Introduction

We are currently living in the era of the Fourth Industrial Revolution. With the rapid advancement of digital technologies such as artificial intelligence, big data, and the Internet of Things, fundamental innovations have occurred in various fields, leading to extensive changes throughout society. Education in schools is no exception. There is a growing trend of actively integrating these cutting-edge technologies into classrooms. Furthermore, with the widespread adoption of online education and remote learning due to the COVID-19 pandemic that began in 2020, there has been increased interest in utilizing various educational technologies (Edu-tech) for teaching and learning. The development of technology plays a catalytic role in changing the paradigm of the education system, and we are entering an era of a major transformation in education. In recent years, there have been various movements reflecting the current trends in English education in South Korea. In an English as a Foreign Language (EFL) environment like ours, students have very limited opportunities to use English in their daily lives. Therefore, it is important to maximize students’ speaking opportunities within the regular curriculum time to enable them to naturally acquire English. However, it is currently challenging to achieve this in Korean classrooms. Students only have 2 h per week (for grades 3–4) or 3 h per week (for grades 5–6) dedicated to learning English, which is insufficient for practice. Additionally, with an average class size of 23 students (OECD, 2019), it becomes difficult to provide appropriate feedback for individual speaking practice. Furthermore, there is a wide range of English proficiency levels among students in the classroom. However, assignments are uniformly provided, making it too easy for proficient students to practice the target language in the textbook, resulting in a lack of motivation to participate in the learning process. On the other hand, struggling students find it too difficult to even speak the target language and therefore refrain from verbal participation. Therefore, teachers need to explore the use of various Edu-tech tools in line with the current trends to address these issues and provide personalized lessons tailored to students’ levels, while offering effective feedback.

With the recent advancements in machine learning and deep learning, which are key technologies in artificial intelligence, learners now have access to various English programs. Artificial intelligence technologies are considered as alternatives to overcome the physical limitations of the EFL education environment, and there is a growing interest in the potential use of AI chatbots. Various interactive AI English education programs have been developed, and attempts are being made to integrate them into school education. Due to the high interest in AI chatbots, diverse research studies on AI chatbots in English education, both domestic and international, are underway. These studies include analyses of the characteristics of AI chatbots (Coniam D, 2014; Kim et al., 2022; Haristiani N, 2019; Huang et al., 2019; Kılıçkaya F, 2020; Dokukina I and Gumanova J, 2020; Pérez JQ et al., 2020; Yin Q and Satar M, 2020; Yoon and Park, 2020), research on developing AI chatbots (Mondal et al., 2018; Lee, 2018; Muhammad AF et al., 2020; Sung, 2022), and research on the use of AI chatbots in teaching and learning in school settings (Gayathri AN and Rajendran VV, 2021; Lin CJ and Mubarok H, 2021; Jeon, 2022; Yoo, 2021; Wu, 2022; Yang J, 2022; Mendoza S et al., 2022; Abidin et al., 2022). Although many research results have emerged, particularly in 2021, regarding the use of AI chatbots in teaching and learning in school settings, there is still a significant lack of related research. This is because there have not been many cases of utilizing AI chatbots in school settings, and research on the role of teachers and principles of lesson design in AI chatbot-assisted classes has been insufficient. In particular, it has been challenging to find research targeting elementary school students, likely due to their lower vocabulary level and limited proficiency in using diverse sentence structures, as the regular English curriculum is introduced from the third grade of elementary school in South Korea. However, it is expected that developing and implementing AI chatbots that incorporate vocabulary levels and sentence structures suitable for elementary English education, while stimulating learners’ interest, would yield significant effects (Kim and Lee, 2020; Chu and Min, 2019; Xia Q et al., 2023). Therefore, there is a strong demand for research on developing AI chatbots for use in elementary English classes and the principles of lesson design for AI chatbot-assisted classes.

