Author Unknown: Evaluating Performance of Author Extraction Libraries on Global Online News Articles

TL;DR

This paper evaluates the performance of five author extraction tools on multilingual online news articles, revealing variability across languages and highlighting the need for further validation for reliable author identification.

Contribution

It introduces a cross-lingual dataset for author extraction and compares existing tools, providing insights into their effectiveness across different languages.

Findings

Go-readability and Trafilatura are most consistent for author extraction

All tools show high variability across languages

Further validation needed for specific languages and regions

Abstract

Analysis of large corpora of online news content requires robust validation of underlying metadata extraction methodologies. Identifying the author of a given web-based news article is one example that enables various types of research questions. While numerous solutions for off-the-shelf author extraction exist, there is little work comparing performance (especially in multilingual settings). In this paper we present a manually coded cross-lingual dataset of authors of online news articles and use it to evaluate the performance of five existing software packages and one customized model. Our evaluation shows evidence for Go-readability and Trafilatura as the most consistent solutions for author extraction, but we find all packages produce highly variable results across languages. These findings are relevant for researchers wishing to utilize author data in their analysis pipelines, primarily indicating that further validation for specific languages and geographies is required to rely on results.