Analysis and Classification of Textual Data Using Machine Learning Techniques

Abstract

Recent advances in Artificial Intelligence (AI) have seen widespread applications across domains such as computer vision, natural language processing, and graph-based learning. Among these, Large Language Models (LLMs) have emerged as a cornerstone of modern AI research, with applications ranging from language understanding to content generation. As research in this field rapidly expands, newcomers face the challenge of navigating an overwhelming number of survey papers that attempt to consolidate knowledge on LLMs. This project addresses this issue by performing a comprehensive data exploration and analysis of metadata from recent LLM survey papers. Through the analysis of publication trends, citation patterns, and topical coverage, we aim to offer insights that simplify the discovery process for beginners and provide a clearer understanding of the current landscape. Our findings are intended to facilitate more efficient reading and research in the field of LLMs, enabling new researchers to quickly grasp key developments and emerging trends.