The aim of this study is to develop principles for designing elementary English speaking lessons using AI chatbots and validate their effectiveness. Through this research, the developed principles for designing elementary English speaking lessons using AI chatbots will guide teachers in effectively incorporating AI chatbots into their English classes at the elementary school level, enabling students to achieve cognitive and affective goals in the English subject. In other words, the objective of this study is to develop design principles that guide the instructional design of elementary English speaking lessons using AI chatbots from an educational technology perspective. The specific research questions set to achieve these objectives are as follows:

  1. 1.

    What are the principles for designing elementary English speaking lessons using AI chatbots?

  2. 2.

    Are the principles for designing elementary English speaking lessons using AI chatbots valid?

Theoretical background

Elementary English curriculum in South Korea

In Korean elementary schools, English education was introduced as a new subject in the 6th national curriculum (1992–1997) and became an official subject in 1997. Since the 7th national curriculum (1997–2007) until the present, the overarching goal of the English curriculum has been to enhance English communication skills. In the revised curriculum announced by the Ministry of Education in December 2022, fostering communicative competence was presented as the comprehensive core competency of the English subject. It explicitly stated the intention to maximize the efficiency of learning by utilizing various media, information and communication technologies in line with the digital and AI educational environment in order to adapt to the changing times (Ministry of Education, 2022, p.6).

There is increasing interest among researchers in exploring teaching methods that provide learners in the EFL context, such as in South Korea, with opportunities to understand discourse or writing and express their own thoughts and emotions. One of the prominent approaches is Communicative Language Teaching (CLT), which has been widely utilized (Richards, 2005). Within the CLT framework, various teaching methods have emerged, including the Natural Approach, Content-Based Instruction, and Task-Based Learning. Among them, Task-Based Learning has garnered significant attention from domestic researchers, particularly since Prabhu (1987) first proposed it in 1987. Task-Based Learning involves providing tasks that allow learners to naturally acquire and use the language while performing the tasks. Learners engage in interaction with their peers during task performance, using and acquiring the target language more efficiently (Nunan, 1999). In this study, we aim to develop principles for designing elementary English speaking lessons using AI chatbots, with a focus on Task-Based Learning as the underlying teaching approach.

A study on the use of chatbots in English education

Since 2019, there has been active research both domestically and internationally on the potential of using AI chatbots in foreign language education. These studies have primarily focused on examining the effects of using chatbots in English classes, particularly in terms of cognitive and affective aspects. Many studies have investigated the effects of chatbots on speaking skills, and most of them have shown statistically significant positive effects. Specifically, AI chatbots have been found to increase learners’ exposure to English language environments, provide more opportunities for English language use, and enhance their communication abilities (Yang, 2022). Learners have also benefited from immediate and effective spelling and grammar feedback from AI chatbots, leading to improved fluency (Haristiani, 2019), and the authenticity and accuracy of the English provided by chatbots have been effective in enhancing learners’ conversational skills (El Shazly, 2021; Muhammad et al., 2020).

Studies comparing and analyzing the interactions between chatbots and high- and low-achieving learners have shown some differences. It has been found that proficient learners are more engaged in conversations with chatbots and tend to have higher satisfaction, while struggling learners may discontinue the conversation prematurely (Xia et al., 2023). Similarly, according to Chiu et al. (2023), beginner-level students require teacher support for effective motivation, whereas advanced learners may be hindered by teacher intervention. According to Shin (2019), lower-achieving students tend to produce more utterances when sentences are shorter, while higher-achieving students engage in more extensive conversations and use verb phrases more diversely when presented with less challenging texts. These findings highlight the importance of considering learners’ English proficiency levels when designing English classes that incorporate chatbot interactions.

Learners have also shown a high interest in AI chatbot-assisted lessons in the affective domain, experiencing a sense of comfort. Particularly in speaking skills development, the anxiety often associated with traditional language learning methods has been reduced (Kılıçkaya, 2020; Mageira et al., 2022), and students have demonstrated a high level of interest and engagement with AI chatbots. These emotional stability, high interest, and attention have been found to enhance learners’ confidence and improve their learning immersion (Huang et al., 2019). However, learners’ motivation can decline over time, so it is necessary to design lessons that incorporate specific learning tasks to maintain consistent motivation (Yin and Satar, 2020).

