Get the latest market trends in your inbox

Stay on top of the latest market trends and economic insights with the Axios Markets newsletter. Sign up for free.

Please enter a valid email.

Please enter a valid email.

Subscription failed
Thank you for subscribing!

Catch up on coronavirus stories and special reports, curated by Mike Allen everyday

Catch up on coronavirus stories and special reports, curated by Mike Allen everyday

Please enter a valid email.

Please enter a valid email.

Subscription failed
Thank you for subscribing!

Denver news in your inbox

Catch up on the most important stories affecting your hometown with Axios Denver

Please enter a valid email.

Please enter a valid email.

Subscription failed
Thank you for subscribing!

Des Moines news in your inbox

Catch up on the most important stories affecting your hometown with Axios Des Moines

Please enter a valid email.

Please enter a valid email.

Subscription failed
Thank you for subscribing!

Minneapolis-St. Paul news in your inbox

Catch up on the most important stories affecting your hometown with Axios Minneapolis-St. Paul

Please enter a valid email.

Please enter a valid email.

Subscription failed
Thank you for subscribing!

Tampa-St. Petersburg news in your inbox

Catch up on the most important stories affecting your hometown with Axios Tampa-St. Petersburg

Please enter a valid email.

Please enter a valid email.

Subscription failed
Thank you for subscribing!

Please enter a valid email.

Please enter a valid email.

Subscription failed
Thank you for subscribing!

In London, an argument over apartments, 1969. Photo: William Lovelace/Daily Express/Hulton Archive/Getty

Among efforts to make social media a more congenial place, researchers at Cornell are working on artificial intelligence that detects nasty online conversations when they are only starting to take that turn.

What's going on: Most studies of online conversation look for phrases such as, "What the hell is wrong with you.” But, by then, it's too late. In their new paper, Justine Zhang, Jonathan Chang and Cristian Danescu-Niculescu-Mizil say they aim to ferret out anti-social clues "when the conversation is still salvageable."

How they did it: The Cornell team studied some 1,200 conversations on Wikipedia Talk pages, reports MIT Tech Review, in a collaboration with researchers from Jigsaw and Wikimedia.

Among their findings:

  • Cues of civil conversations include greetings and gratitude as well as opinions that are hedged.
  • Conversations going bad feature sentences starting with the word "you," which signals potential trouble.

That won't surprise many of us: The researchers found that humans are still better at this than AI — a control group of humans detected a bad conversation in advance 72% of the time, compared with 61.6% for the AI.

  • Yet if all humans were terrific at heading off online battles, we would not be in some of the mess we currently confront. In other words, early detection would be a good thing.

One bit of good news: In some of the conversations their AI had flagged, the humans eventually self-corrected.

  • The paper concludes, "Interactions which initially seem prone to attacks can nonetheless maintain civility, by way of level-headed interlocutors, as well as explicit acts of reparation."

Go deeper

Biden plans to ask public to wear masks for first 100 days in office

Joe Biden. Photo: Mark Makela/Gettu Images

President-elect Joe Biden and Vice President-elect Kamala Harris sat down with CNN on Thursday for their first joint interview since the election.

The big picture: In the hour-long segment, the twosome laid out plans for responding to the pandemic, jump-starting the economy and managing the transition of power, among other priorities.

Caitlin Owens, author of Vitals
32 mins ago - Health

Coronavirus death rates rising across the country

Expand chart
Data: The COVID Tracking Project, Census Bureau; Cartogram: Andrew Witherspoon/Axios

Daily coronavirus-related deaths in the U.S. hit a new record on Wednesday, when roughly 2,800 people died from the virus.

The big picture: Caseloads and hospitalizations continue to rise, and deaths are spiking in states all across the country.

32 mins ago - World

Ratcliffe's long-term China play

Ratcliffe testifies before the Senate Intelligence Committee in May. Photo: Andrew Harnik-Pool/Getty Images

Director of National Intelligence John Ratcliffe told Axios in an interview Thursday that "China and China alone is the only country that has the ability to compete with the U.S." — and hopes the intelligence community will adopt his view even under "the next administration."

Why it matters: Ratcliffe's comments suggested that he's trying to lock in the Trump era's harder line on China for the long term.