Exploration and practice of online information teaching model based on big data and artificial intelligence decision-making

Abstract

Due to the new crown pneumonia outbreak in 2019, many schools are unable to teach online, which stimulates the birth of a new teaching model in the education industry. Online teaching has developed by leaps and bounds with the rapid development of information technology. Information-based teaching is a way to enhance student learning from the learning environment. There are many factors that influence the learning environment, including the classroom teaching scenario, cooperation between teachers and students, and communication in the classroom. In the teaching process, the teaching mode has changed from the traditional teacher-teaching-student-learning fill-in-the-blank teaching to the independent acquisition of knowledge by students. In order to investigate the current status of teaching informatics on the Internet, we chose a university in city A as a research object to investigate the current status of teaching informatics in its online philosophy department. At present, information technology teaching in China is still in a backward state. The current situation of information-based teaching in China is (1) the lack of information-based teaching resources and the lack of standardization in the use of resources. (2) Lack of awareness of online information teaching. In order to promote the level of online information-based learning of our schoolchildren from a comprehensive perspective, and in response to the drawbacks of online information-based teaching in China found in the above experimental survey, we propose an online information-based learning model based on big data and artificial intelligence decision-making to enhance students’ learning interest through an interesting learning model. After experimental verification, it can be concluded that our proposed model can significantly improve students’ behavioral performance and learning ability, and has a certain role in enhancing students’ learning effectiveness. Finally, we make recommendations based on the current state of application of big data and artificial intelligence in online informatics teaching. The recommendations are to improve the current situation of information-based teaching on the one hand to improve the quality of information-based resources, which requires the joint gate-keeping of the government, schools and teachers. On the other hand, the information technology literacy of teachers should be improved.

Keywords

artificial intelligence decision-making big data online informatization teaching mode

Introduction

With the continuous progress of information technology and economic development in society, various new technologies have been popularized in daily life. Multimedia and other technologies are widely used in the teaching field, changing the traditional teaching mode. In China, since the beginning of 2019, some students are isolated at home by the new crown pneumonia epidemic and cannot have offline classes. To solve this problem, large-scale online teaching has been launched in China. The opening of online teaching is an emergency measure to adapt to the form of our country, but the increase in demand for online teaching has promoted the development of online information-based teaching in our country and has caused some impact on our education industry.^1,2

Information-based teaching is a way to enhance students’ learning effect from the learning environment. There are many factors affecting the learning environment, including the classroom teaching scenario, the cooperation between teachers and students, and the communication in the classroom. In the teaching process, the teaching mode has changed from the traditional teacher-teaching-student-learning fill-in-the-blank teaching to the independent acquisition of knowledge by students. In the traditional teaching mode, teachers are the lecturers of knowledge and students are the receivers of knowledge, and students are passive receivers of knowledge, and the learning effect is often not good. However, in the information-based teaching, the teacher turns from the knowledge imparter to the helper for students to acquire knowledge independently. In this teaching mode, students arrive at knowledge that is no longer a rigid text in a book, but a collaborative effort between the students and the teacher, with continuous discussions. Informatization uses multimedia as a medium to build scenarios through modern information technology to better help the progress of teaching and learning. In the traditional way of teaching, multimedia is a tool for teachers to teach, and teachers can use multimedia to demonstrate and show the knowledge to students better. However, under the information-based teaching method, multimedia becomes a tool for students to access information, communicate with each other, and show themselves.

