Publications

Modeling Social Readers: Novel Tools for Addressing Reception from Online Book Reviews
Code Base @ OSF
Royal Society Open Science (under review)
We develop a suite of novel NLP tools that comprise semi-supervised event sequencing and impressions’ extraction from Book reviews from on Goodreads.com.

Conspiracy in the time of corona: automatic detection of emerging COVID-19 conspiracy theories in social media and the news
Code Base @ GitHub
Journal of Computational Social Science
We show how the various narrative frameworks fueling stories on the internet rely on the alignment of otherwise disparate domains of knowledge, and consider how they attach to the broader reporting on the pandemic. Our processing architecture employs interlocking NLP tools to extract open information.

An Automated Pipeline for Character and Relationship Extraction from Readers Literary Book Reviews on Goodreads.com
ACM WebSci’ 2020
We develop a pipeline of interlocking automated methods to extract key characters and their relationships, and apply it to thousands of reviews and comments posted on Goodreads.com. We manually derive the ground truth narrative framework from SparkNotes, and then use word embedding tools to compare relationships in ground truth networks with our extracted networks. We find that our automated methodology generates highly accurate consensus narrative frameworks.

In the News

[Spectrum] Artificial Intelligence Separates Conspiracy Theory From Conspiracy Fact
[Spokus] Le complotisme au temps du corona
[BBC] Conspiracies: The Secret Knowledge - Narrative Graphs
[Analytics Insight] Fighting Conspiracy Theories in SMS using Artificial Intelligence
[Ars Technica] Folklore structure reveals how conspiracy theories emerge, fall apart
[The Conversation] An AI tool can distinguish between a conspiracy theory and a true conspiracy
[UCLA Newsroom] How conspiracy theories emerge – and how their storylines fall apart
[Newsy] Experts Say QAnon Likely To Keep Evolving Even Without Trump In Office