Teaching reform of dance major based on TPACK learning theory and AI classroom

Abstract

In response to the current dilemma of poor teaching efficiency in dance majors and limited application of subject teaching knowledge through integrated technology, a dance professional teaching method based on integrated technology subject teaching knowledge learning theory and artificial intelligence intelligent classroom is proposed. By integrating subject teaching knowledge of technology, an analysis of dance professional teaching is conducted, and a dance professional teaching framework is proposed. At the same time, human-computer system technology was introduced for the dual-teacher lecture mode of AI smart classroom teaching method. The validation of the teaching effect showed that the teacher-lecture score of the control group decreased by 4.73% on average compared to the experimental group. The post-class scores of the experimental group using the study of the proposed method increased by 3.17% compared to the control group. The difference in students’ course evaluation scores between the experimental and control groups was statistically significant (p < 0.05). The results indicate that the teaching method provides new ideas and methods for the teaching reform of dance majors. Integrating the theoretical knowledge of subject teaching with artificial intelligence intelligent classrooms can improve the efficiency and quality of dance teaching, and also enhance learning experience and satisfaction, which has important application value and practical significance in the field of art education.

Keywords

TPACK AI classroom dance education human-machine collaboration dual teacher mode teaching method

Introduction

As educational computing continues to evolve, the Theory of Technological Pedagogical Content Knowledge (TPACK) learning that integrates technology has emerged. The TPACK theory emphasizes the ability to integrate technology, teaching methods, and subject content in the teaching process, which is of great significance for improving teaching quality and students’ learning experience.^1,2 The TPACK theory provides a theoretical foundation and practical guidance for the effective integration of educational technology, which has received widespread attention and application in the education industry. However, in the teaching practice of certain professional fields, especially dance majors, their application still faces many challenges. Dance, as an art form of body language, has extremely high requirements for visual and motor accuracy in its teaching.³ Traditional teaching methods have been unable to satisfy the interactive needs of dance teaching, and there is an urgent need to explore new teaching models and methods. Artificial Intelligence (AI) combined with classroom teaching provides new ideas for dance education. AI classroom can achieve more real-time and personalized interaction between teachers and students through intelligent interactive tools.^4–6 Therefore, conducting research on dance professional teaching reform based on TPACK learning theory and AI classroom is conducive to promoting the application value and practical significance of intelligent teaching technology in art education.

The TPACK, proposed by Mishra and Koehler in 2006, has become a vital framework in the educational technology. Jiang et al. conducted a literature review and questionnaire survey to analyze the influencing factors of middle school teachers’ teaching to improve the TPACK level of preparatory biology teachers in modern intelligent basic teaching. Through comparison, it was found that the biological talent training program had promoting effects on improving the TPACK.⁷ Parwati et al. proposed an integrated application based on the TPACK framework and flipped classroom to enhance students’ understanding of mathematical concepts. Through the assistance of virtual laboratory media, students’ grades and comprehension abilities in mathematics learning were effectively improved.⁸ In order to clarify the knowledge required for teachers to integrate technology into educational practice in the context of information and communication technology in the 21st century, Ait Ali et al. proposed a TPACK framework. Through the review of empirical research journal articles in the database, the application of the TPACK in health vocational education was determined, and the positive guiding role of TPACK as a theoretical basis for educators’ future practice and research was emphasized.⁹ Max et al. conducted an analysis on teachers’ involvement in the Education Maker Space project through semi-structured interviews and questionnaire surveys in order to optimize their TPACK and attitudes towards the information technology in the classroom. During the project process, the TPACK, technology acceptance, intention, and motivation to use digital media of future teachers were improved.¹⁰

