# Mapping the Web of Science, a large-scale graph and text-based dataset with LLM embeddings

arXiv: https://arxiv.org/abs/2602.04630 · HTML: https://mlsanity.com/paper/2602.04630/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 6 of its 12 references that are in the map.
- First posted on arXiv 4 Feb 2026.

## Builds on (most cited first, 6 of 6)

- [From Louvain to Leiden: guaranteeing well-connected communities](https://mlsanity.com/paper/1810.08473/) (2018)
- [Text Clustering with Large Language Model Embeddings](https://mlsanity.com/paper/2403.15112/) (2024)
- [A Survey of Text Representation Methods and Their Genealogy](https://mlsanity.com/paper/2211.14591/) (2022)
- [Domain Adapted Word Embeddings for Improved Sentiment Classification](https://mlsanity.com/paper/1805.04576/) (2018)
- [A principled methodology for comparing relatedness measures for clustering publications](https://mlsanity.com/paper/1901.06815/) (2019)
- [Clustering scientific publications based on citation relations: A systematic comparison of different methods](https://mlsanity.com/paper/1512.09023/) (2015)

## Abstract (arXiv)

Large text data sets, such as publications, websites, and other text-based media, inherit two distinct types of features: (1) the text itself, its information conveyed through semantics, and (2) its relationship to other texts through links, references, or shared attributes. While the latter can be described as a graph structure and can be handled by a range of established algorithms for classification and prediction, the former has recently gained new potential through the use of LLM embedding models. Demonstrating these possibilities and their practicability, we investigate the Web of Science dataset, containing ~56 million scientific publications through the lens of our proposed embedding method, revealing a self-structured landscape of texts.