Four Shades of Life Sciences: A Dataset for Disinformation Detection in the Life Sciences

TL;DR

This paper introduces a new dataset and methodology for detecting disinformation in life sciences texts by analyzing linguistic features and applying machine learning models, addressing limitations of existing fact-checking datasets.

Contribution

The study presents Four Shades of Life Sciences, a novel labeled dataset of 2,603 texts across 14 topics, and explores linguistic features with machine learning for disinformation detection.

Findings

Linguistic and rhetorical features can distinguish disinformative texts.

Large language models outperform classical classifiers in detection accuracy.

The dataset enables future research in life sciences disinformation detection.

Abstract

Disseminators of disinformation often seek to attract attention or evoke emotions - typically to gain influence or generate revenue - resulting in distinctive rhetorical patterns that can be exploited by machine learning models. In this study, we explore linguistic and rhetorical features as proxies for distinguishing disinformative texts from other health and life-science text genres, applying both large language models and classical machine learning classifiers. Given the limitations of existing datasets, which mainly focus on fact checking misinformation, we introduce Four Shades of Life Sciences (FSoLS): a novel, labeled corpus of 2,603 texts on 14 life-science topics, retrieved from 17 diverse sources and classified into four categories of life science publications. The source code for replicating, and updating the dataset is available on GitHub: https://github.com/EvaSeidlmayer/FourShadesofLifeSciences