A general model for an instructional video-based personalized programming learning environment and its practical implications

Constructing Instructional videos for personalized learning is a tedious and time-consuming process because it requires additional manpower as well as technological competence. This paper proposes a general model that can be adopted to design a personalized instructional video environment. The main components are 1. Learning style awareness-express basic idea regarding the learning style model 2. Learning style identification is the process of identifying the learning preference using a learning style model 3. Content Prediction Rules-set of rules to select suitable instructional videos matching the learning preference of the learner 4. Video Content Repository-Store all video content ready to deliver 5. Content Dispatcher-Dispatch instructional video content to the learner. The construction and management of video content are difficult and require ample time and patience. Major hurdles are the Construction of unique Instructional videos that match the learning preference of the learner, Content creation duration and effort, Lack of specialized content creators, and Space and cost of managing video content. In a video-based personalized learning platform, learners get the video content based on the recommendations from the learning style model. The selection of the learning style depends on the requirements and interests of the developer. Open Source, as well as Freemium Text-to-Video AI tools such as steve.ai, GliaCloud, Synthesia, Stable Diffusion videos, Deforum Stable Diffusion, Make-A-Video, and Lumen5, are available to support and enhance the manual process of the educational video-making process. Open-Source Cloud-based video hosting services such as PeerTube, Vimeo, MediaGoblin, and YouPHPTube can be integrated into the EdTech environment to reduce video delivery delay and hosting charges.