The application of AI in education is driving the development of intelligent classrooms, achieving significant changes in educational models, educational concepts, and teaching environments.¹¹ Nie et al. investigated the impact of Human-Machine Collaboration (HMC) on students’ cognitive load and learning emotions in intelligent classrooms by comparing different classroom discussion methods. Through classroom testing questionnaires and interview questionnaires, the test scores of participants were statistically analyzed. It was found that AI in intelligent classrooms always focused on the cognitive load of learners, minimizing their cognitive load as much as possible.¹² Kang et al. proposed an AI instructor Dancing Inside system based on 2D pose estimation method to address the challenges of teacher-student interaction in online dance learning. By collaborating with teachers and AI to provide timely feedback, learning outcomes and learners’ emotional experiences were enhanced.¹³ Cao proposed an innovative method that combined AI tools and M-learning platform to improve students’ learning outcomes in online dance learning. The Choreographic Creativity Rating Scale was used to evaluate students' dance achievements. Additional online extracurricular activities could enhance students’ physics skills, expressiveness, and creativity.¹⁴ To optimize the efficiency of teaching strategies for meta-cognition in collaborative dance creation, Buck-Pavlick proposed a theoretical framework based on critical teaching, intersectionality, and educational constructivism. Through dance writing and collaborative dance creation, students’ metacognitive ability and cognitive monitoring were enhanced in middle school dance classes, thereby achieving class community building, social emotional skills enhancement, and social awareness enhancement for students in AI and blended learning environments.¹⁵ Yağanoğlu et al. proposed the concept of an intelligent classroom that integrated information systems and innovative technologies in order to achieve real-time monitoring of environmental parameters in intelligent campus classrooms. By automatically improving physical conditions, it was expected to produce educational effects on students’ attention span and bring administrative convenience in ensuring safety and increasing savings, thereby achieving energy conservation.¹⁶

Based on the above, although TPACK has been widely applied in educational technology, its application still faces challenges in the teaching practice of dance majors. In addition, dance teaching requires extremely high accuracy in visual and motor skills, and traditional teaching methods are difficult to meet its interactive needs. Therefore, the study aims to reform dance teaching by utilizing TPACK learning theory and AI classroom, to enhance the efficiency and quality of dance teaching. By analyzing the current situation of dance teaching, an innovative dance teaching plan based on TPACK learning theory and AI classroom is designed. By applying the TPACK theory to the design of the AI classroom, it aims to solve the problems in the teaching of dance majors and improve the interactivity and learning effect of teaching. The AI classroom provides a new way of thinking for dance education by realizing more real-time and personalized interaction between teachers and students through intelligent interactive tools. Combined with the TPACK theory, the AI classroom can not only improve the teaching efficiency but also enhance the students’ learning experience and satisfaction, which has an important application value and practical significance in the field of art education. The goal of the study is to explore a new dance teaching mode by guiding the design of AI classroom through TPACK theory, with a view to realizing the deep integration of technology and teaching in dance professional teaching.

The overall structure of the research includes three parts. The first part designs a dance professional teaching strategy based on TPACK learning theory and AI classroom. Part three conducts experiments on the designed teaching strategies for dance majors. Part four summarizes the results and indicates research directions.

Methods and materials

Firstly, taking the course of Basic Dance Technique as an example, it analyzes the professional teaching of dance in combination with TPACK learning theory and proposes a professional teaching framework for dance. Secondly, the AI smart classroom for dance teaching was designed based on HMC technology, and the professional teaching strategy for dance was proposed in combination with TPACK learning theory.

Teaching framework for dance major based on TPACK learning theory

The TPACK learning theory was developed by Punya Mishra and Matthew J. Koehler in 2006 to explain and guide teachers on how to effectively integrate educational technology into their teaching. The TPACK framework is based on three core elements: Technological Knowledge (TK), Pedagogical Knowledge (PK), and Subject Content Knowledge (CK).^17,18 These three elements do not exist in isolation but interact to form four composite knowledge domains: Pedagogical Content Knowledge (PCK), Technological Content Knowledge (TCK), Technological Pedagogical Knowledge (TPK), Pedagogical Knowledge for Integrating Technology, and TPACK for Integrating Technology. The TPACK framework emphasizes that effective technology integration requires a deep understanding of the dynamic, interactive relationships between content, pedagogy, and technology, and that this understanding must be shaped within a particular pedagogical context. Therefore, in order to improve the efficiency of teaching dance majors, the study analyzes the current situation of teaching dance majors in terms of TK, PK as well as CK, teaching objects, and teaching objectives, using the Basic Dance Technique course as an example. Among them, dance professional TK mainly refers to all the techniques used by dance teachers in the teaching process, including traditional techniques and modern techniques. PK mainly refers to the teaching methods and knowledge used by dance teaching teachers during the teaching process. CK mainly refers to the understanding of dance related knowledge by the teaching staff. The specific content can be shown in Figure 1.