It describes the specific methods of constructing a pathology course in an online environment, such as the use of multimedia resources, interactive tools, and real-time/asynchronous communication platforms, analyzes the impact of online teaching on students’ test scores and explores whether it can effectively improve learning performance; at the same time, it examines the effect of this mode on cultivating learning interest, exercising independent learning ability, and improving practical application skills and information literacy, etc., discusses the acceptance of online learning by students and the impact of this mode on students' active learning, cooperative learning and in-depth learning. We also examine the effect of this mode on cultivating learning interests, practicing independent learning ability, improving practical application skills and information literacy, and discuss the acceptance of students to the online learning mode, and the impact of this mode on students’ active learning, cooperative learning and deep learning.³

It has been 3 years since the opening of online teaching in China, and China’s information-based teaching is currently showing two major trends. On the one hand, China’s teaching shows the trend of combining offline and online, and schools are improving the quality of online teaching by optimizing infrastructure, improving online classroom environment and equipping stable service tools. On the other hand, is the combination of information-based teaching with technologies such as artificial intelligence and big data. Big data analysis can help teachers better deal with the problems encountered in the teaching process. Artificial intelligence technology can develop personalized learning programs by analyzing students’ behavior, and I also provide technical support to discover students’ potential and achieve individualized learning. Artificial intelligence technology has a great role in helping teachers to teach, which reduces the burden of teaching and gives them enough energy to devote to the innovative development of the classroom. The basic model of online information-based teaching is shown in Figure 1.⁴

Figure 1.

Basic model of online information-based teaching.

The advent of the big data era has revolutionized the industrial structure of society. Compared with the past, society pays more attention to and relies on the overall use of information. The essence of big data is the aggregation of complex data. The basic mode of operation of big data is the collection and processing of information. The key to big data is not the massive data set, but the core requirement is the method of analyzing the data. With the advent of the era of big data and the development of algorithm technology, artificial intelligence represented by machine learning has realized self-improvement and gained new vitality through data mining and algorithm updating. At present, many industries and fields are enthusiastically taking action to combine with AI technology, and the development of big data and AI has brought new opportunities to online information teaching. The rapid development of big data and artificial intelligence has brought development opportunities to all walks of life, and progress has been made in the field of promoting the development of online information-based teaching practices. Big data’s ability to store and analyze massive amounts of data gives online information-based teaching practice an analytical tool. Artificial intelligence can build intelligent virtual scenarios and make the virtualized environment a tool for student learning. Artificial intelligence technology and big data technology provide opportunities for online information-based teaching.^5,6

Online information-based teaching questionnaire survey

Survey process

In order to investigate the status of online informatics teaching, we selected a university in city A as the research object to investigate the status of its online informatics philosophy department. We selected 40 students for the experimental investigation of online teaching. In the evaluation process, we mainly analyzed the following indicators of students: students’ concentration, students’ learning style, students’ understanding of knowledge, and students’ application of knowledge, etc. The evaluation indicators were scored on a scale of 0–10. To strengthen the persuasiveness of the experiment, we added a control group of 40 students randomly selected for offline learning, taught by the same teacher, with the same content and duration control as the first group. At the same time, in order to ensure the consistency of the subjects in the experimental and control groups. The subjects of the two groups were screened before the experiment, and their final test results are shown in Table 1.

Table 1.

Tests on the control group and experimental group before the experiment.

Project	Control group	Experimental group
Language expression ability	9.201	9.214
Mental health	8.886	8.771
Learning ability	9.321	9.322
The love of learning	7.258	7.222
Comprehensive ability	8.369	8.324

This shows that the subjects of the experimental group and the control group can be considered to be consistent to a certain extent, which indicates that the differences between the experimental group and the control group can be ignored and the credibility of the experiment is improved.^7,8

Survey results

The control group and the experimental group were investigated, respectively. We first studied the students’ learning habits. This project is divided into two indicators, students’ concentration and students’ learning style. We calculate the average scores of the two groups of data, respectively. The specific data are shown in Table 2.

Table 2.

Learning behavior test.

Groups	Project	Fraction
Experimental group	Concentration	8.36
Experimental group	Learning style	8.01
Control group	Concentration	9.32
Control group	Learning style	9.18

It can be seen from Table 2 that the scores of the control group in concentration and learning style are higher than those of the experimental group, which indicates that the scores of offline students’ concentration and learning habits are higher than those of online students.

