Applications of NLP for the Analysis, Discovery, and Visualization of Scientific Literature

Scope:

The rapid growth in scientific literature across different fields has created both opportunities and challenges for researchers, practitioners, and policymakers. Access to extensive digital repositories enhances knowledge discovery. However, the large volume, complexity, and variety of scientific texts make it difficult to extract meaningful insights efficiently. Natural Language Processing (NLP) has become an essential approach for tackling this problem. It provides powerful tools for automated text mining, semantic analysis, knowledge graph development, and intelligent visualization of scholarly data. This special issue on “Applications of NLP for the Analysis, Discovery, and Visualization of Scientific Literature” aims to showcase innovative research that explores new NLP models, such as deep learning, transformer-based architectures, and hybrid methods, for examining and analyzing scientific documents. It will also highlight approaches for citation and co-authorship analysis, trend prediction, topic modeling, recommendation systems, and visualization techniques that enable users to easily navigate large collections of scholarly work.

The goal is to foster collaboration among computer scientists, information scientists, linguists, and domain experts. This will aid in developing clear, interpretable, and user-friendly NLP solutions. Ultimately, this Special Issue seeks to promote the use of NLP to accelerate scientific discovery, enhance access to information, and support better decision-making in research and innovation settings.

Topics:

We invite original research papers, review articles, and case studies on the following topics (but not limited to):

• Scientific literature mining
• Natural language processing in scholarly data
• Transformer-based models for text analysis
• Semantic representation of research articles
• Automated knowledge graph construction
• Topic modeling and trend analysis
• Citation network analysis
• Scholarly document classification
• Research paper summarization
• AI-driven literature recommendation systems
• Cross-domain knowledge discovery
• Named entity recognition in scientific texts
• Visual analytics of scholarly big data
• Multilingual scientific text processing
• Explainable AI for research literature analysis

Guest editors:

Dr. P. Raviraj, Dept. of Computer Science & Engineering, GSSS Institute of Engineering and Technology for Women, India. Email: raviraj@gsss.edu.in. 

Dr. Jingshan Huang, School of Computing, University of South Alabama, United States. Email: huang@southalabama.edu.

Dr. Maode Ma, KINDI Center for Computing Research, College of Engineering, Qatar University, Qatar. Email: mammdsg@ieee.org.

Submission deadline: 25 January 2026

Note: When submitting articles for this special issue, please select the section: “NLP for Scientific Literature.”