The Expected Parrot Domain-Specific Language (EDSL) package makes it easy to conduct computational social science and market research with AI. Use it to design surveys and experiments, collect responses from humans and large language models, and perform data labeling and many other research tasks. Results are formatted as specified datasets and come with built-in methods for analyzing, visualizing and sharing.
- PyPI:
pip install edsl - Documentation
- Starter tutorial
- EDSL is compatible with Python 3.9 - 3.12.
- API keys for language models. You can use your own keys or an Expected Parrot key that provides access to all available models. See instructions on managing keys and model pricing and performance information.
An integrated platform for running experiments, sharing workflows and launching hybrid human/AI surveys.
A quick example:
# Import a question type
from edsl import QuestionMultipleChoice, Agent, Model
# Construct a question
q = QuestionMultipleChoice(
question_name = "research",
question_text = "What is the worst part of conducting research?",
question_options = [
"Securing funding",
"Finding reliable data sources",
"Publishing in reputable journals",
"Balancing research with other responsibilities",
"Dealing with peer review feedback"
]
)
# Create an agent
a = Agent(traits = {"persona":"You are a researcher."})
# Select a model
m = Model("gemini-1.5-flash")
# Administer the question
results = q.by(a).by(m).run()
# Inspect the results
results.select("research")Output:
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┓
┃ answer.research ┃
┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┩
│ Balancing research with other responsibilities │
└──────────────────━━━━━━━━━━━━━━━━━━━━━━━───────┘