In the second part, we compare the degree of students’ understanding and application of knowledge. In order to facilitate the progress of the experiment, we select the concept of “data science” as the object of detection, and test the students’ understanding and application of this concept in the experimental group and the control group, respectively. The test results are shown in Figure 2.

Figure 2.

The test results.

As can be seen from Figure 2, the control group had a higher level of understanding of data science concepts and application of the concepts than the control group, which indicates that the offline learning effect is much higher than the result of online learning.

After the experiment, we conducted a questionnaire survey of 40 students who were taught online, and 36 students reported that the teacher’s lessons used to be boring, completely copied the book content, and lacked interest. There were also students who reported other reasons, though they were in the minority.^9,10

It can be concluded from the above two groups of experiments that both students’ external behavioral performance and students' internalization of knowledge were higher in the control group than in the experimental group. The experimental group was the result of students’ online learning and lack of face-to-face communication with teachers, while the control group was the result of offline learning.

Credibility analysis

Validity analysis of the data of the questionnaire is an important guarantee of the reliability of the questionnaire results. Table 3 shows that the KMO value of validity analysis is 0.770, and according to the criterion of validity analysis, it is known that when the coefficient of validity analysis >0.06, the data of this experiment is considered to have good reliability.^11,12

Table 3.

Validity analysis.

Project	Factor 1	Factor 2	Factor 3	Factor 4
Eigenvalues (before rotation)	3.196	1.287	2.898	2.999
Variance explanation rate (before rotation)	19.62%	9.64%	10.90%	8.97%
Cumulative variance interpretation rate (before rotation)	16.61%	88.24%	67.13%	47.08%
Eigenvalues (after rotation)	3.88	1.35	4.26	2.15
Variance explained rate % (after rotation)	86.89%	66.68%	69.22%	69.55%
Cumulative variance explained rate % (after rotation)	77.67%	76.63%	79.99%	88.55%
KMO value	0.770
Barth’s spherical value	0
Df	66

Reliability analysis is an important criterion to test the credibility of the questionnaire; as shown in Table 4, the reliability coefficient of this experiment is 0.889, which is between 0.8 and 1 and has a high reliability.

Table 4.

Reliability analysis.

Sample size	Number of projects	Cronbach’s α coefficient
80	10	0.889

Investigation significance

Through the comparison of online problems and offline teaching and learning situation, the shortcomings of online informatization teaching were found, and we were able to propose targeted solutions to this problem, which is of great significance to improve the level of informatization teaching in China, and can help our students to be able to learn and express their thoughts in a more comfortable way under epidemic conditions.^13,14

The current situation of online informatization teaching practice

Lack of informatization teaching resources and lack of norms for resource use

Digital education resources in schools are generally composed of two parts, on the one hand, the digital resources generated by government-led planning, and on the other hand, schools carry out high-quality courses, as well as courses in cooperation with enterprises. In general, China’s informatization teaching resources model is too old, teaching resources are often generated from the perspective of the course maker, in accordance with its accumulated experience and expertise, the construction of a complete subject system construction courses. There are also a small number of information-based teaching resources in China that are produced by enterprises to make profits while better meeting the needs of their customers. The backward digital resource production mode leads to the uneven level of our informatization curriculum and makes it difficult to play its role effectively. Another reason for the low level of China’s informatization teaching is the backward application model. Many teachers only understand online classes as live or recorded webcasts, and through teaching platforms such as Learning Pass, Tencent Classroom, and Nail, they cannot open live or recorded courses, and the teaching process in this mode is completely a one-man show for teachers, lacking interaction with students. This teaching mode cannot effectively use high-quality learning resources. At present, China’s education informatization is changing from the 1.0 era to the 2.0 era. The development of education informatization is not simply a combination of information technology and the classroom, but a deep integration of information technology and the classroom while promoting innovation and development. Therefore, teachers should abandon the concept of equating online teaching with live streaming, innovate classroom design, reform teaching mode, and create a truly useful teaching style.^15,16

