Depression among students is a major mental health concern that interferes with both their emotional and

academic. Depressed students go unnoticed since they hide their symptoms or confuse them with normal

stress. Depression often affects focus and attention, making it hard for students to follow lessons, complete

assignments, or retain information. Having a detection system in place enables early intervention that can help

educators to detect warning signs early. This research used Agile Software Development Methodology in

designing and developing a student depression detection system. This methodology enables continues

feedback and enhancement to ensure the system is effective in meeting user needs. The process of development

is segmented into short cycles referred to as sprints, with each sprint dedicated to developing particular

features. For the evaluation, we selected eight (8) participants and five (5) IT experts for their technical

resource for the early identification of depression in students. It is advised to adopt the student depression

detection system in colleges and schools to aid in the identification of vulnerable students.

Keywords: Artificial Intelligence, Depression Detection, Multinomial Naïve Bayes Algorithm, Agile

Methodology, ISO/IEC 25010.

Student depression nowadays is a serious mental health problem that affects not only their emotional lives but

also their academic performance. According to the World Health Organization (2023) depression is the major

cause of depression globally is increasing because of personal issues, social demands, and academic pressure.

Most students with depression remain undetected because they might conceal their symptoms or confuse them

with normal stress, resulting in no early intervention based on Auerbach et al. (2018).

Utilizing a proven depression detection system makes it possible for early intervention to occur such that

warning signs are noticed before they grow into full-blown mental illness. The common measures of

identifying depression among students is through self-reporting surveys and observation by teachers have been

criticized on the grounds of stigma, underreporting, and personal bias according to Ibrahim et al. (2013).

However, developments like artificial intelligence have brought in more efficient and data-driven methods of

early detection. AI-based systems can examine a range of signs of depression such as body language, voice

pitch, and social media use to detect at-risk students as explained by Shen et al. (2021).

Machine Learning algorithms can analyze vast amount of data sets by identify subtle behavioral changes and

forecasting in mental health issues with significant accuracy as mentioned by Rao et al. (2022). This can be

seen in Natural Language Processing (NLP) methods that can evaluate written answers of students in

screenings and allowing students to receive the assistance they require without delay. A proactive technology-

enabled strategy for depression detection not only improves students' overall well-being and it’s cultivating

a supportive community that deeply respects and upholds both academic achievement and emotional

resilience.

The study of Ibrahim et al. (2013) depression is a significant health condition, the third cause of disability

following heart and respiratory illnesses. Despite their social privilege, the university students are at greater

risk because of academic pressure and changes in lifestyle. Yet rates vary between settings probably because

of varying methods of assessment, cultural views, and environmental influences. The identification of these

and a lack of data on diagnosable mental disorders in university students. This is a concern regarding accuracy

and the necessity of more thorough tests to properly assess their mental health. In addition of Buchanan (2012)

the National Institute of Mental Health recommends the development of interventions to avert clinical

depression in high-risk populations of college students.

This places emphasis on preemptive mental health care in institutions of higher learning. Medical school is an

extremely stressful institution, and therefore, medical students are more likely to be depressed than their peers.

This highlights the essential value of mental health support in medical education as explained by Puthran et

al. (2016).

In the study conducted by Islam et al. (2018) the social networks offer an interactive approach for users with

their friends and express their emotions by posting messages. These interactions yield important information

about users' feelings. By understand ing the social network, the researchers can investigate trends in emotional

expression, communication, psychological state, and behavior of the users.

investigate the potential of using social media for early detection since patterns of text and image posts of users

can tell a lot about their mental state.

Based on the study of Deshpande & Rao (2017) the detection system is a developing research area that aims

to detect an emotion using text mining. The development of web-based media has created huge user data

which allows for sentiment analysis of text. Furthermore, the development of machine learning and the

availability of depression data provide an opportunity for developing an early diagnostic system. These

systems are important in minimizing the number of affected individuals by diagnosing and addressing

concerns before they escalate according to Amanat et al. (2022).

