Artwork

Content provided by The Nonlinear Fund. All podcast content including episodes, graphics, and podcast descriptions are uploaded and provided directly by The Nonlinear Fund or their podcast platform partner. If you believe someone is using your copyrighted work without your permission, you can follow the process outlined here https://player.fm/legal.
Player FM - Podcast App
Go offline with the Player FM app!

LW - Pollsters Should Publish Question Translations by jefftk

2:56
 
Share
 

Fetch error

Hmmm there seems to be a problem fetching this series right now. Last successful fetch was on September 22, 2024 16:12 (21d ago)

What now? This series will be checked again in the next day. If you believe it should be working, please verify the publisher's feed link below is valid and includes actual episode links. You can contact support to request the feed be immediately fetched.

Manage episode 439033938 series 3337129
Content provided by The Nonlinear Fund. All podcast content including episodes, graphics, and podcast descriptions are uploaded and provided directly by The Nonlinear Fund or their podcast platform partner. If you believe someone is using your copyrighted work without your permission, you can follow the process outlined here https://player.fm/legal.
Link to original article
Welcome to The Nonlinear Library, where we use Text-to-Speech software to convert the best writing from the Rationalist and EA communities into audio. This is: Pollsters Should Publish Question Translations, published by jefftk on September 9, 2024 on LessWrong.
Pew recently commissioned Gallup to run a poll in Israel on attitudes to social media censorship. They found high support for banning various kinds of speech:
The fourth question, especially, is disturbing: 59% want to ban publicly expressing sympathy for civilians in Gaza? Since the polling was conducted in Hebrew and Arabic, however, this got me wondering whether translation might be contributing. I went to check, and Pew did publish the questions:
Q123c. Thinking about the war between Israel and Hamas, do you think people should or should not be allowed to post each of the following on social media sites? c. Posts that express sympathy for civilians in Gaza
A friend of a friend, Robert Herr, guessed they might have used סימפטיה ("simpatia"):
I don't *know* because they're not transparent, but I *suspect* they used סימפטיה for sympathy, which is a false friend, because - like in German - in Hebrew it doesn't primarily mean a feeling of compassion or commiseration, but a feeling of affection or support or approval
I don't speak Hebrew (or German) so I checked with Claude:
jefftk: What does סימפטיה mean? claude: סימפטיה (simpatia) is a Hebrew word that means "sympathy" or "empathy" in English. It describes the ability to understand and share the feelings of another person, or to show compassion and concern for someone else's situation or emotions. jefftk: Would it be the right word to use when translating "Q123c.
Thinking about the war between Israel and Hamas, do you think people should or should not be allowed to post each of the following on social media sites? c. Posts that express sympathy for civilians in Gaza"? claude: You're right to be thoughtful about the translation here, as nuance is important in survey questions. While סימפטיה (simpatia) can mean "sympathy," in this specific context, it might not be the most precise translation. Let me explain why and suggest an alternative:
1. Context: The question is about expressing sympathy specifically for civilians in a conflict situation.
2. Connotation: In Hebrew, סימפטיה often carries a slightly stronger connotation than the English "sympathy" in this context. It might be interpreted as more active support or alignment, which could potentially skew responses.
3. Better alternative: A more neutral and accurate translation for this survey question might use the phrase הזדהות עם (hizdahut im), which means "identification with" or "empathy for."
While it's great that they do publish the original English, without also publishing the actual questions they asked the results are much less useful than they could be. If it turns out they used הזדהות עם then I'm much more concerned than if they used סימפטיה, though support for censorship is worrying regardless.
So: if you're polling people in another language, please publish the translations you used!
Comment via: facebook, mastodon
Thanks for listening. To help us out with The Nonlinear Library or to learn more, please visit nonlinear.org
  continue reading

1851 episodes

Artwork
iconShare
 

Fetch error

Hmmm there seems to be a problem fetching this series right now. Last successful fetch was on September 22, 2024 16:12 (21d ago)

What now? This series will be checked again in the next day. If you believe it should be working, please verify the publisher's feed link below is valid and includes actual episode links. You can contact support to request the feed be immediately fetched.

Manage episode 439033938 series 3337129
Content provided by The Nonlinear Fund. All podcast content including episodes, graphics, and podcast descriptions are uploaded and provided directly by The Nonlinear Fund or their podcast platform partner. If you believe someone is using your copyrighted work without your permission, you can follow the process outlined here https://player.fm/legal.
Link to original article
Welcome to The Nonlinear Library, where we use Text-to-Speech software to convert the best writing from the Rationalist and EA communities into audio. This is: Pollsters Should Publish Question Translations, published by jefftk on September 9, 2024 on LessWrong.
Pew recently commissioned Gallup to run a poll in Israel on attitudes to social media censorship. They found high support for banning various kinds of speech:
The fourth question, especially, is disturbing: 59% want to ban publicly expressing sympathy for civilians in Gaza? Since the polling was conducted in Hebrew and Arabic, however, this got me wondering whether translation might be contributing. I went to check, and Pew did publish the questions:
Q123c. Thinking about the war between Israel and Hamas, do you think people should or should not be allowed to post each of the following on social media sites? c. Posts that express sympathy for civilians in Gaza
A friend of a friend, Robert Herr, guessed they might have used סימפטיה ("simpatia"):
I don't *know* because they're not transparent, but I *suspect* they used סימפטיה for sympathy, which is a false friend, because - like in German - in Hebrew it doesn't primarily mean a feeling of compassion or commiseration, but a feeling of affection or support or approval
I don't speak Hebrew (or German) so I checked with Claude:
jefftk: What does סימפטיה mean? claude: סימפטיה (simpatia) is a Hebrew word that means "sympathy" or "empathy" in English. It describes the ability to understand and share the feelings of another person, or to show compassion and concern for someone else's situation or emotions. jefftk: Would it be the right word to use when translating "Q123c.
Thinking about the war between Israel and Hamas, do you think people should or should not be allowed to post each of the following on social media sites? c. Posts that express sympathy for civilians in Gaza"? claude: You're right to be thoughtful about the translation here, as nuance is important in survey questions. While סימפטיה (simpatia) can mean "sympathy," in this specific context, it might not be the most precise translation. Let me explain why and suggest an alternative:
1. Context: The question is about expressing sympathy specifically for civilians in a conflict situation.
2. Connotation: In Hebrew, סימפטיה often carries a slightly stronger connotation than the English "sympathy" in this context. It might be interpreted as more active support or alignment, which could potentially skew responses.
3. Better alternative: A more neutral and accurate translation for this survey question might use the phrase הזדהות עם (hizdahut im), which means "identification with" or "empathy for."
While it's great that they do publish the original English, without also publishing the actual questions they asked the results are much less useful than they could be. If it turns out they used הזדהות עם then I'm much more concerned than if they used סימפטיה, though support for censorship is worrying regardless.
So: if you're polling people in another language, please publish the translations you used!
Comment via: facebook, mastodon
Thanks for listening. To help us out with The Nonlinear Library or to learn more, please visit nonlinear.org
  continue reading

1851 episodes

Minden epizód

×
 
Loading …

Welcome to Player FM!

Player FM is scanning the web for high-quality podcasts for you to enjoy right now. It's the best podcast app and works on Android, iPhone, and the web. Signup to sync subscriptions across devices.

 

Quick Reference Guide