Lack of awareness of online information teaching

Online teaching is a new teaching mode compared with the traditional teaching mode. He does not require students to be in the same space, and the teaching format is more flexible and diverse. However, because the online teaching mode is not mature enough, there are still various drawbacks of online teaching in China. Many online classroom teaching is just a matter of overlaying information technology, for example, some teachers teaching will copy the content of previous teaching. During asynchronous teaching, teachers may assign numerous tasks that are not only useless for student learning, but also consume a lot of time. When teachers teach online, they should consciously strengthen their exploration and innovation of online teaching modes. The teaching structure should be optimized and the teaching process should be reconstructed to bring students a better student learning experience.

Hardware facilities are the indispensable foundation of online information teaching. The lack of high-quality hardware support, such as a stable network connection, reliable electronic equipment and multimedia teaching tools, can seriously affect the teaching experience and learning effect. For example, low-bandwidth networks can cause video to stall and affect the quality of remote interactions; incompatible software and hardware combinations can cause educational resources to be inaccessible. Therefore, when planning online teaching projects, relevant departments must fully consider the updating and maintenance of hardware facilities to ensure that every participant can obtain equal learning opportunities. At the same time, the advanced degree of hardware also directly affects the implementation of new technologies, such as the application of Virtual Reality (VR) and Augmented Reality (AR) in education, which require powerful computing power and high-resolution display devices.

Transformation of information-based teaching model based on artificial intelligence and big data

Overview of the model

In order to promote the level of online information learning of our schoolchildren from a comprehensive perspective, and to address the drawbacks of our online information teaching found in the above experimental survey, we propose an online information learning model based on big data and artificial intelligence decision-making to enhance students’ learning interest through an interesting learning model. Big data enables analysis of massive amounts of data, and in our model, teachers can obtain students' learning status through the back-end of the learning platform and derive the results of the analysis with the help of functions such as clustering analysis of big data. Artificial intelligence technology aims to make decisions by transforming machines to simulate human processes. Artificial intelligence technology can use the results of big data analysis as input parameters for training machine learning algorithms, which can eventually output the results of decision-making. The specific model flow of decision-making is shown in Figure 3.^17,18

Figure 3.

Online information-based teaching model based on big data and artificial intelligence decision-making.

The online information-based teaching mode is more scientific and intelligent compared with the traditional teaching mode, leaving the decision-making to artificial intelligence, avoiding the one-size-fits-all teaching method of the traditional teaching method, paying more attention to students’ individual differences, and being able to promote students' skill development. This teaching mode has an important significance in improving students’ learning effect and promoting students' overall development.^19,20

Key Formulas of the information-based teaching model based on artificial intelligence and big data

T Key formula (1): Formula (1) is used to initially classify the initial data acquired by the IoT sensor.

G_{1} (S) = \frac{C_{1} (S)}{R_{1} (S)}

(1)

Formula (1) is used to initially categorize the raw data acquired by IoT sensors, where $G_{i}$ denotes the weight of a specific category of data, $C_{1}$ and $R_{1}$ are the eigenvalues and reference values of the category of data, respectively, which are derived by calculating the ratio of the two.

Key Formula (2): Formula (2) is used to combine different categories of data, and the combination uses the “with” operator to combine two categories of data together in a binary way.

G (S) = G_{1} (S) + G_{2} (S) = K_{1} T i n (S) + \frac{K_{2} L o u t (S)}{1 + T o u t (S) \cdot L o u t (S)}

(2)

Formula (2) is used to combine different types of data, using the “with” operator to merge binary data together, $G$ denotes the combined weight, $G_{1}$ and $G_{2}$ denote the weights of different categories of data, respectively, $K_{1}$ and $K_{2}$ are constants, and $T i n$ and Out are the time parameters and output parameters.

Key formula (3): Formula (3) shows that K1 and K2 are two modes of processing data, K1 is the formula dealing with behavioral information and K2 is the formula dealing with student learning effects.

