Incorporating an Intelligent Tutoring System into the DiscoverOChem Learning Platform

The current work develops intelligent tutoring aspectsfor theDiscoverOChem learning platform. Intelligent tutoring systems aretechnology-based learning systems that can adapt the learning experience to better serve individual users. DiscoverOChem (www.discoverochem.com) isa free Internet-based platform for learning undergraduate-level organicchemistry. Data from previous years of students were used to analyzehow well individual students performed on various pages of the platform.Correlations between pairs of pages were analyzed. Predictive models,which use a user's results on previous pages to predict thatuser's likely performance on upcoming pages, were developedand evaluated. The most successful set of models, which utilizes randomforests of one-branch decision trees, was incorporated into the DiscoverOChemplatform as a recommender system. This system helps individual usersto identify pages that are likely to challenge them and provides targetedrecommendations about which previous pages to review in order to helpthem become better prepared to succeed on the upcoming page. We anticipatethat learners will benefit from this new individualization of theirlearning experiences. We also anticipate that the general 6-step frameworkthat was used to develop this system will be broadly useful for creatingintelligent learning platforms for other subjects as well.