Toxic Bias: Perspective API Misreads German as More Toxic

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Nogara, Gianluca, Pierri, Francesco, Cresci, Stefano, Luceri, Luca, Törnberg, Petter, Giordano, Silvia
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917724113862656
author Nogara, Gianluca
Pierri, Francesco
Cresci, Stefano
Luceri, Luca
Törnberg, Petter
Giordano, Silvia
author_facet Nogara, Gianluca
Pierri, Francesco
Cresci, Stefano
Luceri, Luca
Törnberg, Petter
Giordano, Silvia
contents Proprietary public APIs play a crucial and growing role as research tools among social scientists. Among such APIs, Google's machine learning-based Perspective API is extensively utilized for assessing the toxicity of social media messages, providing both an important resource for researchers and automatic content moderation. However, this paper exposes an important bias in Perspective API concerning German language text. Through an in-depth examination of several datasets, we uncover intrinsic language biases within the multilingual model of Perspective API. We find that the toxicity assessment of German content produces significantly higher toxicity levels than other languages. This finding is robust across various translations, topics, and data sources, and has significant consequences for both research and moderation strategies that rely on Perspective API. For instance, we show that, on average, four times more tweets and users would be moderated when using the German language compared to their English translation. Our findings point to broader risks associated with the widespread use of proprietary APIs within the computational social sciences.
format Preprint
id arxiv_https___arxiv_org_abs_2312_12651
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Toxic Bias: Perspective API Misreads German as More Toxic
Nogara, Gianluca
Pierri, Francesco
Cresci, Stefano
Luceri, Luca
Törnberg, Petter
Giordano, Silvia
Social and Information Networks
Proprietary public APIs play a crucial and growing role as research tools among social scientists. Among such APIs, Google's machine learning-based Perspective API is extensively utilized for assessing the toxicity of social media messages, providing both an important resource for researchers and automatic content moderation. However, this paper exposes an important bias in Perspective API concerning German language text. Through an in-depth examination of several datasets, we uncover intrinsic language biases within the multilingual model of Perspective API. We find that the toxicity assessment of German content produces significantly higher toxicity levels than other languages. This finding is robust across various translations, topics, and data sources, and has significant consequences for both research and moderation strategies that rely on Perspective API. For instance, we show that, on average, four times more tweets and users would be moderated when using the German language compared to their English translation. Our findings point to broader risks associated with the widespread use of proprietary APIs within the computational social sciences.
title Toxic Bias: Perspective API Misreads German as More Toxic
topic Social and Information Networks
url https://arxiv.org/abs/2312.12651