Beyond original Research Articles Categorization via NLP

TL;DR

This paper introduces a new NLP-based method using SciBERT and K-Means clustering to categorize scientific abstracts, including unknown categories, outperforming traditional labeling systems and aiding research navigation.

Contribution

It presents a novel approach combining pre-trained language models and clustering for effective scientific literature categorization beyond existing labels.

Findings

Improved subject information capture over traditional arXiv labels

Effective clustering of scientific abstracts using SciBERT embeddings

Potential enhancement of research navigation and recommendation systems

Abstract

This work proposes a novel approach to text categorization -- for unknown categories -- in the context of scientific literature, using Natural Language Processing techniques. The study leverages the power of pre-trained language models, specifically SciBERT, to extract meaningful representations of abstracts from the ArXiv dataset. Text categorization is performed using the K-Means algorithm, and the optimal number of clusters is determined based on the Silhouette score. The results demonstrate that the proposed approach captures subject information more effectively than the traditional arXiv labeling system, leading to improved text categorization. The approach offers potential for better navigation and recommendation systems in the rapidly growing landscape of scientific research literature.