, China.In the context of the era of modern information technology to promote the digital transformation of education, it is also imperative to explore the intelligence of classroom teaching evaluation. This paper proposes a Bayesian probabilistic model based on PyMC3, weights it, and introduces the principle of incremental learning, which greatly reduces the error of the plain Bayesian algorithm in collecting and processing data teaching evaluation data. The Bayesian algorithm is used to classify and filter original classroom teaching evaluation data. The data analysis part of this paper examines the intelligent classroom, the teacher’s lecture scoring, and the student’s grades. With the help of the weighted plain Bayesian algorithm, the level of student participation in the traditional lecture mode and intelligent classroom were determined respectively, from which the classroom acceptance level and the probability of high or low evaluation of teaching were calculated. From the data collection, it can be seen that the full attendance rate of students in three months reached 54%, and the average satisfaction score of the algorithm on the teacher’s instruction reached 0.53. Therefore, the plain Bayesian algorithm used in this paper can effectively analyze the teaching evaluation data and accurately visualize the data association between student classroom engagement and teaching evaluation.https://doi.org/10.2478/amns-2024-0255plain bayesintelligent classroomincremental learningpymc3teaching evaluation11y60 |
| spellingShingle | Liang Fenglan Shen Weiwei Chen Le Research on the Evaluation of Deeply Intelligent Classroom Teaching and Learning in Colleges and Universities Based on Data Analysis Applied Mathematics and Nonlinear Sciences plain bayes intelligent classroom incremental learning pymc3 teaching evaluation 11y60 |
| title | Research on the Evaluation of Deeply Intelligent Classroom Teaching and Learning in Colleges and Universities Based on Data Analysis |
| title_full | Research on the Evaluation of Deeply Intelligent Classroom Teaching and Learning in Colleges and Universities Based on Data Analysis |
| title_fullStr | Research on the Evaluation of Deeply Intelligent Classroom Teaching and Learning in Colleges and Universities Based on Data Analysis |
| title_full_unstemmed | Research on the Evaluation of Deeply Intelligent Classroom Teaching and Learning in Colleges and Universities Based on Data Analysis |
| title_short | Research on the Evaluation of Deeply Intelligent Classroom Teaching and Learning in Colleges and Universities Based on Data Analysis |
| title_sort | research on the evaluation of deeply intelligent classroom teaching and learning in colleges and universities based on data analysis |
| topic | plain bayes intelligent classroom incremental learning pymc3 teaching evaluation 11y60 |
| url | https://doi.org/10.2478/amns-2024-0255 |
| work_keys_str_mv | AT liangfenglan researchontheevaluationofdeeplyintelligentclassroomteachingandlearningincollegesanduniversitiesbasedondataanalysis AT shenweiwei researchontheevaluationofdeeplyintelligentclassroomteachingandlearningincollegesanduniversitiesbasedondataanalysis AT chenle researchontheevaluationofdeeplyintelligentclassroomteachingandlearningincollegesanduniversitiesbasedondataanalysis |