Investigation of Sentiment Analysis for the Diagnosis of ADHD

• Published in: SN computer science Vol. 6; no. 6; p. 633
• Main Authors: Patel, Raju, Dwivedi, Kaustubh, Singh, Rayan, Tiwary, Ishita, Muniraj, Manigandan, Adhikari, Manoj Singh, Tripathi, S. K.
• Format: Journal Article
• Language: English
• Published: Singapore Springer Nature Singapore 01.08.2025; Springer Nature B.V
• Subjects: Accuracy; Algorithms; Attention deficit hyperactivity disorder; Computer Imaging; Computer Science; Computer Systems Organization and Communication Networks; Data acquisition; Data Structures and Information Theory; Datasets; Decision trees; Deep learning; Diagnosis; Educational technology; Electroencephalography; Emerging Applications of Cyber-Physical System; Human error; Hyperactivity; Information Systems and Communication Service; Learning disabilities; Machine learning; Magnetic resonance imaging; Medical personnel; Mental health; Neural networks; Original Research; Pattern Recognition and Graphics; Sentiment analysis; Social networks; Software Engineering/Programming and Operating Systems; Support vector machines; Vision; ADHD; Support vector machine; Gaussian naive bayes; Sentiment-based model; Machine learning
• ISSN: 2661-8907; 2662-995X; 2661-8907
• DOI: 10.1007/s42979-025-04175-y

Attention-deficit/hyperactivity disorder (ADHD) is a neurodevelopmental condition that affects people from every age group, that can be identified by many traits, including impulsivity, hyperactivity, and inattention. It is one of the most prevalent disorders in children, (global prevalence of 5–7%) however when continued into adulthood, it may affect social functioning, employment, and education. Accurate diagnosis of ADHD is challenging because there are many subtle symptoms and behavioral pattern assessments are subjective in nature. The objective of this study is to develop a machine learning and deep learning model that uses sentiment analysis from various textual sources for detecting ADHD and hence empowers the traditional diagnosis methods and helping healthcare workers as well as patients. The methodology used here involves data acquisition from multiple sources, preprocessing, and then the application of boosting ensemble of support vector machine (SVM) classifiers, Gaussian naive Bayes (NB) models, and then a voting ensemble technique. Additionally, a deep learning model was built using an advanced BERT transformer model with neural network architecture, which excels in capturing patterns in textual data and gives higher accuracy and precision compared to traditional machine learning models. This approach enhances diagnostic accuracy and offers a more scalable solution for ADHD detection in the future.