How Pew Research Center is – and is not – using large language models in our work
In this post, we’ll share our current guidelines for the internal use of large language models and potential areas of experimentation.
A behind-the-scenes blog about research methods at Pew Research Center.
For our latest findings, visit pewresearch.org.
Latest from Decoded
-
What a survey experiment tells us about measuring religious tolerance in Australia
We ran a survey experiment on religious tolerance in Australia to examine whether respondents’ answers capture a general distaste for religion rather than intolerance for particular religious groups.
-
Measuring partisanship in Europe: How online survey questions compare with phone polls
We compared three different online survey methods in certain countries to see which one would most closely replicate our phone results.
-
Reproducibility as part of code quality control
In this post, we discuss reproducibility as a part of Pew Research Center’s code review process.
-
Redacting identifying information with computational methods in large text data
In this post, we discuss three methods to identify and remove specific words and phrases in unstructured text data.
-
How we adopted Kubernetes for our data science infrastructure
In this post, we delve into Kubernetes – the back-end tool that powers the systems our research team interacts with.
-
Improving our website’s accessibility with alt text for charts
Our approach to alt text – and overall website accessibility – has evolved in recent years.
-
How adding a ‘Don’t know’ response option can affect cross-national survey results
In our surveys, people are much less likely to skip questions online than when speaking to interviewers in person or on the phone; we explore how offering a “Don’t know” option in online surveys affects results.
-
What Twitter users say versus what they do: Comparing survey responses with observed behaviors
We explore the connection between Americans’ survey responses and their digital activity using data from our past Twitter research.
-
Assessing the effects of generation using age-period-cohort analysis
In this piece, we demonstrate how to conduct age-period-cohort analysis, a statistical tool, to determine the effects of generation.
-
Can machines compete with humans in transcribing audio? A case study using sermons from U.S. religious services
To test whether machine transcription would be practical for studies of sermons in 2019 and 2020, we compared human and machine transcriptions of snippets from a random sample of 200 audio and video sermons.
Search All Decoded Posts
To search or browse all of Pew Research Center findings and data by topic, visit pewresearch.org
About Decoded
This is a blog about research methods and behind-the-scenes technical matters at Pew Research Center. To get our latest findings, visit pewresearch.org.
Copyright 2024 Pew Research Center