Abstract
Title: MindSpace – AI-Driven Stress Detection and Cognitive Pattern Analysis Using
Natural Language Processing
Mental health awareness has become a crucial global concern, especially among students and
young professionals who face increasing academic and social pressures. Traditional methods of
identifying mental stress rely heavily on self-reporting and human evaluation, which are often
time-consuming and subjective. With advancements in Artificial Intelligence (AI) and Natural
Language Processing (NLP), it is now possible to assess emotional states directly from written
language.
MindSpace is an AI-driven system designed to detect and analyze cognitive stress patterns from
textual input. The project integrates pre-trained transformer models such
as DistilBERT or RoBERTa to extract semantic and emotional features from sentences. By
calculating a “Stress Index” (ranging from 0–100%), the system classifies user inputs into
categories such as Low, Moderate, or High Stress. Additionally, a suggestion engine provides
personalized recommendations — such as relaxation tips, motivational quotes, or focus exercises
— based on the detected emotion.
The proposed model leverages datasets like GoEmotions and DailyDialog, combined with
linguistic features (word entropy, emotional tone) to enhance prediction accuracy. Evaluation is
performed using standard metrics such as accuracy, F1-score, and confusion matrix analysis. The
results are visualized on a user-friendly dashboard to help users monitor mood trends over time.
This project directly aligns with United Nations Sustainable Development Goal (SDG) 3:
Good Health and Well-Being, promoting mental wellness through AI-based preventive tools.
The ultimate goal is to empower users to better understand and manage their emotional health
using technology, bridging the gap between psychology and computational intelligence.
Student Name: Mehar Chaithanya Pemmasani
Register Number: RA2311003011556,RA2311003011551
Guide Name: Dr. K. C. Prabu Shankar (102253)
College name : Department of Computer Science and Engineering, SRM Institute of Science
and Technology, Kattankulathur Campus (SRM KTR)
Base Paper Reference:
Sharma, S., Patel, R., & Kumar, A. (2022). Stress Detection through Linguistic Patterns in
Social Media Posts Using Deep Learning. IEEE Access, 2022. DOI:
10.1109/ACCESS.2022.3145639