Abstract:
There is an urgent need to detect and manage mental health disorders among college students, who often face psychological challenges due to academic pressures and significant life changes. In this context, expert systems emerge as a potential tool to assist in the diagnosis and management of mental health problems. The purpose of this study is to present the results of a systematic review of expert systems for detecting mental health disorders in college students through the systematic literature review (SLR) method. By asking four research questions covering types of mental health disorders, methods used, comparisons between methods, and testing techniques, this study limits its review to studies published in the last five years, from 2019 to 2024. This review covers various types of mental health disorders, such as depression, anxiety, stress disorders and other mental health disorders that are often experienced by the college student population. As well as evaluating and comparing methods such as forward chaining, backward chaining, certainty factor and fuzzy logic methods to identify the advantages and disadvantages of each method. Certainty Factor emerged as the most accurate method with an accuracy of 96.09% and the recommendation for combining methods for this study is certainty factor and forward chaining with an accuracy result of 100%. In addition, this study also discusses the testing process to ensure the effectiveness and accuracy of the resulting diagnosis. The findings of this systematic review are expected to provide valuable insights for the development of more effective expert systems in supporting college students' mental health.