Figure 1.

Analysis of teaching and learning in the dance program.

In Figure 1, the teaching object, as the main role of learning, is the builder of meaningful knowledge. Therefore, the research mainly analyzes the general laws and characteristics of students’ physical and mental development, as well as their cognitive level when possessing relevant knowledge. The teaching objectives mainly include improving students' dance literacy, comprehensive artistic quality, cultivating correct posture, coordination, and flexibility, and enhancing students’ mastery of basic knowledge and skills in dance. In addition, from the perspective of context analysis, the context in dance professional teaching courses mainly refers to the teaching environment composed of teachers and students, including factors such as classroom teaching equipment, student learning situation, and teacher teaching level.^19,20 All factors work together and interact with each other to achieve a complete dance teaching activity. On this basis, further research has been conducted on the integration of dance professional teaching. Based on TK, PK, CK, teaching objects, teaching objectives, and contextual analysis, this study integrates four composite elements: TCK, TPK, PCK, and TPACK. Among them, TCK mainly signifies the knowledge of how to effectively integrate technology with specific subject content, and TPK value signifies the knowledge of how to effectively integrate technology with teaching methods. The specific framework is shown in Figure 2.

Figure 2.

A teaching framework for dance majors based on TPACK learning theory and AI classroom.

In Figure 2, the integration framework is mainly based on TPACK and AI classroom. Among them, TCK in the integration stage mainly presents the content knowledge of the “Basic Dance Techniques” course through teaching techniques. Throughout the teaching process, teachers can use AI classrooms and other means to enrich and deepen the presentation of dance knowledge, promoting students’ understanding of the knowledge representation. TPK mainly refers to teachers using technology to create or select suitable teaching methods for teaching in scenarios supported by AI technology. PCK mainly refers to the presentation of specific content knowledge using appropriate dance teaching methods. As the ultimate integration of dance teaching, TPACK is responsible for achieving mutual promotion of CK, PK, TK, etc., thereby promoting classroom interaction and improving the quality of dance teaching. The implementation stage of teaching is to test the environment for teaching design, while teaching evaluation is an auxiliary means to optimize teaching design.²¹ Therefore, the study combines qualitative and quantitative methods to evaluate the teaching design of dance majors, mainly including student evaluation, observer teacher evaluation, and teacher self-evaluation.²² Among them, the self-evaluation content of the teaching staff is shown in Figure 3.

Figure 3.

Guidelines for self-evaluation of teaching staff.

In Figure 3, the self-evaluation content of the teaching teacher is mainly evaluated from five dimensions: teaching philosophy, teaching content, teaching environment, teaching technology, and teaching methods. According to the corresponding content, it is divided into five evaluation levels: “completely consistent,” “consistent,” “average,” “not very consistent,” and “completely inconsistent.”²³ The study chose expert teachers with senior titles and rich teaching experience to conduct the evaluation, ensuring that the expert teachers had in-depth knowledge and research in the field of dance education. Evaluation of the teaching effect was carried out from the experience before, during and after the class, and detailed scoring criteria were formulated, including five aspects: teaching concept, teaching content, teaching environment, teaching technology, and teaching method. Arrangements were made for expert teachers to observe the classroom teaching of the experimental group and the control group on-site and record the teaching implementation, so as to carry out a comprehensive evaluation.

To ensure the objectivity of the evaluation, arrangements will be made for expert teachers to observe the classroom teaching of the experimental and control groups on site and to record the specifics of the teaching implementation. This includes the teacher’s instructional style, students’ response and participation, and the classroom atmosphere. Through these records, the expert teachers will be able to make a comprehensive assessment of the effectiveness of the teaching and make suggestions for improvement. In addition, a combination of quantitative and qualitative methods, including but not limited to questionnaires, interviews with students and teachers, and classroom observation records, will be used in the evaluation process to ensure that the evaluation results are multi-dimensional and in-depth. Through this comprehensive evaluation method, it will thus be possible to more accurately measure and improve the teaching quality of dance education.

