meta_pixel
Tapesearch Logo
Log in
Science Quickly

Mine Social Media Posts to Predict Flu

Science Quickly

Scientific American

Science

4.2639 Ratings

🗓️ 17 April 2018

⏱️ 3 minutes

🧾️ Download transcript

Summary

Researchers used Twitter searches for nonflu words associated with behavior to predict flu outbreaks two weeks in advance. Learn more about your ad choices. Visit megaphone.fm/adchoices

Transcript

Click on a timestamp to play from that location

0:00.0

Understanding the human body is a team effort. That's where the Yachtel group comes in.

0:05.8

Researchers at Yachtolt have been delving into the secrets of probiotics for 90 years.

0:11.0

Yacold also partners with nature portfolio to advance gut microbiome science through the global grants for gut health, an investigator-led research program.

0:19.6

To learn more about Yachtolt, visit yawcult.co.

0:22.7

.jp.j. That's Y-A-K-U-L-T.C-O.jp. When it comes to a guide for your gut, count on Yacolt.

0:33.7

Hi, I'm Scientific American Podcast editor Steve Merski, and here's a short piece from the April

0:39.2

issue of the magazine in the section we call advances, dispatches from the frontiers of science,

0:45.2

technology, and medicine.

0:48.3

Hashtag flu by Rachel Berkowitz.

0:52.7

Forecasting influenza outbreaks before they strike could help officials take early action

0:57.8

to reduce related deaths, which total 290,000 to 650,000 worldwide every year.

1:06.4

In a recent study, researchers say they have accurately predicted outbreaks up to two weeks in advance

1:12.3

using only the content of social media conversations. The findings could theoretically be used

1:18.6

to direct resources to areas that will need them most. A team at the Pacific Northwest National

1:24.6

Laboratory in Washington State gathered linguistic cues from Twitter conversations

1:29.4

about seemingly non-flu-related topics, such as the weather or coffee. Based on this information,

1:36.9

the researchers nailed down when and where the next flu outbreaks were likely to occur. The researchers

1:43.3

used what's called a deep learning computer model

1:46.5

that mimics the layers of neurons and memory capabilities of the human brain. Their algorithm

1:52.5

analyzed how Twitter language style, opinions, and communication behaviors changed in a given

1:59.2

period and how such changes related to later reports of flu outbreaks.

2:04.5

The study was published in the journal PLOS 1. Computer scientists Svetlana Volkova, who led the study,

...

Please login to see the full transcript.

Disclaimer: The podcast and artwork embedded on this page are from Scientific American, and are the property of its owner and not affiliated with or endorsed by Tapesearch.

Generated transcripts are the property of Scientific American and are distributed freely under the Fair Use doctrine. Transcripts generated by Tapesearch are not guaranteed to be accurate.

Copyright © Tapesearch 2025.