Teaching and design of English speaking using artificial intelligence chatbots

As the results of utilizing AI chatbots in classroom settings have shown positive effects in cognitive and affective domains, the need for systematic principles in designing lessons using AI chatbots has been emphasized. To develop principles for designing elementary English speaking lessons using AI chatbots, it is necessary to analyze previous research related to principles and guidelines for designing English speaking lessons using AI chatbots, both domestically and internationally.

First, it is necessary to consider the selection of appropriate media. Teachers should choose diverse and multidimensional media, taking into account the learning conditions and content (Yu, 2022). Selecting a medium that allows learners and the chatbot to engage in conversations by changing the order of questions and answers can encourage learners to produce more utterances. Therefore, it is important to select a medium that is suitable for learners’ proficiency levels and enables meaningful interaction (Chapelle, 2001). In the context of designing English speaking lessons using AI chatbots, the medium refers to the selection of a chatbot builder.

Second, it is important to design the learning content and assign tasks considering the learners’ proficiency levels and specific situations. It is crucial to construct the content that is appropriate for learners’ levels and personal characteristics (Lin and Mubarok, 2021). Careful consideration should be given to various factors such as family structure, social norms, and financial circumstances when designing activities to ensure meaningful engagement for students (Vazhayil et al., 2019). A systematic approach is needed to provide learners with a meaningful and accessible learning experience (Woolf et al., 2013; El Shazly, 2021; Yang, 2022).

Third, it is essential to provide an optimized learning environment when conducting speaking lessons using AI chatbots. The technical infrastructure for utilizing AI chatbots should be prioritized and established (Vazhayil et al., 2019; Li, 2022). Issues such as external noise interfering with the recognition of learners’ voices should be minimized (Kim et al., 2022), and support should be provided to create an environment that is conducive to optimal performance (Bii et al., 2018). Additionally, it is important to encourage learners and reassure them when they encounter difficulties during interactions with AI chatbots to prevent them from feeling overwhelmed.

Fourth, detailed guidance on the usage and task activities of AI chatbots is necessary. Since learners are encountering AI chatbots for the first time, instructors should provide thorough instructions on how to use them (Mendoza et al., 2022). Introduction to educational objectives (Kılıçkaya, 2020) and specific language learning tasks (Yin and Satar, 2020) should also be included to enhance the efficiency of the learning process.

Fifth, it is necessary to provide learners with pre-learning opportunities. If learners pre-learn relevant vocabulary, sentence patterns, and other aspects before using the chatbot (Vazhayil et al., 2019), it can minimize the burden of using the target language.

Sixth, it is important to generate and maintain students’ interest. While the introduction of artificial intelligence technology through the use of chatbots can initially capture students’ interest and attention, strategies are needed to sustain their interest throughout the class (Coniam, 2014; Yin and Satar, 2020; Pérez et al., 2020). Therefore, it is crucial to develop various teaching and learning methods that appeal to students, such as incorporating quizzes, graphics, and animations that facilitate easy understanding by learners (Gayathri and Rajendran, 2021).

Seventh, teachers need to provide appropriate scaffolding to learners. When learners encounter difficulties in interacting with the chatbot, offering necessary visual or additional materials can facilitate continuous conversations among students (Mendoza et al., 2022). It should be noted that while scaffolding is effective for novice learners, it can hinder support from the teacher for advanced learners, as suggested by research findings (Kalyuga, 2007; Williamson and Eynon, 2020; Chiu et al., 2023). Hence, teachers should provide scaffolding tailored to the learners’ levels and characteristics, enabling them to engage in smooth interaction.