Dance major teaching based on TPACK learning theory and AI classroom

According to the TACPK theory-based teaching framework for dance majors proposed in the previous text, the AI classroom is further developed. AI classroom integrates technologies such as motion capture and virtual reality to provide rich TK support for dance teaching. Teachers use data analytics and learning management systems to monitor and adjust teaching strategies in real time to meet individual learning needs. Meanwhile, the immersive environment of AI classroom enhances students’ understanding and mastery of dance technique, culture, and history, providing CK support. HMC can integrate teaching technology and instruction, improve teaching efficiency, and increase student attention.²⁴ Therefore, based on HMC technology, a dual teacher teaching mode for dance professional intelligent learning space is designed. The core concepts of HMC mainly include natural user interface, adaptive learning environment, and intelligent tutoring system. Among them, natural user interface mainly refers to allowing users to interact with the system in a natural way (e.g., voice and tactile feedback), while adaptive learning environment refers to dynamically adjusting the teaching content and difficulty according to students’ learning progress and comprehension. The intelligent tutoring system can provide personalized learning guidance and feedback to help students overcome learning barriers. The implementation steps of HMC in the AI smart classroom are shown in Figure 4.

Figure 4.

HMC implementation process in AI smart classroom.

In Figure 4, HMC technology supports students to construct knowledge through exploration and practice, for example, through simulation experiments and interactive discussions. By providing visual and auditory aids, the cognitive load on students is reduced, enabling them to focus more on deeper understanding of the learning material. At the same time, this study designs an AI classroom based on five principles: the role of technology in the learning process, the supportive role of integrating space in learning activities, the collaborative unity of the Community of Practice (CoP), the hierarchical integrity of teaching activities, and the process of students actively building knowledge. The specific element composition is shown in Figure 5.

Figure 5.

Architecture of AI classroom elements based on HMC.

From Figure 5, the main components of the AI classroom include “Human,” “Object,” “Vein,” “Work,” and “Boundary.” Among them, “Human” mainly refers to teachers, students, and AI teachers, while “Object” refers to teaching technology and educational environment resources. “Vein” mainly refers to the scenarios that need to be created in dance professional teaching. “Work” mainly refers to the two-way teaching behavior between teacher teaching and student learning. “Boundary” mainly refers to the entire dance professional teaching process. In addition, the AI classroom mainly includes four parts: physical space (dance classroom), interactive space, growth space, and virtual space (online platform). Among them, the dance classroom serves as the main space for teachers and students to conduct dance classroom teaching. The virtual space is mainly implemented by online platforms, which can record students’ learning situation throughout the entire process and accurately evaluate teaching effectiveness. The growth space is mainly a place for students to learn and connect independently, and AI is responsible for providing feedback on the effectiveness of student simulation training. The interactive space mainly refers to the interaction platform between teachers and students, students and students, and humans and AI. Due to the proposed AI classroom being a dual teacher teaching architecture based on HMC, it is necessary to divide the teaching between human teachers and AI teachers. The specific division of labor can be shown in Figure 6.

Figure 6.

Schematic of the division of labor between human and AI teachers.

In Figure 6, the study divides the teaching tasks between human teachers and AI teachers in three stages: before the start of the dance course, during the teaching process, and after the end of the course. The human teacher is responsible for designing the entire teaching process and planning teaching tasks before class, while the AI teacher mainly conducts portrait analysis of students and constructs professional knowledge and training guidance architecture for dance before class. During the teaching process, the teaching is conducted in a mode where human teachers are the main participants and AI teachers are the auxiliary ones. After the lecture, human teachers evaluate and optimize the teaching, and formulate plans for students’ subsequent learning. AI teachers mainly visualize the learning process of students and guide their self-learning. Combining the above, the dance professional teaching model based on TPACK learning theory and AI classroom can be shown in Figure 7.

Figure 7.

