Data Modeling
Latest Issue - Volume 1 Number 1 2026
Discover the perfect home for your research. Our extensive collection of journals and sections spans over thousands academic disciplines, ensuring you find the right fit for your work.
Explore trending research themes and collaborate with leading experts. Join an existing community or start a new one to advance knowledge in emerging areas...
Begin your publishing journey with confidence. Access our comprehensive author hub for expert guidance, tools, and resources to help you prepare, submit, and share your research effectively.
Ready to make an impact? Submit your work today and amplify its reach by publishing with us. Start your submission process quickly and easily.
Benefit from our efficient peer review system. Receive timely decisions on your manuscript—our average acceptance time is just 76 days.
Data Modeling
Data Modeling is an international, open access, peer-reviewed journal that publishes: Original Research; Reviews; Hypothesis formation and commentaries in the fields of b
Volumes
See all (1) >Article
Data Modeling
Volume 1 Number 1 2026
Table of Contents
Research Article
Data Modeling and Machine Learning
HCNN-LSTM with BERT Embeddings and TomekLinks for Imbalanced News Text Classification
Kamruzzaman Mithu 1*, Md. Nesar Uddin 1, Md. Ataur Rahman 1, Sayed Rokibul Hossain 1, Mohammad Nurul Huda 1
This study presents a robust hybrid framework that improves imbalanced news classification through contextual embeddings, better minority-class recognition, and superior performance.
Abstract | Full Text | Open Access Article
The peer-reviewed and edited version of record published online before inclusion in an issue
These articles have been peer reviewed and accepted for publication. They are still in production and have not been edited, so may differ from the final published form.
The Most Read ranking is based on the number of downloads in the last 60 days from papers published on the Data Modeling within the last 12 months. Usage statistics are updated daily.
-
HCNN-LSTM with BERT Embeddings and TomekLinks for Imbalanced News Text Classification
This study presents a robust hybrid framework that improves imbalanced news classification through contextual embeddings, better minority-class recognition, and superior performance.
Submit Article
Use the online submission system to send us your manuscript.
Call for Papers
We are seeking Contributions for a special issue. More.
Best Paper Award
Authors are awarded for Best Paper for this Journal Annually
Advertisement