K_{1} = D \cdot P \cdot L \cdot \frac{S t - E \cdot T e s t}{T}, K_{2} = \frac{1 + E \cdot T e s t - I t e m \cdot D}{S t \cdot L i n} + D \cdot L

(3)

Formula (3) $K_{1}$ and $K_{2}$ represent two kinds of data processing, $K_{1}$ for behavioral information, $K_2$ for students’ learning effect, and the specific calculation involves the parameters $D, P, L, S t, E, L out, T out, T out$ and T.

Key formula (4): Formula (4) is the way to make the final decision, and this formula is a model of unsupervised learning for machine learning. The results of the training can be derived by iterative training, and G is the training result of the data.

G (S) = \frac{K_{1} K_{2}}{K_{1} S^{3} + K_{2} S^{2} + S + 1}

(4)

Formula (4) is an unsupervised learning decision-making model with iterative training to arrive at the final result, $G$ denotes the result of the training data, $S$ is the dataset, and $K_{1}$ and $K_{2}$ may be the training parameters.

Application effect of the model

We also randomly selected 40 students in this middle school for the survey, and the results of the survey concluded that the information-based teaching model based on artificial intelligence and big data constructed by this model has good application effect and can significantly improve the learning effect of students, and the scores in students’ understanding and comprehension of knowledge are 91.358 and 88.369, respectively, which are higher than the experimental group and control group in the second part.

The information-based teaching mode based on AI and big data not only innovates teaching methods, but also profoundly affects educational concepts. In practice, it can customize personalized learning paths, adjust teaching strategies according to students’ learning behavior and achievement feedback, and improve learning efficiency. Theoretically, this model challenges the traditional one-size-fits-all approach to education, supports multiple intelligences theory and constructivism, and emphasizes active knowledge construction and situational learning. In addition, big data analytics can help identify potential problems in the education system, provide data support for decision-making, and promote educational equity.

Online informatization teaching mode

Improving the quality of information-based teaching resources

Improving the quality of information teaching resources should be approached from two perspectives. On the one hand, we should start from the supply of resources, and on the other hand, we should increase the utilization of resources. The poor quality of informatization teaching resources is a major bottleneck that restricts the development of informatization teaching. The relevant education departments should bear the burden of screening out excellent informatization education resources, developing standards for education informatization resources, screening and integrating existing digital resources, etc., to improve the utilization rate of resources and find high-quality teaching resources that are really useful to students. Some digital resources are so old that they have lost their because value, but people are used by many universities. This requires the education sector to increase the screening of information-based teaching resources and improve their quality assurance mechanisms. Improve the quality of information technology teaching Han Yingjia brigade innovation of information technology teaching resources. With the birth of the “Internet +” application concept, the application of information technology teaching resources has also changed. Informatization resources are now changing from teaching applications to learning applications, from teaching tools to teaching cores, from course delivery to overall student development, etc. The way information resources are used is the first step in the allocation of information-based education resources. The users of informatization teaching resources are not only limited to students and teachers, but also the majority of social workers. To promote the optimal allocation of resources, a professional informatization resource classification platform should be established to bring together the power of universities, enterprises, society and other platforms to meet the personalized learning needs of learners through technologies such as big data analysis and artificial intelligence.²¹

Improving teachers’ informatization literacy

With the development of information technology, the key factors that restrict information technology teaching in China have information technology turned into professional talents. With the pressure of teachers’ lectures and little preparation time, online teaching brings great challenges to teachers, especially for those who have not used online teaching. Therefore, improving teachers’ information technology literacy and information technology teaching ability is the key task of online information technology teaching at present. This requires college teachers to take the initiative to explore new teaching methods, adapt to informationized teaching and improve their ability to use informationized resources. According to the characteristics of information-based teaching, optimize the teaching process, improve the teaching content, and ensure that their classroom content meets the expected goals. At the same time, universities can also organize training activities to help teachers establish correct teaching concepts, overcome the shortcomings of online teaching, deeply integrate information technology with the classroom, and improve their own information-based teaching ability. On the other hand, improving online teaching technology guarantee is also an important step to promote teachers’ informatization literacy cultivation.