A model for teaching dance majors based on TPACK learning theory and AI classroom.

From Figure 7, the dance professional teaching model proposed in the study integrates spatial, technological, and TPACK teaching elements, and combines the teaching teacher, AI teacher, and students into a CoP. The dance professional course teaching is carried out through the teaching process before, during, and after class. All teaching participants with CoP participate in teaching activities guided by dance teaching objectives. Among them, teaching elements mainly include five elements: CoP, learning activities, scenario construction, intelligent management, and interconnectivity. The entire teaching design process mainly revolves around the TPACK teaching theory and combines it with AI courses for teaching.

Results

To prove the dance professional teaching method on the basis of TPACK learning theory and AI classroom proposed in the research, a dance professional teaching experiment application is first carried out. The teaching effect is analyzed from the self-evaluation of the teaching teacher and the expert learning score. Secondly, the dance performance and course satisfaction evaluation of students after the experiment are evaluated.

Experimental design for teaching application in dance major

In order to verify the effectiveness of the dance teaching method based on TPACK learning theory and AI classroom proposed in the study, two classes of dance majors in a certain university are used as experimental and control groups for teaching practice. Among them, the experimental group uses the proposed teaching method for teaching, while the control group uses the traditional teaching method. Both the experimental group and the control group consist of 34 students. The pre-test scores of dance professional knowledge for the two groups before conducting the experiment are presented in Table 1.

Table 1.

Comparison of the performance of the experimental and control groups.

Group	Number of cases	Average value	Standard deviation	95% confidence interval		Minimum value	Maximum values	Sig.
Group	Number of cases	Average value	Standard deviation	Lower limit	Higher limit	Minimum value	Maximum values	Sig.
Test	34	85.17	6.67	86.91	91.42	68.00	100.00	0.31
Control	34	85.62	8.73	85.71	91.53	58.00	100.00	0.31

From Table 1, the Sig value between the two sets of data was 0.31, indicating that no significant difference existed between the two sets of data (p > 0.05). It also indicates that the dance professional knowledge levels of the two groups are similar, and the data follows a normal distribution. The study set a semester (approximately 4 months) as the experimental cycle to fully assess the impact of the teaching methods on student learning outcomes. The experiment was divided into three phases: pre-class preparation (2 weeks), in-class implementation (12 weeks), and post-class evaluation (2 weeks). The experimental group’s pre-course preparation included the following: installing and testing the hardware and software required for the AI Smart Classroom, including the motion capture system, virtual reality device, and learning management system; providing technical training to the experimental group’s students to ensure their familiarity with the operation of the AI Smart Classroom; and designing personalized learning paths and adjusting the instructional content and difficulty based on the students’ pre-test results. The control group’s course preparation included the following: maintaining the traditional dance teaching environment without introducing the AI Smart Classroom technology; and conventional dance teaching training.

During the in-class implementation phase, the experimental group used motion capture technology to record students’ dance movements in real time and provide instant feedback through AI analysis; virtual reality technology was used to simulate different dance scenarios to enhance students’ immersion and learning experience; and teachers tracked students’ learning progress and performance through the learning management system to adjust teaching strategies in real time. At the same time, a dual-teacher model was implemented, with human teachers responsible for instructional design and guidance, and AI teachers providing personalized feedback and coaching. The control group adopts traditional face-to-face teaching methods and uses traditional teaching tools and methods. Human teachers were responsible for all teaching activities, including demonstration, guidance, and feedback.

The post-course evaluation stage focuses on teaching evaluation in terms of learning outcome assessment, technology effect assessment, and teaching method optimization. In addition, the study utilizes the Student Learning Satisfaction Scale to measure the teaching effectiveness. Satisfaction of the students in the experimental and control groups with the dance teaching program was investigated as a validation of the effectiveness of the proposed methodology. The survey content of this scale is displayed in Table 2.

Table 2.

Content distribution of the student learning satisfaction scale.

