Homepage2Vec: Language-Agnostic Website Embedding and Classification

TL;DR

This paper introduces Homepage2Vec, a language-agnostic website embedding and classification model, supported by a large multilingual dataset, achieving high accuracy and resource-efficient feature usage.

Contribution

It provides a new multilingual website dataset and a pre-trained model that classifies and embeds websites in a language-independent manner.

Findings

Homepage2Vec achieves a macro F1-score of 0.90.

The model performs well across low- and high-resource languages.

A small subset of features suffices for high performance.

Abstract

Currently, publicly available models for website classification do not offer an embedding method and have limited support for languages beyond English. We release a dataset of more than two million category-labeled websites in 92 languages collected from Curlie, the largest multilingual human-edited Web directory. The dataset contains 14 website categories aligned across languages. Alongside it, we introduce Homepage2Vec, a machine-learned pre-trained model for classifying and embedding websites based on their homepage in a language-agnostic way. Homepage2Vec, thanks to its feature set (textual content, metadata tags, and visual attributes) and recent progress in natural language representation, is language-independent by design and generates embedding-based representations. We show that Homepage2Vec correctly classifies websites with a macro-averaged F1-score of 0.90, with stable performance across low- as well as high-resource languages. Feature analysis shows that a small subset of efficiently computable features suffices to achieve high performance even with limited computational resources. We make publicly available the curated Curlie dataset aligned across languages, the pre-trained Homepage2Vec model, and libraries