IndoBERT recall for detecting suicidal ideation and triggering safety override.
A research-driven mental health support chatbot that combines crisis detection, multi-label emotion recognition, clinical screening, and LLM-based response generation in one neuro-symbolic workflow.
BATINARA was designed to address a key challenge in AI-assisted mental health support: large language models can be empathetic and flexible, but they may also produce unsafe or inappropriate responses during high-risk situations.
This project builds a safer hybrid architecture where predictive modules handle crisis detection and emotional understanding first, then guide the generative module through rule-based ethical control.
A neuro-symbolic hybrid system that combines machine learning, BERT-based safety filtering, and LLM response generation.
BATINARA emphasizes safety, contextual personalization, and transparent emotion visualization rather than using generative AI alone.
IndoBERT recall for detecting suicidal ideation and triggering safety override.
Multi-label emotion classification used to personalize the conversation context.
Screening results help modulate response style and conversational support level.
Ethical control is enforced through rule-based intervention logic and response override.
The system receives journal text or chat input from the user.
IndoBERT detects crisis-level intent and can override the generative pathway if risk is found.
Random Forest predicts multi-label emotions for contextual understanding.
Dynamic Context Integration Logic injects ethical and clinical context before the LLM generates a response.
Combines IndoBERT for crisis detection and Random Forest for multi-label emotion classification.
Uses the OpenAI API to generate responses that adapt to user condition, emotional context, and chosen support style.
Adjusts the tone and support style using emotion signals, PHQ-9/GAD-7 results, and therapeutic personas.
When crisis intent is detected, the system prioritizes protective intervention over free-form generation.
BATINARA was developed as my undergraduate research project. My work covered both the research and product side: dataset preparation, model experimentation, system design, interface flow, and implementation of the hybrid chatbot logic.
Built the crisis detection flow using IndoBERT-based text classification.
Developed the multi-label emotion classification approach using classical ML.
Structured the connection between predictive outputs, clinical screening, and LLM prompting.
Designed the user flow for onboarding, self-test, dashboard, and chat experience.
The onboarding interface focuses on accessibility, user trust, and privacy-aware entry into the platform.
BATINARA uses PHQ-9 and GAD-7 as structured screening inputs to support triage and dynamic personalization.
The dashboard visualizes user progress, screening results, and emotional patterns to make the system more transparent.
The chat module supports multiple therapeutic styles, contextual response generation, and emergency override when crisis-related intent is detected.
BATINARA is not only about generating responses, but about reducing harm in sensitive mental health contexts.
Emotion signals and screening results help the system respond in a more adaptive and context-aware way.
The system visualizes emotional interpretation and user progress to improve clarity and trust.
This project combines academic research, AI system design, and interface development in one integrated workflow.
You can read the journal page or open the full PDF to see the full methodology, abstract, and references.