This Algorithm Can Predict Relationship Trouble
Science Quickly
Scientific American
4.4 • 1.4K Ratings
🗓️ 5 July 2016
⏱️ 2 minutes
🧾️ Download transcript
Summary
Transcript
Click on a timestamp to play from that location
| 0:00.0 | This is Scientific Americans 60 Second Science. I'm Erica Barris. Got a minute? |
| 0:07.0 | Watch your tone because it turns out it really isn't what you say. It's how you say it, at least when it comes to |
| 0:14.8 | couples and couples counseling. That's according to a study in proceedings of |
| 0:19.2 | inter-speech. Researchers developed a computer algorithm to gauge relationships between spouses based on their vocal patterns. |
| 0:27.0 | Working with hundreds of recorded conversations from marriage therapy sessions collected over two years, |
| 0:32.0 | the algorithm was able to predict whether a relationship |
| 0:35.3 | was going to get better or worse with an accuracy of just under 80%. |
| 0:41.2 | How they did it? |
| 0:42.2 | The recordings were divided by acoustic features that used speech processing techniques to track pitch and voice warble and intensity. |
| 0:50.0 | These clips from the researcher's training video illustrate psychological states that characterize distressed relationships. |
| 0:57.0 | This one, for example, shows negative effect and reactivity, behaviors that relationship experts believe are troublesome. |
| 1:05.0 | I want you to just come home at a more reasonable time, rather than walking in the door at 11. |
| 1:13.0 | I just don't think you understand how much I have to do, like what my work entails. |
| 1:20.0 | What is there to understand? |
| 1:22.0 | The counseling sessions were also tested against behavior. But what is there to understand? |
| 1:22.7 | The counseling sessions were also tested against behavioral analyses with codes for positives |
| 1:27.6 | such as acceptance and the negatives such as blame. |
| 1:31.5 | Using only that more standardized research method wasn't as |
| 1:34.7 | predictable as listening to the vocal expressions. Now these examples are |
| 1:39.1 | negative as the researchers focused on distressed relationship dynamics. |
| 1:44.0 | One could imagine the algorithms may also work the same way when looking at positive vocal patterns. |
| 1:50.0 | Because even married couples sometimes say nice things to each other. |
... |
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 2026.