Dimension		Instruction	Question number
B1	Technology acceptance	The perceived ease of use and perceived usefulness of various intelligent technologies and equipment in the space	7
B2	Interaction process	The interaction of students with other people, technology, equipment, and environment during the learning process	6
B3	Space environment	The comfort level of the physical environment in the intelligent learning space	3
B4	Learning experience	The overall learning experience and feelings during the learning process	5
B5	Teaching model satisfaction	The feelings and satisfaction with the teaching model	4

According to the scale shown in Table 2, a satisfaction survey questionnaire for dance professional teaching is designed. The questionnaire mainly consists of six parts, namely, “Student Personal Information Collection,” “Technology Acceptance Level,” “Interaction Process,” “Student’s Perception of AI Classroom Space Environment,” “Subjective Experience of Student Learning Process,” and “Satisfaction with Teaching Mode.” At the same time, the questionnaire is developed using the Likert five point scale, which includes options such as “strongly agree,” “agree,” “uncertain,” “disagree,” and “strongly disagree,” with corresponding scores of 5, 4, 3, 2, and 1 points.²⁵

Teacher self-evaluation and professional teacher evaluation

Firstly, the study conducts self-evaluation of the teaching staff. According to the self-evaluation criteria of the teaching staff, the teaching effectiveness is evaluated based on the experiences before, during, and after class. The scoring results in three stages are shown in Figure 8.

Figure 8.

Comparison of teachers’ self-evaluation in the two groups. (a) Pre-course instructor self-evaluation. (b) Self-evaluation by the instructor of the lesson. (c) Post-course instructor self-evaluation.

From the self-evaluation scores in Figure 8(a), there was little difference in the self-evaluation results of the teaching teachers in the teaching philosophy (A1) and teaching technology (A4). From the evaluation scores of the two teaching methods (A5), the experimental group increased by 8.89% compared with the control group. This indicates that incorporating TAPCK theory and AI classrooms can improve teachers’ teaching methods, promote effective knowledge transfer among students, and enhance their ability to solve dance-related problems. From the in class stage in Figure 8(b) and the after class stage in Figure 8(c), the self-evaluation scores of the experimental group teachers significantly improved. The proposed method can improve the teaching level of teachers and enhance their self-affirmation, thereby promoting students’ learning efficiency and increasing their interest in learning. At the same time, three expert teachers are selected to rate the teaching content, respectively, mainly based on the five dimensions of self-evaluation by the teaching teachers, and then calculate the average value. The results are shown in Figure 9.

Figure 9.

Comparison of expert rating results. (a) Results of control group teaching scores. (b) Results of test group teaching scores.

From Figure 9(a), the average teaching scores of the control group in the five dimensions were 92.67, 94.67, 95.33, 93.33, and 92.67, respectively, with a total mean of 93.73 points. Compared with the scores of the experimental group in Figure 8(b), the average scores of the control group in the five dimensions decreased by 5.12%, 3.72%, 2.72%, 5.08%, and 7.02%, respectively. The control group scored the highest in the dimension of teaching, which may be due to the teachers’ rich experience in the design process of teaching. From Figure 9(b), the highest scores were obtained in terms of teaching content and teaching methods. The teaching method based on TAPCK theory can integrate TK, PK, and CK into one, which not only provides teachers with a clear teaching path but also promotes teachers’ understanding of the integration of technology into teaching. When combined with AI classroom, the proposed dance teaching method has obvious advantages in teaching technology. Comparing the score differences between the two groups in five dimensions, the experimental group shows the most significant increase in scores in teaching content, teaching technology, and teaching methods. The teaching method can promote the presentation of dance courses in teaching content, help students enrich and deepen dance teaching content, understand dance knowledge, and improve teaching efficiency.

Student evaluation

To further demonstrate the effectiveness of dance teaching methods on the basis of TPACK learning theory and AI classroom, the study further investigates the teaching effects of two groups. Firstly, the dance major scores are compared after teaching, as presented in Table 3.

Table 3.

Comparison of dance major scores after teaching in two groups.