Eighth, strategies for promoting meaningful negotiation of meaning are needed to elicit additional utterances from learners. Utilizing strategies that encourage meaningful negotiation of meaning, teachers can specifically prompt learners’ speech (Bygate, 1987; Lin and Mubarok, 2021). Additionally, for words or expressions that the chatbot does not immediately understand, strategies such as “requesting repetition,” “eliciting clarification,” and “eliciting inference” have been proposed (Chu and Min, 2019).

Ninth, it is necessary to provide immediate and personalized feedback to learners’ utterances (Haristiani, 2019; Kılıçkaya, 2020; Dokukina and Gumanova, 2020; Xia et al., 2023). There are two ways to provide feedback: one is through an AI chatbot that recognizes learners’ utterances and provides immediate feedback, and the other is for teachers to provide feedback to learners who have difficulties in conversing with the chatbot.

Last, it is important to have learning management that allows students to appropriately review and evaluate their learning process (Mendoza et al., 2022). Providing reflection journals can facilitate students’ reflection on their tasks and presentations (Kong, 2020), and enabling learners to manage their learning materials and progress is also suggested (El Shazly, 2021; Xia et al., 2023). Learners should have the means to plan, review, and evaluate their learning process effectively.

Methodology

This study applied the Design and Development research methodology to develop principles for designing elementary English speaking classes using AI chatbots. Design and Development research is a systematic approach that aims to establish empirical foundations for creating new models, instructional or non-instructional products, and tools, as well as the development, evaluation, and validation processes associated with them (Richey and Klein, 2014, p. 6). It serves the purpose of generating new knowledge and validating existing practices.

According to Richey and Klein (2014), there are two types of research in the field of design and development: “Products and tools research” and “Model research”(Table 1). “Products and tools research” describes and analyzes the design and development processes used in specific projects, making it context-dependent. On the other hand, “Model research” aims to provide a general analysis of new design and development processes and can be somewhat more generalized compared to “Products and tools research.” Model research is utilized in developing design models, and further, design principles, strategies, and guidelines (Richey and Klein, 2014).

Table 1 The representative types and characteristics of design and development research.
Full size table

In this study, we utilized “Model research” among these two types. Model research allows us to analyze the effectiveness and validity of existing or newly created models in the context of model development and the development process. Exploring model research involves three main topics: model development research, model validation research, and model use research.

First, “model development research” aims to develop comprehensive models and the processes associated with their components. Second, during the “model validation” phase, the validation of the model’s components is carried out. Lastly, in the “model use” phase, the conditions that affect the model’s use are studied, including research on the characteristics and expertise of designers and their decision-making processes.

In this particular study, which focuses on developing and validating a new instructional design model for elementary English speaking courses using AI chatbots, I performed model development research and model validation research. The specific procedures are outlined as follows.

First, the initial design principles were derived through a review of domestic and international literature related to using AI chatbots in classroom settings. The literature review encompassed academic papers, conference proceedings, institutional research reports, articles, and books. The main topics were AI chatbots and English-speaking classes, while subtopics were categorized into principles for designing classes using AI chatbots and models for designing classes using AI chatbots.

Second, to validate the viability of the initial design principles, an expert validation review was conducted. The expert panel consisted of individuals who held master’s or doctoral degrees in the relevant field and had published papers or presented on topics related to the research (Table 2). The validity assessment questionnaire for the design principles was adapted from Kim S (2016a, 2016b) to suit the present study. The questionnaire utilized a 4-point scale (4: strongly agree, 3: agree, 2: disagree, 1: strongly disagree) for closed-ended items and included open-ended items to allow experts to provide additional comments and opinion.

Table 2 Expert panel profile and validity evaluation participation process.
Full size table

Third, a usability evaluation was conducted to determine if the developed instructional design principles utilizing the AI-based chatbot for elementary English-speaking classes were helpful for elementary school teachers in the field. Three elementary school teachers participated in the evaluation, selected based on their interest in AI chatbots or prior experience using them during class. The participants had a range of teaching experience, from 7 to 20 years, to ensure that the application of the developed design principles was feasible across different levels of teaching experience (Table 3).

