In recent years, the system of student learning and academic emotions has been taken seriously to re-engineer the teaching-learning process at all levels of education. This research paper considers both aspects of assessing the translation of knowledge i.e. qualitative and quantitative. In the current scenario, quantitative and qualitative learning outcome measurements are utilized separately without any associativity, which has been recognized as a key gap in the current study. An intelligent model is developed based on students' quantitative performance and real-time reviews. Scores gauge in the tests, mid-term examination, end-term examination, etc., are referred to as quantitative measures. Whereas storing academic emotions i.e. how much students are engaged & emerged during the class and the same are referred to as qualitative measures. The conventional way to improve learning outcomes is to change pedagogy or assessment criteria but here a novel idea is presented where academic emotions enjoin the reasons for underperformance with quantitative assessment. The proposed model correlates the qualitative and quantitative measures of students learning using machine learning and curates the reason at a micro-level why the translation of knowledge is not happening for each course's learning outcomes.