In Search of a Conspiracy A Practical Guide for Identifying Conspiracy Theories in Unstructured Textual Data
In Search of a Conspiracy A Practical Guide for Identifying Conspiracy Theories in Unstructured Textual Data

Summary/Abstract: Our study aims to describe a computer-aided method of searching for conspiracy thinking inunstructured textual data. Collecting such data from the Internet usually involves using keywords to find relevantdocuments for further analysis. Although this step determines the results, many researchers select keywordsarbitrarily without evaluating their tools. We introduced a method of keyword expansion that combines wordembeddings and human cognitive abilities to identify potential keywords. In our study, we found that the relativelyinformed participants (N = 154) could not recall even a short list of relevant keywords, and the ones they selectedwere mostly useless in detecting conspiracy thinking. The designed Conspiracy Thinking Index performed betterin detecting conspiracy-related text in a large text corpus (≈ 1.1M tweets) than supervised machine learningalgorithms while remaining simple and transparent.

• Details
• Contents