Table 3 Usability evaluation participant profiles.
Full size table

During the usability evaluation, the participating teachers had one-on-one discussions with the researchers to receive explanations about the instructional design principles and discuss any areas of misunderstanding. Next, the teachers designed lessons based on the provided instructional design principles and, upon completing the lesson designs, responded to a usability evaluation questionnaire. The usability evaluation items were designed on a 4-point scale to assess the teachers’ understanding of the instructional design principles for AI-based elementary English-speaking classes and the practical assistance provided by the design principles in their actual lesson planning. The final section of the questionnaire allowed the teachers to freely provide their opinions on strengths, weaknesses, and suggestions for improvement.

The responses from the expert validation and usability evaluation were analyzed for validity and reliability using the Content Validity Index (CVI) and Inter-Rater Agreement (IRA) among the evaluators. Based on the input from experts and users, the final instructional design principles were developed.

The specific procedure of the study is as depicted in Fig. 1.

Fig. 1: The process of developing instructional design principles.
figure 1

It indicates the research type, research methods, procedural steps, and the flow of outputs for developing the final model of instructional design.

Full size image

Results

Derivation of the initial design principles and components of the model

Through a review of existing literature, elements applicable to designing elementary English speaking classes using AI chatbots and general design principles were identified. Based on commonalities among the findings, the components were derived through an iterative process. As a result, five initial components of the model for designing elementary English speaking classes using AI chatbots were identified: AI chatbot learning tool, AI chatbot utilization curriculum, AI chatbot learning support, AI chatbot utilization activities, and AI chatbot learning outcomes and evaluation, as presented in the Table 4.

Table 4 The initial design principles and components.
Full size table

Expert Validation results regarding the initial Components

The expert validation of the components of the principles for designing elementary English language classes using AI chatbots was conducted in two phases (Table 5). In the first phase of expert validation, the average score for the “level of components” was the highest at 3.60, while the other items ranged between 3.00 and 3.40. The IRA among the experts was 0.11, indicating a need for modifications in the overall design principles. IRA stands for the Index of IRA, which is an index representing the reliability of evaluations among experts. In this paper, it is calculated by dividing the number of items on which experts unanimously agreed by the total number of items (Rubio et al., 2003). In the primary expert validation, among the total of 9 domains, an IRA of 1.00 was observed, as one item received a score of 1. This is due to the fact that one of the five experts assigned a score of 2 to one or more items. However, in the second phase of expert validation, the revised components based on the converging opinions from the first phase were evaluated by the experts. The CVI was 1.00, indicating that the experts considered all items to be valid. The IRA was also 1.00, indicating high agreement among the experts and ensuring the reliability of their evaluations.

Table 5 Results of expert validation for the components.
Full size table

The expert reviews on the components conducted in the second phase are summarized in the below Table 6. First, there were opinions from experts indicating that some components have incorrect hierarchy, and some sub-components are overlapping, suggesting the need to reorganize the components and sub-components and derive the upper-level components again. For example, the provision of individual feedback was considered more suitable for the sub-component of “AI Chatbot Utilization Activities”, according to one expert. Additionally, there were opinions suggesting that the components, “AI Chatbot Learning Tool”, “AI Chatbot Utilization Curriculum” and “AI Chatbot Learning Support” all seemed to be included in “AI Chatbot Utilization Activities”, making it difficult to distinguish each item effectively. Second, it was recommended that the descriptions of the components should be distinct and clearly presented, highlighting the differentiation between “AI Chatbot Utilization Activities” and “AI Chatbot Learning Support.” Third, since some sub-components are not well-differentiated within each component, there is a need to modify the names of the components to align with the corresponding sub-components.

Table 6 The expert opinions and improvements regarding the components from the primary and secondary expert reviews.
Full size table

Some of the initial components have a broader scope and lack clear explanations, thus requiring modification in response to the expert reviews. Fourth, there is a need to add certain sub-components to each component and provide clear explanations for them. For instance, one expert suggested adding the principle of sharing and reflecting on opinions with group members when utilizing the new technology of AI chatbots in certain activities. These expert reviews have been taken into account to make improvements.