The development of online teaching technology is a key link in the process of educational informatization. It involves not only the iteration of technology itself, but also the reform of teacher training, curriculum design, policies and regulations. For example, the popularity of cloud computing and mobile internet makes learning possible anytime, anywhere, while blockchain technology provides new ideas for credit certification and lifelong learning archives management. To facilitate this development, interdisciplinary collaboration is needed, integrating educational resources, building an open and shared knowledge base, and sustained investment and policy support to ensure sustainable development and widespread adoption of technologies.

Promoting the innovation of informatization teaching mode

Online informatization teaching mode must take innovation as the first driving force of development, continuously improve itself in innovation, and lead the development direction of college teaching system with innovation. Combine college informatization teaching with artificial intelligence technology and big data technology, promote informatization teaching to be more efficient and intelligent, and provide students with personalized teaching solutions. School leaders, teachers, students, and must clearly understand the advantages and shortcomings of online teaching, seize the advantages of online teaching, promote the changes of online teaching, highlight the advantages of online teaching, and use artificial intelligence technology to make personalized decisions for the characteristics of different students.

Innovation is an important driving force for the development of education. In the rapidly changing information age, education systems must be constantly innovated to meet the needs of society. This includes innovations in teaching methods, such as flipped classrooms and project-based learning, as well as innovations in curriculum content, incorporating STEM education and critical thinking training. Technological innovations, such as AI-assisted instruction and intelligent learning management systems, are also hallmarks of educational modernization. By encouraging innovative spirit among teachers and students, education can cultivate a new generation of talents with problem-solving ability and strong adaptability, laying the foundation for sustained social and economic growth.

Conclusion

With the continuous progress of social information technology and economic development, various new technologies are popularized in daily life. Multimedia and other technologies are widely used in the teaching field, changing the traditional teaching mode. Our country has been affected by the new crown pneumonia epidemic since 2019, and some students are isolated at home and cannot attend classes offline. To solve this problem, China has launched large-scale online teaching and learning. Information-based teaching is a way to enhance student learning from the learning environment, which is influenced by many factors, including the classroom teaching scenario, teacher-student cooperation, and communication in the classroom. In the teaching process, the teaching mode has changed from the traditional teacher-teaching-student-learning fill-in-the-blank teaching to the independent acquisition of knowledge by students. In order to explore the status of online informatics teaching, we selected a university in city A as the research object to investigate the status of its online informatics philosophy department. At present, information technology teaching in China is still in a backward state. The current situation of information-based teaching in China is (1) the lack of information-based teaching resources and the lack of standardization in the use of resources. (2) Lack of awareness of online information teaching. In order to promote the level of online information-based learning of our schoolchildren from a comprehensive perspective, and in response to the drawbacks of online information-based teaching in China found in the above experimental survey, we propose an online information-based learning model based on big data and artificial intelligence decision-making to enhance students’ learning interest through an interesting learning model. After experimental verification, it can be concluded that our proposed model can significantly improve students’ behavioral performance and learning ability, and has a certain role in enhancing students’ learning effectiveness. Finally, we make recommendations based on the current state of application of big data and artificial intelligence in online informatics teaching. The recommendations are to improve the current situation of information-based teaching on the one hand to improve the quality of information-based resources, which requires the joint gate-keeping of the government, schools and teachers. On the other hand, the information technology literacy of teachers should be improved.

