Abstract
This work aims to investigate the application of advanced deep learning algorithms and image recognition technologies to enhance language analysis tools in secondary education, with the goal of providing educators with more effective resources and support. Based on artificial intelligence, this work integrates data mining techniques related to deep learning to analyze and study language behavior in secondary school education. Initially, a framework for analyzing language behavior in secondary school education is constructed. This involves evaluating the current state of language behavior, establishing a framework based on evaluation comments, and defining indicators for analyzing language behavior in online secondary school education. Subsequently, data mining technology and image and character recognition technology are employed to conduct data mining for online courses in secondary schools, encompassing the processing of teaching video images and character recognition. Finally, an experiment is designed to validate the proposed framework for analyzing language behavior in secondary school education. The results indicate specific differences among the grouped evaluation scores for each analysis indicator. The significance p values for the online classroom discourse’s speaking rate, speech intelligibility, average sentence length, and content similarity are −0.56, −0.71, −0.71, and −0.74, respectively. The aim is to identify the most effective teaching behaviors for learners and enhance the support for online course instruction.
Similar content being viewed by others
Introduction
The swift evolution of artificial intelligence (AI) technology has garnered considerable attention for its application in secondary education. Notably, language analysis technology, an integral facet of AI, holds substantial promise within the realm of secondary education. This study seeks to assess the efficacy of AI-based language analysis technology in secondary education, aiming to furnish a scientific foundation for educational reform. Technological innovations are resha** secondary education as online education gains popularity and evolves. Language analysis technology, leveraging techniques like natural language processing and text analysis, can delve into students’ linguistic expressions during the learning process, thereby equip** educators with a more comprehensive understanding of students’ learning dynamics. Through AI, a nuanced analysis of students’ language proficiency, expression patterns, and related aspects becomes feasible, offering precise guidance for personalized teaching and subject-specific tutoring.
In the online environment, teaching behavior can significantly impact learners’ experiences and learning outcomes. Therefore, as a crucial dimension of teaching practice, teaching behavior plays a pivotal role in influencing the effectiveness of instruction. Studying this controlling mechanism can help promote online courses and facilitate more efficient student learning1. Some scholars have found a significant correlation between teaching behavior and academic emotion, arguing that teaching behavior can alleviate students’ negative emotions online, such as anxiety and loneliness2. Conversely, online teaching behavior serves as a direct expression of educators’ teaching abilities and comprehensive skills. Educators must reflect on their teaching behaviors to enhance the effectiveness of online instruction. Therefore, the foundation for building high-quality online courses should begin with the online Teaching Behavior Analysis (TBA)3.
Based on the media used by educators, teaching behaviors can be categorized into verbal and non-verbal behaviors. Notably, classroom discourse is fundamental for student–teacher communication, constituting approximately 80% of all teaching behaviors4. Makarenko, a renowned educator in the former Soviet Union, emphasized that, under the same teaching model, different classroom discourses might lead to a 200-fold difference in teaching effectiveness, underscoring the importance of classroom discourse5. Additionally, classroom discourse, a crucial component of educators’ teaching behavior, serves as a key indicator in evaluating the quality of online courses6. Therefore, focusing on online TBA and leveraging big data technologies to mine its characteristics and patterns holds great significance for enhancing the teaching quality and learning outcomes of online courses7.
The innovative development of online course-supportive big data platforms and related data processing technologies has become a new research focus. Understanding how classroom discourse influences the learning experience and teaching effectiveness is essential to improve online educators’ essential teaching skills. To this end, this work introduces big data mining technology to explore educators’ teaching characteristics and behaviors that affect the quality of online courses. It analyzes the teaching objectives, evaluates online educators’ experiences, and explores online TBA methods. Based on the research findings, implications are suggested for enhancing online educators’ teaching skills. The research results provide an essential reference and basis for improving the online learning experience and teaching effectiveness.
Literature review
The online course-oriented data mining technology based on AI targets the unique data collected from the teaching environment, teaching objects, and teaching process in online courses. It focuses on big data in online courses, which falls into the main category of educational big data research and application Descriptive statistics of grouped evaluation of different classroom discourse comprehensive scores.
In the grouped online course evaluation, speech intelligibility is rated as “excellent” (97.9 points), “middle” (91.1 points), and “poor” (81 points). Speaking rate is rated as “fast” (93 points), “middle” (90 points), and “slow” (84 points). In comparison, content similarity is rated as “low” (93 points), “middle” (91.4 points), and “high” (82.8 points). Average sentence length is rated as “short” (93.2 points), “medium” (90.6 points), and “long” (77.8 points). The evaluation scores for different groups of indicators vary.
Analysis of variance
Figure 4 conducts an analysis of variance (ANOVA) to explore whether there are statistical differences in the classroom discourse evaluation scores of the four indicators between different groups.
ANOVA of comprehensive scores of classroom discourse evaluation in different groups.