Group	Number of cases	Average value	Standard deviation	Sig.
Test	34	92.00	6.28	0.005
Control	34	89.17	7.81	0.005

From Table 2, after teaching dance courses, the average score of the control group was 89.17 points, and the average score of the experimental group was 92.00 points. Both Sig (Bilateral) was 0.005, and the difference was significant. In comparison with the control group, the average score of the experimental group increased by 3.17%. This indicates that the dance teaching method based on TAPCK learning theory and AI classroom can improve students’ learning efficiency and promote their understanding of dance professional knowledge. On this basis, the study further analyzes the scores of the Student Learning Satisfaction Scale, as shown in Figure 9.

From the satisfaction evaluation results of the control group students in Figure 10(a) and the experimental group in Figure 10(b), the student satisfaction score under the dance teaching method proposed in the study outperformed the control group. In comparison with the control group, the experimental group increased its average scores in technology acceptance (B1) by 14.74%, interaction process (B2) by 17.86%, spatial environment (B3) by 27.73%, learning experience (B4) by 18.01%, and teaching mode satisfaction (B5) by 22.47%. Combining Figure 9(a) and (b), the proposed dance teaching method had the most significant optimization effect in the B3 and B5 dimensions. This indicates that the AI classroom based on HMC has optimized the spatial environment of dance professional teaching and improved the learning atmosphere of dance professional teaching. The dance professional teaching framework based on TPACK learning theory has a positive impact on teachers’ teaching techniques and methods. The t-test results are displayed in Figure 11.

Figure 10.

Student satisfaction scores for control and test groups. (a) Scoring results for students in the control group. (b) Scoring results for students in the test group.

Figure 11.

Control and test group student scores t-test.

From Figure 11, there were significant differences in the two groups in all five dimensions (p > 0.05). This indicates that after applying the dance professional teaching method based on TPACK learning theory and AI classroom, there is a significant difference in the teaching effect between the experimental group and the control group in terms of students’ experience and satisfaction with the entire learning process. After applying the dance teaching method proposed in the research, students' acceptance of teaching techniques (B1) significantly increased. This indicates that the application of TPACK learning theory and AI classroom can optimize teaching forms, stimulate students’ learning motivation, and achieve interactive feelings in the learning process.

Conclusion

A dance professional teaching strategy based on TPACK learning theory and AI classroom was proposed to address the shortcomings of traditional teaching methods in interactivity and learning effectiveness. By designing a teaching framework based on TPACK theory and an AI classroom based on HMC technology, a dual teacher teaching mode was constructed to integrate teaching technology and instruction. The new teaching method improved the teaching level and effectiveness of teachers. Compared with the expert scores of the experimental group, the average scores of the control group in the five dimensions decreased by 5.12%, 3.72%, 2.72%, 5.08%, and 7.02%, respectively. The average score of dance knowledge among the experimental group students increased by 3.17% in comparison with the control group. The experimental group showed obviously better performance in dance major and student satisfaction than the control group. The dance teaching method based on TPACK learning theory and AI classroom can effectively improve students’ learning efficiency and satisfaction, and has positive reform significance for dance teaching. However, despite the positive results of the research, the cost-benefits arising from the implementation of the new teaching methodology have been neglected. This is of crucial importance for the adoption of the method in higher education or vocational institutions. Therefore, the study will be conducted in the future to optimize and analyze the proposed method in terms of long-term follow-up observations and cost of economic benefits. At the same time, consideration will be given to exploring the application of more intelligent technological tools in dance teaching in order to further optimize teaching strategies and improve teaching effectiveness.

Footnotes

Declaration of conflicting interests

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

Funding

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

References

Thohir

Jumadi

Warsono

. Technological pedagogical content knowledge (TPACK) of pre-service science teachers: A Delphi study. J Res Technol Educ 2022; 54(1): 127–142.

Bueno

Niess

Engin

, et al. Technological pedagogical content knowledge: Exploring new perspectives. Australas J Educ Technol 2023; 39(1): 88–105.

Smith

Cross

. The McNorm library: creating and validating a new library of emotionally expressive whole body dance movements. Psychol Res 2023; 87(2): 484–508.

Groumpos

. A critical historic overview of artificial intelligence: issues, challenges, opportunities, and threats. Artif Intell Appl 2023; 1(4): 197–213.

