In this week’s social intelligence stories that caught our attention, we have the signals to mass shooting, social media data and algorithm enquiry, ISIS on TikTok, Broadway social analytics, sarcasm detection, and Twitter’s ban on political ads.
How to tell when social media posts signal a mass shooter in the making
Across at Fast Company, Katharine Schwab teams up with computer scientist Anna Rumshisky to collect and analyse more than 185,000 words of extremist or hateful narratives published online by people who have then gone on to commit large scale shootings or terrorist crimes as well as a second sample of 50,000 words published online who did not go on to kill. They wanted to find whether they could identify signals in online posts that could help police and other officials tell the difference between people who are upset and ranting and those who intend to do real physical harm. Read the full article to find out the results.
Republican FTC commissioner seeks social media inquiry
Christine Wilson, the Republican FTC Commission wants her agency to prove how social media companies use consumers’ information to shape the algorithms that determine what their users see and read. Could this open the floodgates to more probing and laying groundwork for new legislation?
Islamic State turns to teen-friendly TikTok
The Wall Street Journal reported that Storyful, the social media intelligence agency, had identified around two dozen accounts on TikTok connected to ISIS. Publishing short propaganda videos to connect with teenagers.
Read the full article here. (gated content)
Broadway Social Analytics
A little niche but it is interesting to see moves to quantify what’s happening online around Broadway. With most ticket sales, purchasing decisions, and fan experience happening online, a Broadway show’s digital presence is important. The exclusive data highlights the top growing plays, musicals and upcoming productions. For us, the analytics will be a little basic, but food for thought on how to make them more meaningful?
Sarcasm detection: a step towards sentiment analysis
This article outlines a new approach for sarcasm detection. This was the basis of a summer internship project at Forsk-Labs. If you’re not technical, this one isn’t for you are you can obtain the QR Code to the GitHub repo.
Twitter bans political advertising
Unless you’ve been offline, not watching the news or picked up a newspaper you’ll have seen the news that Twitter has banned political advertising on the platform. The changes will come into play on the 22nd of November, and will affect both candidate ads and issue ads, although ads encouraging voter registration will still be allowed, along with other expectations. The full policy will be available on the 15th of November.
There’s been mass online discussion on the bold move – some in favour and others questioning the move. What do you think?