In the ANOVA of the speech intelligibility dimension, F = 11.8 and p = 0.0009. In the ANOVA of the speaking rate, F = 2.67, and p = 0.093. In the ANOVA of the content similarity, F = 4.65, and p = 0.045. In the ANOVA of the average sentence length, F = 11.83, and p = 0.0008. The results indicate that the comprehensive scores of grouped evaluations among different indicators exhibit varying significance.
Correlation analysis of the online classroom discourse indicators and course evaluation in secondary schools
Figure 5 illustrates the correlation analysis results between online classroom discourse indicators and comprehensive course evaluation scores in secondary schools.
Correlation analysis between classroom discourse indicators and comprehensive scores of course evaluation.
In Fig. 5, a significant negative correlation is observed between speech intelligibility and the comprehensive score of online course evaluation, with a correlation coefficient of −0.71. The speaking rate is significantly negatively correlated with the comprehensive online course evaluation score, with a correlation coefficient of −0.56. The content similarity of classroom discourse is significantly negatively correlated with the comprehensive course evaluation score, showing a correlation coefficient of −0.74. The average sentence length of classroom discourse is significantly negatively correlated with the comprehensive online course evaluation score, with a correlation coefficient of −0.71.
Regression analysis of classroom discourse indicators in secondary school online education on course evaluation
Figure 6 presents the results of stepwise multiple regression analysis examining the impact of classroom discourse indicators on learners’ course evaluation.
Results of stepwise multiple regression analysis of the impact of classroom discourse indicators on comprehensive course evaluation.
In Fig. 6, the model fitting equation is y = −24.74 (similarity) −4.64 (sentence length) + 127.44. The model fitting determination coefficient R2 = 0.78, the adjustment coefficient R2 = 0.76, and the model fitting and coefficient are highly significant. Among these, similarity emerges as the strongest explanatory variable, explaining the majority of the variation in the comprehensive course score, while sentence length contributes to a smaller portion of the variation in the comprehensive course score.
Discussion
The experimental outcomes of this work demonstrate significant applications of deep learning and image recognition technologies in secondary education. Utilizing these advanced technologies enables a more comprehensive and objective assessment of online verbal communication among secondary school students, which is crucial for identifying and addressing teaching issues. Educators can practically use these results to promptly recognize and rectify communication challenges, thereby enhancing students’ positive experiences in online education. A key finding of this study is the understanding of the relationship between various verbal communication indicators and course evaluations, laying a theoretical foundation for personalized teaching support. This allows educators to adapt teaching methods flexibly based on students’ learning styles and needs, improving teaching’s specificity and effectiveness. Educators can better meet personalized learning needs through targeted teaching strategies, enhancing education’s overall effectiveness.
In practical applications, this work provides crucial data support for educational decision-makers, empowering them to make informed policy decisions and implement measures to enhance online course quality and effectiveness. It is recommended that educational decision-makers establish decision frameworks based on empirical data to drive improvements in the entire education system. Based on this, managerial recommendations include suggesting educational institutions incorporate deep learning and image recognition technologies into online education assessments to comprehensively understand teaching quality and student experiences. Educators can devise targeted teaching improvement strategies by identifying key verbal communication indicators, such as adjusting speech speed or enhancing speech comprehensibility, to elevate students’ learning experiences. Personalized learning experiences, especially in aspects like speech speed and content similarity, will aid students in better assimilating into the online learning environment, aligning more closely with subject interests and learning styles. Ultimately, this contributes to refining individual educators’ teaching methods and provides valuable insights for the entire education system’s development. In formulating online education policies, it is recommended that educational decision-makers fully leverage research results to promote evidence-based development. Understanding the relationship between verbal communication indicators and comprehensive course evaluations allows policymakers to precisely guide the direction of online education development, fostering overall improvements in educational standards. Emphasizing data-driven decision-making in the policy formulation process ensures the effectiveness and sustainability of policies, hel** translate research findings into practical educational reforms and policy implementations.
Conclusion
The implementation of the online “Gold Course Construction” plan initiated by the Ministry of Education, aimed at develo** first-class online courses, is considered a crucial strategy for enhancing the quality of higher education in China, particularly in terms of talent training. Consequently, there has been a significant rise in the analysis and research on classroom discourse. This work builds upon previous research and utilizes AI to effectively mine and analyze teaching behaviors, specifically focusing on classroom discourse in online courses at the secondary school level. The primary emphasis is on constructing a CDA framework for online secondary school courses, providing the foundation for a dataset in subsequent experiments by integrating AI-driven data mining technology. The experimental findings highlight content similarity and average sentence length as the most influential indicators of classroom discourse, both falling under the strategic features category. Among these, content similarity is pivotal in learners’ online learning compared to average sentence length. It is essential to note that this work currently tests the effectiveness of CDA on only three types of English and Chinese courses in secondary schools. Future efforts will involve designing experiments to investigate whether similar characteristics and patterns exist in the classroom discourse of other disciplines. The ultimate goal is to offer methods and references for educators to enhance classroom discourse and strengthen teaching effectiveness.
