We could have predicted the events of January 6th from Parler's data - 8 minutes read
Violent hashtag frequencies in Parler
I ran a crawler to collect posts and comments on the Parler social network for months before Amazon shut them down. Parler was a poorly-engineered app that hosted a wide range of hate speech, conspiracy theories, threats of violence, and disinformation.
Users could only search posts on Parler (called “Parleys”) by hashtags, not by the text content within the post itself. This led users to liberally apply hashtags within any Parley that they wished to disseminate widely, unknowingly providing valuable metadata to researchers like myself.
For example, here is a random Parley from January 6th in Washington D.C.
#trump had to allow #mikepence to sign his own death warrant…..
#TraitorPence #GITMO #firingsquad
#ALLorNOTHING #2theEND #wildDC #magarally #wildprotest
#saveamericarally #trumprally #dc #ArrestPence #traitorVP
#JAN6 the new #911….. #makethempay #retribution
Hanging politicians goes viral on Parler
Relative frequency of hashtags that call for execution by hanging — e.g. “pelosi4gallows”, “hangtraitors”, “bringbackpublicexecutions”, etc. Yes, those are real hashtags that were widely used.The notion of murdering politicians was widely discussed on Parler for months before the 2020 US election, and these posts were never moderated. The relative frequency of hashtags involving hanging/execution more than doubles after the 2020 US election (blue vertical line above), more than triples on the day of the Electoral College vote (green line), and is an order of magnitude higher on the day of the Capitol riot (red line).
It is clear that Parler allowed the idea of attacking and hanging politicians to spread virally on the platform, either through gross negligence or willing ignorance. This idea manifested itself in the gallows erected outside the US Capitol on January 6th. The gallows are a reference to the white supremacist literature The Turner Diaries, in which a “Day of the Rope” features politicians hung en masse.
A reference to the “Day of the Rope” where dissenters from white supremacist groupthink are systematically murdered, followed in the story by violent reprisals against non-whites and nuclear armageddon.Below is a word cloud of hashtags associated with posts that explicitly mention murdering specific politicians (Nancy Pelosi, Joe Biden, AOC, and even lesser-known Democrats like Eric Swalwell).
Hashtags that show up more frequently have a larger font, and it should be no surprise that many of the 45th president’s campaign slogans are so closely associated.In the graph below, hashtags are connected and placed closer together when they are frequently mentioned together. Tags are grouped into communities that are frequently mentioned together, and edges span across communities to indicate association between various topics of discussion.
Visualizing discussion topics on Parler and how various discussions are linked by analyzing hashtag correlation.Exploring the dataset
I use the Wolfram Language for analysis, which allows me to sample and search the dataset around particular topics of discussion. As I randomly perused based on hashtags in the discussion graph above, I realized how difficult moderating this kind of conversation would be. For example, consider the post below:
The author of the post is sharing a book on guerilla warfare that is available on Amazon. I can look up the post author by their user ID, and from their other posts and comments it is obvious that they are trying to incite guerilla warriors to attack the “deep state”. Amazon is wise to not provide a platform for this information to disseminate digitally, but are they simply pushing these people back to the printing press? And at what point does a book on guerilla warfare become too dangerous to provide a platform to? These are questions that I don’t think will be answered consistently for a long time, and will instead be decided by the pressure of public outrage every time a mass shooting or violent protest breaks out.
The next viral hashtag
I think people with radical ideas seek to simply make as many people as possible aware of their ideas, so they can recruit the most radical of these people to support them. In the aftermath of the January 6th insurrection, there was one particular class of hashtags that sought greater awareness.
The use of hashtags calling for civil war increased by around 30% after the failed insurrection at the Capitol.The hashtags related to civil war are frequently associated with the Boogaloo movement and the campaign of Donald Trump. This is particularly frightening for those of us living in America — I am predicting we will see the real-world effects of this radicalization within the coming months.
Using the Wolfram Language to visualize relative frequency of hashtags with the given keywords. You can see toward the end that posts about hanging politicians are being replaced by posts calling for civil war.Community associations of hashtags — these groups of tags are frequently mentioned together. Yellow and green are references to the Boogaloo movement, purple hashtags typically involve violence and anti-establishment topics, while red tags are typically associated with Donald Trump.In a world of 24-hour news cycles and the proliferation of online disinformation, hashtags are ostensibly correlated to whatever is popular on the Internet at a particular time. Because of the simplistic nature most users would simply “echo” the posts of others (the Parler equivalent of a retweet), the hash tags and post IDs allow ideas to be “contact traced” across the network. In a future post, I will share my research on ways to measure the contagiousness of an idea and to quantify how radicalized a user has become.
Word cloud for hashtags on posts that explicitly call for civil war in America.The QAnon conspiracy
There are a substantial number of Americans (at least 100,000 on Parler and two sitting US congresswomen) who believe there is a vast global conspiracy by a cabal of Satan-worshipping pedophiles to consolidate power, and that Donald Trump is secretly trying to bring them down. One distinct feature of the QAnon conspiracy is how new layers of rationalization are continuously added through widely disseminated videos — unlike the moon landing conspiracies, QAnon’s purported conspiracy is ongoing, and continuously adapting to current events. As the theory evolves, it provides opportunities for anyone on the Internet to insert more dangerous ideas into it.
QAnon posts on Parler are frequently associated with COVID denial and a belief that Bill Gates/George Soros orchestrated the pandemic, with the “evidence” often presented in poorly-edited videos.This is a popular QAnon post taken from a random sample of the dataset. It has been viewed over 181,000 times, reposted over a thousand times, upvoted over a thousand times, and has a truly spectacular thread of 319 comments attached to it, of which ~10% explicitly call for the murder of George Soros, and over half express contempt toward the Black Lives Matter movement.
What’s next
This is a work in progress. The Internet Archive is putting together a far more comprehensive dataset of posts, images, comments, users, and media from Parler which I recommend to data scientists looking to take up this project. My future plans for this project are:
Perform NLP and sentiment analysis on the comments that users leave on posts, and identify which hashtags are associated with which sentiments
Analysis of disinformation sites, the rate at which they propagate across the Parler social network, and the hashtags most frequently associated with each one
Quantifying the radicalization of a user by showing a statistically-significant trend toward more violent ideas and hashtags
Clean up the data and make it publicly accessible to researchers
You can contact me about this post and to request access to the dataset by messaging me on Twitter or emailing parlerdatascientist.com. I will be keeping my identity concealed for obvious reasons — there is panic among the ex-Parler community that all their data, even private/deleted posts, have been scraped and archived — it has, just not by me. Furthermore, Parler did not follow industry standards in obfuscating EXIF metadata from uploaded images, so millions of users had their exact location logged.
Please don’t make the problem worse
I do not think the average Parler user deserves to be victimized, called a fascist, or have their privacy taken from them. I will not be taking part in anything like that.
The people who committed crimes should be treated as criminals. However, there were some pretty violent sociopaths on Parler who need compassion and mental help, not provocation from doxxers. I believe we need to study how technology enabled a group of people to radicalize each other and reinforced an echo chamber of conspiracies and racism.
Disclaimer: since Parler has never enforced their Terms of Service with regards to violent speech, I slept fine at night ignoring their ToS with regards to automated scraping of the site.
Source: Medium
Powered by NewsAPI.org