Singaraja – Academics from Ganesha University of Education (Undiksha) have developed an innovative digital-based product aimed at detecting students’ mental health conditions. The research team, comprising Dr. Agus Aan Jiwa Permana, S.Kom., M.Cs., Prof. Dr. Kadek Suranata, M.Pd., and Dr. I Gede Partha Sindu, M.Pd., focused their efforts on creating solutions to address depression and suicide prevention among students.
This innovation aims to tackle the prevalent issue of depression among university students, which can hinder their ability to meet academic demands. depression and suicide from the start. Academic resilience plays a vital role in helping students persevere during challenging times. However, traditional counseling services, which are typically conducted face-to-face, often pose limitations due to the need for appointments, time commitments, and one-on-one sessions. This sparked the idea to develop a more accessible and efficient digital counseling service.
The Research Team’s Leader, Dr. Agus Aan Jiwa Permana, explained that the digital counseling model focuses on life stories, These stories can reveal significant insights into an individual’s experiences, uncovering the levels of depression and resilience. The life story-based digital counseling model offers an overview of a student’s mental health, enhanced by Artificial Intelligence(AI) to validate and strengthen decision-making processes.
The model uses Long Short-Term Memory (LSTM), a proven AI method capable of predicting and classifying depression and resilience levels. LSTM’s ability to retain long-term memory allows it to efficiently process time-sequenced data, accelerate learning, and provide a more responsive mental health support system for students.
The mode;’s strength lies in its use of validated data frim multiple sources, including social media platforms like Twitter (X), WhatsApp, and Instagram, as well as responses from the Star Questionnaire. These data sources are considered authentic as they are completed voluntarily, free from pressure. The integration of this data allows the LSTM model to deliver highly accurate results, providing a detailed overview of students’ mental health specifically in relation to depression and resilience.