Expert validation results for the initial design principles

The expert validation for the overall design principles was conducted, considering the criteria of validity, explanatory power, usefulness, universality, and comprehensibility. Expert opinions were examined and provided for the items of validity, explanatory power, usefulness, universality, and comprehensibility for the overall design principles in two rounds of validation. The summarized results of the expert validation for the overall design principles, conducted in the 1st and 2nd rounds, are presented in the Table 7.

Table 7 Expert Validation Results for the Overall Design Principles.
Full size table

The results of the first expert validation review on the overall design principles showed generally high scores, with an average of 3.60 or above in all categories. The CVI was above 0.80 for all items, indicating that the participating experts found the design principles to be valid. The IRA was 0.80, indicating a reasonable level of consistency among the experts’ evaluations and establishing their reliability. However, one expert suggested that adding explanations and examples would facilitate teachers’ ability to design lessons according to the derived principles. In the second expert validation, explanations and examples were added, and a design principle and detailed guidelines related to communication and collaboration in group activities were included. The revised components were restructured and organized according to the design principles. In the second validation, all categories of the design principles, including validity, clarity, usefulness, universality, and comprehensibility, received the highest score of 4.00. The CVI was 1.00 for all items, indicating that all participating experts found the design principles to be valid. The IRA was also 1.00, suggesting a high level of consistency and reliability among the evaluators’ ratings.

The initial principles and detailed guidelines were restructured, revised, deleted, integrated, and refined based on the input from primary experts. As a result, a set of second-stage design principles and detailed guidelines was derived, consisting of a total of 10 principles and 24 detailed guidelines. The expert validation opinions and modifications incorporated during this process are summarized in Table 8.

Table 8 The opinions and suggestions from the primary and secondary expert validations regarding the design principles.
Full size table

Firstly, the components were restructured as a result of the overall restructuring based on the expert feedback, addressing the unclear inclusion relationship between principles and detailed guidelines and eliminating any duplication or overlap with previously mentioned principles and detailed guidelines. Secondly, areas with low validity scores and suggestions for modifications based on the expert validation feedback were either removed or integrated, while essential principles and detailed guidelines representing the core aspects of the study were added. Any content that resembled or duplicated existing information was removed during this process. Thirdly, due to changes in some components and the addition and removal of principles, the overall positioning and restructuring of the framework were readjusted. Fourthly, the content was elaborated by providing more specific and actionable statements, modifying abstract and ambiguous descriptions into concrete statements that represent specific actions or behaviors. Lastly, examples and explanations were added to the detailed guidelines to facilitate understanding and provide references for designing English speaking courses using AI chatbots. These additions aimed to assist in comprehending the detailed guidelines and their practical application. The third-round design principles were improved based on these experts’ feedback and recommendations.

Usability evaluation results

The usability evaluation was conducted to assess the suitability of the developed 2nd iteration instructional design principles for actual classroom use by teachers. Three elementary school teachers working in schools in Seoul and Gyeongsangnam-do, South Korea participated in the usability evaluation. They were given an explanation of the developed instructional design principles by the researcher and were asked to imagine themselves designing an elementary English-speaking class using an AI chatbot. Based on this, they were requested to create a teaching and learning guide. Subsequently, a usability evaluation questionnaire was provided to assess the extent to which the instructional design principles were helpful in lesson planning.

The usability evaluation results for the two questions indicate an average score of 4.00, with both CVI and IRA showing a score of 1.00 (Table 9). All three teachers who participated in the usability evaluation provided positive responses, stating that design principles and detailed guidelines are helpful in designing English speaking lessons using AI chatbots. Their opinions on the strengths, weaknesses, and areas for improvement of each principle and model, as presented in open-ended questions, are summarized in Table 10 as follows.