The article presents several key strengths and innovations that contribute to the discourse on online informatics teaching in the context of China’s educational landscape, particularly under the influence of the COVID-19 pandemic: (1) Relevance and Timeliness: The study addresses a critical issue in modern education—the transition to online teaching due to the pandemic. This is highly relevant given the global shift toward digital learning environments necessitated by health restrictions. (2)Empirical Investigation: By focusing on a specific university philosophy department in City A, the research provides empirical evidence on the current state of online informatics teaching. This localized approach offers insights into practical challenges faced by educators and students alike. (3) Identification of Shortcomings: The paper identifies two major issues hindering the effectiveness of online informatics teaching in China: the scarcity of standardized, high-quality resources and a lack of awareness regarding the potential of online information teaching. These findings pinpoint areas for improvement.

Footnotes

Funding

The author received no financial support for the research, authorship, and/or publication of this article.

Declaration of conflicting interests

The author declared no potential conflicts of interest with respect to the research, authorship, and/or publication of this article.

References

Boton

. Remote teaching of building information modeling during the COVID-19 pandemic: a case study. Sustainability 2020; 12(20): 8665.

Sun

Anbarasan

Kumar

. Design of online intelligent English teaching platform based on artificial intelligence techniques. Comput Intell-US 2021; 37(3): 1166–1180.

Liu

Wang

Teng

. Online teaching quality evaluation based on multi-granularity probabilistic linguistic term sets. J Intell Fuzzy Syst 2021; 40(5): 9915–9935.

Ting

. Chemistry course network teaching based on key information search and big data cloud platform. J Intell Fuzzy Syst 2021; 40(4): 7347–7358.

Bhimavarapu

. Analysing student performance for online education using the computational models. Universal Access Inf 2024; 23(3): 1051–1058.

Tang

, et al. An analysis model of learners' online learning status based on deep neural network and multi-dimensional information fusion. Comput Model Eng Sci 2023; 135(3): 2349–2371.

Miao

. Online and offline mixed intelligent teaching assistant mode of English based on mobile information system. Mob Inf Syst 2021; 2021: 7074629.

Chiu

Tsai

Liang

. Laypeople's online health information search strategies and use for health-related problems: cross-sectional survey. J Med Internet Res 2022; 24(9): e29609.

Arora

Sahi

Yates

. Will teachers continue to teach online post-COVID-19? Behav Inf Technol 2023; 42(8): 1110–1126.

10.

Jiang

. Analysis and optimization of the online vocal teaching system based on intelligent computing. Math Probl Eng 2022; 2022: 5320615–5320618.

11.

Wang

. Precision teaching model under online and offline hybrid learning environment. J Nonlinear Convex A 2023; 24(6): 1315–1325.

12.

Chen

Liu

, et al. Online robot teaching with natural human-robot interaction. IEEE Trans Ind Electron 2018; 65(12): 9571–9581.

13.

Wang

Zhan

. Optimized clustering model for interdisciplinary collaborative teaching information of physical education based on big data. Arch Clin Psychiat 2021; 48(1): 82–88.

14.

González-González

Infante-Moro

. Implementation of E-proctoring in online teaching: a study about motivational factors. Sustainability-Basel 2020; 12(8): 3488.

15.

Cui

Han

Zhu

. A novel online teaching effect evaluation model based on visual question answering. J Internet Technol 2022; 23(1): 91–98.

16.

Cao

Lin

, et al. Hybrid fake information containing strategy exploiting multi-dimensions data in online community. Mathematics-Basel 2022; 10(18): 3265.

17.

Wan

Wang

, et al. Intervening coupling diffusion of competitive information in online social networks. IEEE T Knowl Data En 2021; 33(6): 2548–2559.

18.

Qiu

Feng

. English online hybrid teaching based on internet-of-things information technology. Mob Inf Syst 2022; 2022: 3075225.

19.

Song

Wei

Shen

, et al. Evaluation of an online oral English teaching model using big data. Mob Inf Syst 2022; 2022: 7934575.

20.

Hou

. Application of dynamic process neural network model identification in ethnic dance online teaching system. Comput Intell Neurosci 2022; 2022: 2825530.

21.

Liang

Chai

Lee

VWY

. Surveying and modelling 21st century online learning patterns of medical students. Int J Environ Res Publ Health 2022; 19(19): 12648.