SENTIMENT ANALYSIS IN STUDENT LEARNING EXPERIENCE

The task of predicting students' performance has become more challenging due to the obscurity, volume, and irregularities of data. These factors compounded with the human element of mood and altitudes of the student and the perception of the lecturers by the students have brought about "SUBJECTIVITY" in the learning environment. This design seeks to eliminate "SUBJECTIVITY" in Student Learning Experience by leveraging on machine Learning algorithms & Methodology. This paper builds on existing techniques and aims to improve upon them. Success was achieved in this regard by combining academic and social variables in the attribute set. These variables will go a long way in improving student performance and success rates as well an explaining extensively the components of a student learning metric and its features.