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 Video

Updated: Jan 12, 2026

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
03:14

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

1.0K

Meta-learner-based frameworks for interpretable email spam detection.

Meghana Kshirsagar1,2, Vedant Rathi3, Conor Ryan1,2

  • 1Biocomputing Developmental Systems Research Group, Department of Computer Science and Information Systems, University of Limerick, Limerick, Ireland.

Frontiers in Artificial Intelligence
|November 6, 2025
PubMed
Summary
This summary is machine-generated.

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

Predictive Models for Kidney Offer Acceptance: Challenges and Strategies.

Journal of transplantation·2026
Same author

The Biodiversity of Peter I Island-The Most Remote Island in the World.

Ecology and evolution·2025
Same author

Spin decoherence in molecular crystals: Nuclear vs electronic spin baths.

The Journal of chemical physics·2025
Same author

Arab2Vec: An Arabic word embedding model for use in Twitter NLP applications.

PloS one·2025
Same author

Accelerating Biomolecular Modeling with AtomWorks and RF3.

bioRxiv : the preprint server for biology·2025
Same author

Enhanced Macular Telangiectasia Type 2 Detection: Leveraging Self-Supervised Learning and Ensemble Models.

Ophthalmology science·2025
Same journal

Logic, inference, understanding: cross-domain generalization for generative language models.

Frontiers in artificial intelligence·2026
Same journal

Label tree semantic losses for rich multi-class medical image segmentation.

Frontiers in artificial intelligence·2026
Same journal

Score-based generative diffusion models to synthesize full-dose FDG brain PET from MRI in epilepsy patients.

Frontiers in artificial intelligence·2026
Same journal

Resource-efficient retrieval-augmented question answering for the Indian Lok Sabha dataset.

Frontiers in artificial intelligence·2026
Same journal

Violation detection in power operation sites based on multi-scale detection and few-shot learning.

Frontiers in artificial intelligence·2026
Same journal

Deep reinforcement learning-based reversible medical image encryption framework for secure IoMT environments.

Frontiers in artificial intelligence·2026
See all related articles

A novel meta-learner significantly improves spam email classification. This advanced model outperforms traditional machine learning and deep learning methods, offering more robust and efficient spam filtering for real-world applications.

Area of Science:

  • Computer Science
  • Artificial Intelligence
  • Machine Learning

Background:

  • Email remains a critical communication channel, yet is challenged by pervasive spam.
  • Effective spam classification is vital for efficient digital communication and user experience.

Purpose of the Study:

  • To develop and evaluate a novel meta-learner for spam email classification.
  • To compare the meta-learner's performance against traditional machine learning (ML) and deep learning (DL) models.
  • To assess the impact of various word embeddings, vectorization schemes, and model architectures on spam detection.

Main Methods:

  • A novel meta-learner was developed and compared against five ML and five DL spam classifiers.
  • Performance was evaluated on the Enron-Spam and TREC 2007 datasets, including a hybrid dataset.
Keywords:
algorithmic biasclassificationdata biasdeep learningmachine learningmeta-learnernatural language processingspam email detection

Related Experiment Videos

Last Updated: Jan 12, 2026

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
03:14

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

1.0K
  • The meta-learner's predictions were stacked against individual model predictions.

    • Main Results:

    • The meta-learner achieved superior performance, with an accuracy of 0.9905 and an AUC of 0.9991 on the hybrid dataset.
    • It outperformed existing state-of-the-art models, including the only other meta-learning spam detection model.
    • In a zero-shot setting on unseen data, it achieved 0.8970 spam sensitivity and 0.7605 AUC.

    Conclusions:

    • Meta-learning provides a robust, bias-resistant approach to spam filtering suitable for real-world deployment.
    • Combining diverse model strengths enhances resilience against evolving spam tactics.
    • The proposed meta-learner offers improved accuracy, generalization, and computational efficiency.