Ahmad

Sri

. Conceptual design impacts in new normal era: The use of Artificial Intelligence (AI) and Internet of Things (IOT) (Case studies: class room and restaurant). Acta Informatica Malaysia 2022; 6(2): 39–42.

Valenzuela

Garcia

Bawica

, et al. Adoption of Artificial Intelligence in the Philippine hotel and leisure industry: An assessment. Acta inform Malays 2023; 7(1): 24–28.

Jiang

Zuo

, et al. Analysis of intelligent teaching ability of pre-service biology teachers based on TPACK theory. J Electr Syst 2024; 20(3): 2263–2270.

Parwati

Suharta

IGP

Sudatha

IGW

. TPACK theoretical correspondence with learning variables and its application effectiveness in learning. Journal of Pedagogy and Education Science 2023; 2(3): 244–256.

Ait Ali

El Meniari

El Filali

, et al. Empirical research on technological pedagogical content knowledge (TPACK) framework in health professions education: A literature review. Med Sci Educ 2023; 33(3): 791–803.

10.

Max

Lukas

Weitzel

. The pedagogical makerspace: Learning opportunity and challenge for prospective teachers’ growth of TPACK. Br J Educ Technol 2024; 55(1): 208–230.

11.

Mustafa

. Smart classrooms, bright minds: The intersection of education and artificial intelligence. Journal Environmental Sciences and Technology 2023; 2(1): 150–158.

12.

Nie

Yuan

Chao

, et al. In smart classroom: Investigating the relationship between human–computer interaction, cognitive load and academic emotion. Int J Hum Comput Interact 2024; 40(13): 3528–3538.

13.

Kang

Yoon

, et al. Dancing on the inside: A qualitative study on online dance learning with teacher-AI cooperation. Educ Inf Technol 2023; 28(9): 12111–12141.

14.

Cao

. Case study of China’s compulsory education system: AI apps and extracurricular dance learning. Int J Hum Comput Interact 2024; 40(13): 3419–3426.

15.

Buck-Pavlick

. Empowering metacognition through dance writing and collaborative dance making. J Dance Educ 2024; 24(2): 125–135.

16.

Yağanoğlu

Bozkurt

Günay

, et al. Design and validation of IoT based smart classroom. Multimed Tool Appl 2024; 83(22): 62019–62043.

17.

Dikmen

Demirer

. The role of technological pedagogical content knowledge and social cognitive variables in teachers’ technology integration behaviors. Participatory Educational Research 2022; 9(2): 398–415.

18.

Hanik

Puspitasari

Safitri

, et al. Integrasi Pendekatan tpack (technological, pedagogical, content knowledge) guru sekolah dasar sikl dalam melaksanakan pembelajaran era digital. JEID: J Educ Int Dev 2022; 2(1): 15–27.

19.

. Analysis of education model for university students’ psychological fitness using machine learning under the environment of virtual reality. Comput Aided Des Appl 2023; 1(1): 102–117.

20.

Hulusic

Gusia

Luci

, et al. Tangible user interfaces for enhancing user experience of virtual reality cultural heritage applications for utilization in educational environment. J Comput Cult Herit 2023; 16(2): 1–24.

21.

Syarnubi

Syarifuddin

Sukirman

. Curriculum design for the Islamic religious education study program in the era of the Industrial Revolution 4.0. Al-Ishlah: Jurnal Pendidikan 2023; 15(4): 6333–6341.

22.

Liberman

Dubovi

. The effect of the modality principle to support learning with virtual reality: An eye‐tracking and electrodermal activity study. J Comput Assist Learn 2023; 39(2): 547–557.

23.

El-Hamamsy

Monnier

Avry

, et al. An adapted cascade model to scale primary school digital education curricular reforms and teacher professional development programs. Educ Inf Technol 2024; 29(9): 10391–10436.

24.

Wang

. Multimedia teaching mode in colleges and universities based on psychology-based human-computer interaction interface design. Int J Hum Comput Interact 2024; 40(13): 3507–3515.

25.

Zhou

, et al. Evaluation of teachers’ information literacy based on information of behavioral data in online learning and teaching platforms: an empirical study of China. Libr Hi Technol 2023; 41(4): 1039–1062.