Table 9 Usability Evaluation Results for Design Principles.
Full size table
Table 10 Suggested strengths, weaknesses, and areas for improvement identified in the usability evaluation.
Full size table

The feedback gathered from Elementary school teachers through the usability evaluation questionnaire yielded the following results. The design principles were found to be helpful in the instructional design process, as they were accompanied by detailed explanations and examples. However, some examples were deemed insufficiently specific, and it was suggested that they should be presented more concretely using terminology familiar to classroom teachers.

The opinions of Elementary school teachers, obtained through usability evaluation, were incorporated into the final model development alongside the results of the secondary expert validation. The final model underwent improvements mainly at the level of terminology and relationships between terms, with no significant structural changes.

Final instructional design principles and guidelines

The final instructional design principles and guidelines derived from expert validation and usability evaluation are presented in the following Table 11. The components include “Creating AI Chatbot Learning Environment,” “AI Chatbot Utilization Curriculum,” “AI Chatbot Teaching and Learning Activities,” and “Evaluation of AI Chatbot Learning”. A total of 10 instructional design principles and 24 detailed guidelines can be applied.

Table 11 Final Instructional Design Principles and Guidelines for Elementary English Speaking Classes Utilizing AI Chatbot.
Full size table

Discussion

In this study, we aimed to develop instructional design principles and guidelines to support the design of elementary English speaking classes utilizing AI chatbots. Based on the results of the research, we can discuss the theoretical and practical aspects as follows:

First, through the development of instructional design principles and guidelines, we have enabled teachers to systematically design English speaking classes using AI chatbots. Unlike previous studies that only focus on measuring the cognitive and definitional effects of using AI chatbots in instruction (Kim, 2016a, 2016b; Han, 2020; Kılıçkaya, 2020) or provide instructional guidelines and models (Lin and Mubarok, 2021; Mendoza et al., 2022), our study includes design principles and guidelines that teachers need to consider during the instructional design process. In particular, there has been a growing interest in utilizing various Edu-tech in public elementary schools in South Korea since the outbreak of the COVID-19 pandemic in 2020. Teachers who are incorporating various edu-tech tools into their lessons might find it confusing, given the vast amount of new edu-tech resources being introduced. At this time, referencing the instructional design principles and guidelines for elementary English speaking classes using AI chatbots can be a valuable resource. Designing their own lessons with the guidance of these principles, especially those incorporating artificial intelligence chatbots, can undoubtedly reduce trial and error and provide useful materials for systematic implementation.

Second, we have applied a research methodology that integrates theoretical and practical aspects based on a review of relevant literature on AI chatbots in English language instruction. While previous studies have focused on developing instructional models based on students’ and teachers’ needs or addressing specific challenges in AI chatbot-assisted instruction (Mendoza et al., 2022), our study contributes to the field by providing a logical process for developing instructional designs. Through a comprehensive review of theories and literature related to AI chatbots, English speaking skills, and instructional design, we derived instructional design principles and guidelines, and further validated them through expert review. The research findings hold significance in guiding instructors to have a systematic and comprehensive perspective when designing their classes.

Third, our study offers ideas that extend beyond the application of AI chatbots in English language instruction alone. It provides insights into utilizing AI chatbots for various languages such as Korean, Chinese, and Japanese. When designing language-specific instruction, teachers can refer to the foundational design principles and guidelines that are essential for incorporating AI chatbots as a learning tool. Furthermore, although our study focuses on instructional design principles for elementary English-speaking classes, the principles and guidelines can be applied to middle school, high school, and university-level English speaking classes with appropriate modifications. By considering the target learners’ proficiency levels and corresponding curricula, our developed design principles and guidelines can be adapted for other levels of English-speaking instruction.

In conclusion, our research contributes to the field by developing instructional design principles and guidelines to support the design of elementary English speaking classes using AI chatbots. These guidelines provide teachers with a systematic and comprehensive approach to instructional design and can be applied not only in English language instruction but also in other languages. Additionally, the principles and guidelines can be extended to different educational levels, offering valuable insights for designing English speaking classes across various learner groups.

