Download full text
(192.8Kb)
Citation Suggestion
Please use the following Persistent Identifier (PID) to cite this document:
https://doi.org/10.48541/dcr.v12.22
Exports for your reference manager
The accuracy trap or How to build a phony classifier
[collection article]
This document is a part of the following document:
Challenges and perspectives of hate speech research
Abstract This guide explains, in four steps, how to build a phony text classifier using supervised machine learning - a classifier that is absolutely unreliable but looks outwardly sophisticated and attractive. You might enjoy this text if one or more of the following statements apply to you: You are interes... view more
This guide explains, in four steps, how to build a phony text classifier using supervised machine learning - a classifier that is absolutely unreliable but looks outwardly sophisticated and attractive. You might enjoy this text if one or more of the following statements apply to you: You are interested in the automated identification of hate speech or related content in online discussions, as long as it looks good; you want to do something with machine learning to impress your peer group, but you do not have the nerve to dig deep into this field as well; you are either a somewhat sneaky or a humorous person. Of course, however, if you are a good and decent researcher, you might also take hints from this text on how not to step into the accuracy trap and how not to fall for the tricks of phony classification.... view less
Keywords
online media; language usage; hate; content analysis; automation
Classification
Basic Research, General Concepts and History of the Science of Communication
Media Contents, Content Analysis
Free Keywords
machine learning; hate speech; incivility
Collection Title
Challenges and perspectives of hate speech research
Editor
Strippel, Christian; Paasch-Colberg, Sünje; Emmer, Martin; Trebbe, Joachim
Document language
English
Publication Year
2023
City
Berlin
Page/Pages
p. 371-381
Series
Digital Communication Research, 12
ISSN
2198-7610
ISBN
978-3-945681-12-1
Status
Primary Publication; peer reviewed