Authors:
Henrique Rodrigues
;
Eduardo Santiago
;
Gabriel Wanderley
;
Laura Moraes
;
Carlos Eduardo Mello
;
Reinaldo Alvares
and
Rodrigo Santos
Affiliation:
Graduate Program in Computer Science (PPGI) at the Universidade Federal do Estado do Rio de Janeiro (UNIRIO), Avenida Pasteur 458, Rio de Janeiro/RJ, Brazil
Keyword(s):
Artificial Intelligence, Machine Learning, Algorithm, Students, Dropout, College, University, Systematic Mapping Study.
Abstract:
Higher Education Institutions (HEIs), including universities, colleges, and faculties, must develop strategies to mitigate students’ dropout rates in undergraduate courses. This is crucial for fulfilling their social role, delivering high-quality professionals to society, contributing to economic development, and preventing the resource wastage. In this context, artificial intelligence (AI) algorithms have emerged as powerful tools capable of predicting dropout rates and identifying undergraduates at risk. This study aims to investigate and discuss the state-of-the-art in applying AI algorithms to address students’ dropout. To achieve this objective, a systematic mapping study (SMS) was conducted, encompassing 223 studies at first. Finally, 23 studies were selected for in-depth analysis to explore the effectiveness of AI algorithms in predicting students’ dropout. Furthermore, we identified key methodological design issues associated with the application of these AI algorithms, inclu
ding common features and challenges in implementing these methodologies. This study contributes by providing practitioners and researchers with an overview of the main challenges faced by AI algorithms in predicting students’ dropout, highlighting issues related to modeling, experimental methodology, and problem framing.
(More)