Conclusion

Based on the research results, the following conclusions can be drawn:

First, the instructional design of elementary English speaking classes using AI chatbots follows a structure where the activities revolve around the “AI chatbot teaching and learning activities” and conclude with reflection and evaluation of the learning process. Teachers have the flexibility to adapt and customize the process based on their specific contexts. This instructional design process relies on the underlying support of the learning tool called Dialogflow and the technical infrastructure required to manage it. Teachers need to align their instructional design with the available software and hardware resources. For example, if there are AI speakers available in the classroom, tasks can be assigned to the whole class or to small groups. Similarly, if there is a limited number of tablet PCs, tasks can be assigned to small groups or rotated among students.

Second, the instructional design principles developed in this study for English speaking classes using AI chatbots can contribute to increasing the attainability of English language goals and standards within the curriculum. The design principles offer options for teachers to choose between repetitive or question-and-answer-based chatbots according to the students’ proficiency levels, enabling personalized instruction. Traditional teacher-centered lecture-style instruction has limitations in achieving personalized instruction, but AI chatbot-assisted instruction can provide an alternative to overcome the physical constraints of dense classroom environments and limited English instruction time. Furthermore, considering the English education environment in South Korean elementary schools, we are exploring methods to replace native English teachers currently placed in elementary schools. Using AI chatbots for English speaking lessons could potentially serve as an alternative to substitute native English teachers. Therefore, in South Korea’s English education environment, it is expected that using AI chatbots for English speaking lessons will have a more significant impact.

Third, AI chatbot-assisted English speaking classes have the potential to reduce the proficiency gap caused by socioeconomic disparities. English language education in Korea heavily relies on private tutoring, and improving speaking skills, one of the four language skills, requires significant investment of time and effort. Utilizing an AI chatbot for English speaking classes allows learners to practice their English speaking skills not only during regular class hours but also after school, enhancing their communication abilities. However, to achieve this, it is crucial to provide each student with a tablet PC or Chromebook and establish wireless internet environments in students’ homes.

Some limitations and suggestions for future research based on the research process and results are as follows:

First, this study focused on elementary school students in South Korea, and the application of the developed instructional design was limited to elementary schools. Therefore, it is necessary to compare the differences and effectiveness of applying the instructional design model to middle school and high school students. To generalize the instructional design model to different educational levels, it is important to analyze which aspects of the design principles and guidelines need to be modified and improved when applying them to middle school and high school students.

Second, the process of planning and implementing AI chatbot-assisted English speaking classes requires more time and effort compared to traditional lecture-style instruction. It requires knowledge of tools like Dialogflow for AI chatbot development and practical experience in creating AI chatbots and learning materials. Additionally, to implement these classes during instructional time, securing tablet PCs, establishing wireless internet environments, and technical preparations like logging into the Google Assistant app on all devices using the teacher’s Google account are necessary. Given these challenges, there is a possibility that teachers might feel burdened and hesitate to implement AI chatbot-assisted instruction. Therefore, educational institutions should establish the necessary technological infrastructure to support teachers in utilizing various AI learning tools, reducing the time and cost burden associated with instructional design.

Third, as AI chatbots are capable of various forms of input and output, including text and speech, it is essential to develop instructional design models not only for English speaking but also for listening, reading, and writing in the field of English education. This would provide guidelines for teachers to conduct interactive English language classes in all four language skills. Further research is needed to explore the ways in which AI chatbots can be utilized in English language instruction across these four areas.

In conclusion, the research has developed instructional design principles and guidelines to support the design of elementary English speaking classes using AI chatbots. These guidelines provide a systematic and comprehensive approach to instructional design, not only for English language instruction but also for other languages. They can be extended to different educational levels, offering valuable insights for designing English speaking classes for diverse learner groups. However, further research is required to address limitations and explore the application of the instructional design model to different educational levels and language skills.