According to Mulyani & Novita (2022) identifying the mood of the people against patients suffering from

depression by labeling posts with the Naïve Bayes Classifier (NBC) algorithm, while Term Frequency-Inverse

depression in university students. The aim was to optimize prediction quality by training the model with 70%

of the data and validating it using the remaining 30% as mentioned by Cruz et al. (2023).

As explained by Nikolaieva (2024) the Agile software development process is an iterative and incremental

process that prioritizes flexibility, customer satisfaction, and rapid delivery of software. The essence of the

Agile approach is breaking down the project into smaller units where each iteration involves a cycle of

planning, designing, coding, and testing. And this methodology will be necessary for the development of the

student depression detection system.

Figure 1. Agile Methodology according to Nikolaieva (2024)

can help identify early signs of mental health struggles. This system would work by analyzing behavioral

patterns through sentiment analysis that could assess written inputs from students like academic reflections to

detect emotional distress.

By integrating an early warning mechanism, the system could alert school counselors and educators when a

student shows signs of depression allowing a timely intervention. It would also provide personalized mental

health resources like recommendations for professional support. And ensuring student privacy and ethical data

usage will be a key consideration in its development. With this system in place, educational institutions can

create a more supportive environment to reducing dropout rates and promoting overall student well-being.

The design phase of the student depression detection system focuses on structuring its components to ensure

foundation for the development and implementation stages.

The development phase involves coding and integrating the designed system components to ensure smooth

functionality. This stage is one of the longest as it requires implementing both the front-end and back-end

structures to create a fully operational web application.

The front-end development will involve creating the user interface by including the homepage, self-

assessment tools, and counselor dashboard using HTML, CSS, and JavaScript. The design will be made

responsive with Bootstrap, ensuring compatibility across various devices.

Additionally, AI-powered sentiment analysis and behavior tracking will be implemented using machine

Throughout this phase, continuous testing and debugging will be performed.

The testing phase ensures the reliability, accuracy, and functionality of the student depression detection system

before its deployment. This phase involves evaluating the system using multiple testing methods to identify

errors, validate its features, and ensure a seamless user experience.

being.

software quality characteristics and evaluation criteria to ensure the effectiveness, reliability, and usability of

IT systems. When assessing the Student Depression Detection System, this standard is applied in two primary

areas which is the IT Evaluation for technical perspective and Mental Health Evaluation for user-centric

perspective.

acceptability evaluation.

Table 3. Evaluated by Mental Health Evaluators using ISO 25010:2011 criteria.

The functionality (3.75) reaches the highest of all ISO criteria that gives a meaning of that the system satisfies

the user needs which boosts the user engagement and satisfaction. Next is maintainability with the weighted

mean of (3.66) which refers to how easily the system can be adjusted to better suit the needs and surroundings

in terms of both efficiency and flexibility. Given the use of platforms and devices the concept of portability

(3.65) is increasingly significant. The mobility of a systems is assessed on a scale from insufficient to excellent

based on its ability to adapt the diverse environments and function seamlessly across devices. Users depend

on the systems to be reliable and accessible which makes the reliability (3.62) equally important. The users

may always access it without encountering any problems or disruptions. Furthermore, it raises user

involvement of efficiency (3.53) is critical to improving the quality of the user experience. The systems have

a fast -loading speed, fast response times, and effective resource management. And lastly is usability (3.44)

ratings and highlighting the system’s adaptability to evolving psychological research and its strong data

protection measures. Reliability (3.55) ensures consistent and accurate assessments, while usability (3.52)

confirms that students can easily navigate the system with minimal guidance.

Overall, the system has been deemed highly acceptable by mental health professionals and IT experts,

reinforcing its role in providing accurate and accessible mental health evaluations for students. This positive

assessment highlights the system’s effectiveness in identifying early signs of mental health concerns to allow

for timely intervention and support.

Based on the highly acceptable evaluation of the Student Depression Detection System, it is recommended

participants, and confidentiality was maintained throughout.

The authors declare no conflict of interest.

The data that support the findings of this study are available from the authors upon reasonable request.