Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

An optimized deep learning-based drug recommendation system using a sentiment analysis and transformer models for

D Deepa1, T Dhiliphan Rajkumar1, P Nagaraj1

  • 1Department of Computer Science and Engineering, Kalasalingam Academy of Research and Education, Srivilliputhur, India.

Informatics for Health & Social Care
|July 16, 2026
PubMed
Summary

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Adaptive mobility-aware hierarchical task offloading for delay-sensitive applications in fog computing.

Scientific reports·2026
Same author

Deep learning and IoT-based framework for sesame plant identification and weed detection.

Scientific reports·2026
Same author

Attention Gated-VGG with deep learning-based features for Alzheimer's disease classification.

Neurodegenerative disease management·2025
Same author

Optimization enabled ResNet features with transfer learning for Alzheimer's disease detection.

Computational biology and chemistry·2025
Same author

Lung cancer detection and classification using optimized CNN features and Squeeze-Inception-ResNeXt model.

Computational biology and chemistry·2025
Same author

A novel deep learning model for diabetic retinopathy detection in retinal fundus images using pre-trained CNN and HWBLSTM.

Journal of biomolecular structure & dynamics·2024

This study introduces a novel sentiment analysis (SA) drug recommender system using optimized deep learning. The system achieves high accuracy in recommending medicines by analyzing user sentiments from reviews, improving healthcare decisions.

Area of Science:

  • Artificial Intelligence
  • Health Informatics
  • Natural Language Processing

Background:

  • Medicine recommendation systems (MRS) aid healthcare users in decision-making.
  • Analyzing user sentiment in complex, user-generated data is a significant challenge for MRS.

Purpose of the Study:

  • To propose a sentiment analysis (SA)-based drug recommender system.
  • To enhance drug recommendation through optimized deep learning (DL) and transformer-based feature extraction.

Main Methods:

  • A four-stage system: preprocessing, feature extraction (MHABERT), sentiment classification (GOBLSTM), and medicine recommendation.
  • Utilized Multi-Head Attention Bidirectional Encoder Representations from Transformers (MHABERT) for deep semantic feature capture.
  • Employed Golden Jackal Optimized Bidirectional Long Short-Term Memory (GOBLSTM) for sentiment classification.
Keywords:
BERTMedicine recommendation systemdeep learningfeature learningnatural language processingpre-trained transformersentiment analysis

Related Experiment Videos

Main Results:

  • Evaluated on Kaggle and Yelp health datasets.
  • Achieved maximum accuracies of 98.43% (Kaggle) and 98.30% (Yelp).
  • Outperformed existing drug recommendation approaches.

Conclusions:

  • Integrating SA with drug recommendation improves patient outcomes.
  • Optimizes medicine selection processes.
  • Contributes to reducing adverse drug reactions.