Intelligent Tutoring Systems (ITSs) are programmes that model learners’ progress and provide personalized instruction (Fletcher, 2018). Although the vision of an ITS is genuinely caring about learners, current ITS research only focuses on how ITSs teach subject knowledge, and there is a lack of research on whether learners can maintain interest interacting with the system or learn metacognitive skills. Teaching robust, lasting self-regulation skills is identified as a grand challenge in today’s ITS design (e.g. Aleven et at., 2016).

Gamification is designing information systems to stimulate similar experiences and motivations as games do and to bring external consequences, such as entertainment or enjoyment of the system use, which motivate the user towards certain behaviours (Koivisto & Hamari, 2019). Enjoyment and challenge are two essential elements brought by gamification design (Aparicio et al., 2019). Timescale or novelty effect may hinder students’ long-term commitment to the system as learners may find that the games are novel at first, but repetitive over-time, after extended exercise (Jackson & McNamara, 2013). Thus, learners need not only personalised resources to keep learning motivating but also skills to help them regulate their learning. Thus, with gamification providing extrinsic motivation, self-regulated learning may provide intrinsic skills to regulate their study. These two elements are intertwined. The self-regulation may lead to the use of gamification elements and vice versa. Therefore, this paper hypothesizes that:

H1a. Meta-Cognitive Self-regulation has a positive effect on Gamification elements.

H1b. Gamification elements have a positive effect on Meta-Cognitive Self-regulation.

As reviewed previously, Gamification includes Challenge and Enjoyment, which can provide emotional energy to maintain and increase the learner's interest. These two elements actively induce learners to participate in the system, which is also identified to be a key component in a MOOC success (Aparicio et al., 2019). Here, we see ITS as an Information System (IS), whose success examines quality and user satisfaction (See the IS Success Model by Delone & McLean, 2003). Learners are seen as users of an IS, and with gamification, learners shall be more satisfied with its quality and thus use it more. Therefore, it is hypothesized that:

H2. Gamification has a positive effect on ITS (ITS quality and ITS use).

Effective self-regulated learning skills include time management, metacognition, critical thinking, and effort regulation (see Broadbent & Poon, 2015 for a systematic review). Despite other self-regulation skills that may contribute to expert learning, metacognition is highlighted here as the key to the success of an ITS. Here, metacognitive strategies refer to the awareness to monitor, plan, and regulate learning (Yukselturk & Bulut, 2007) An expert learner should use metacognitive skills to self-regulate learning through the circle of planning, monitoring, and evaluation (Ertmer & Newby, 1996). These three steps contribute to better management of the learning process. When students have the cognitive skills of self-regulation, it is believed that they would find the ITS useful and they would increase the use of the ITS. Therefore, the current study hypothesises that:

H3. Meta-cognitive Self-regulation has a positive effect on ITS (ITS Quality and ITS use).

The ITS construct includes ITS Quality as well as ITS Usage. The ITS quality refers to how learners find the ITS helpful in their learning process, and the actual usage of an ITS can bring out positive learning gain. A successful ITS is supposed to enhance students’ subject knowledge and provide increased learning gain for students. An increased usage shall ensure students acquire the targeted learning outcomes. Thus, it is hypothesized that:

H4: ITS has a positive effect on Learning Outcome

The ITS would be introduced to Senior Secondary school students (Year 10-12, age 16-18) in mainland China to develop their skills in Python. It is estimated that more than 1000 students would be participating in this Python course taught by this ITS voluntarily. The length of the duration, of course, is approximately a month, which can provide a foundation of Python language to students. The ITS would be introduced by the teachers of the computer subject, then students shall be allowed to utilize the computer room freely after school hours, which means they have flexibility in arranging their learning agenda. Learners will enter the ITS through login ID and passwords, which means they can be identified and be put into different treatment groups. Participants will be randomly assigned into 5 groups, including the group with a) solely ITS, b) ITS plus Gamification (GAM) component, c) ITS plus Meta-cognitive Self-regulation (SR) component, d) ITS plus GAM and SR components and e) a gradually “Update” version, with four phases, including the gradual “appearance” of GAM component and SR components, and later “disappearance” of the GAM component. For e) group, the four phases include 1) solely the ITS, 2) ITS plus GAM component 3) ITS plus SR component 4) ITS plus GAM and SR components. The four phases will tentatively last for a week, which would be adjusted base on the pilot will be aimed at seeing the interaction effect between GAM and SR components. For data collection, both the ITS log record and a questionnaire will be sources providing data for analysis. Firstly, the ITS helps to collect real-time user data. For the ITS Use, the length of time that each learner uses the system will be recorded, and for learning outcomes, the number of tasks completed by the learner will be marked. Secondly, a questionnaire administered can provide quantitative data. The questionnaire part includes general demographic information, ITS Quality (IQ) constructs, Gamification (GAM) and Meta-cognitive Self-regulated learning (SR). GAM and SR would be measured as two latent variables. The gamification variable has the measures of enjoyment (E) and challenge (CH) and the Metacognitive Self-regulated learning variable has the measures of Planning (P), Monitoring (M) and Evaluation & Feedback (EF). Variables are measured by asking students to rate their perception towards the ITS they were using with a Likert scale. The questionnaire data will be analyzed using structural equation modeling (SEM).

To test the new success model of ITS, an ITS will be developed to help learners to study the programming language Python. After building the system and piloting the study, the ITS will be distributed to approximately 1000 secondary school students in Mainland China. ITS log data and questionnaires will be used to collect data on gamification and regulation in the learning process. Structural equation modelling will be applied to assessing the success of the model to test Hypothesis 1 to 4. The model integrates gamification and metacognitive self-regulation that should affect the quality and use of ITS, which shall lead to better learning outcomes for learners. The establishment of the interaction model would shed lights on further development of gamified ITS with complex content. Learning a programming language can also help promote computational thinking which is a universal skillset for everyone that “involves solving problems, designing systems, and understanding human behavior, by drawing on the concepts fundamental to computer science” (Wing, 2006, p. 33). Although this thinking skill does not necessarily need to be linked to programming or computer science (Voogt et al., 2015), coding provides the context that students can directly learn the thinking skills in. The teaching content is relatively abstract as it can best utilize the features of an ITS. The value of ITS appears to increase along with the need to deal with the complexity, multi-level interactions, and abstract concepts that are required for higher levels of knowledge and technical skill (Fletcher, 2018). In this proposed design, video and text lessons, hands-on exercises and quizzes are provided in the ITS, in which students can best learn Python through the system while developing computational thinking.

Aleven, V., Roll, I., McLaren, B. M., & Koedinger, K. R. (2016). Help helps, but only so much: Research on help seeking with intelligent tutoring systems. International Journal of Artificial Intelligence in Education, 26(1), 205-223. Aparicio, M., Oliveira, T., Bacao, F., & Painho, M. (2019). Gamification: A key determinant of massive open online course (MOOC) success. Information & Management, 56(1), 39-54. Broadbent, J., & Poon, W. L. (2015). Self-regulated learning strategies & academic achievement in online higher education learning environments: A systematic review. The Internet and Higher Education, 27, 1-13. Delone, W. H., & McLean, E. R. (2003). The DeLone and McLean model of information systems success: a ten-year update. Journal of management information systems, 19(4), 9-30. Ertmer, P. A., & Newby, T. J. (1996). The expert learner: Strategic, self-regulated, and reflective. Instructional science, 24(1), 1-24. Fletcher, J. D. (2018). Comments and reflections on ITS and STEM education and training. International journal of STEM education, 5(1), 16. Koivisto, J., & Hamari, J. (2019). The rise of motivational information systems: A review of gamification research. International Journal of Information Management, 45, 191-210. Voogt, J., Fisser, P., Good, J., Mishra, P., & Yadav, A. (2015). Computational thinking in compulsory education: Towards an agenda for research and practice. Education and Information Technologies, 20(4), 715-728. Wing, J. M. (2006). Computational thinking. Communications of the ACM, 49(3), 33-35. Yukselturk, E., & Bulut, S. (2007). Predictors for student success in an online course. Journal of Educational Technology & Society, 10(2), 71-83.