Exploring real world survey contexts

This notebook explores ways of specifying “contexts” in which an EDSL survey is administered to AI agents in order to investigate potential impacts to simulated responses. We show how to do this in three different ways by modifying our Question texts and Agent traits in order to reflect various hypothetical real world contexts.

EDSL is an open-source library for simulating surveys, experiments and other research with AI agents and large language models. Before running the code below, please ensure that you have installed the EDSL library and either activated remote inference from your Coop account or stored API keys for the language models that you want to use with EDSL. Please also see our documentation page for tips and tutorials on getting started using EDSL.

Thank you to Sophia Kazinnik for this idea and helpful suggestions!

Importing the tools

[1]:

from edsl import QuestionLinearScale, Scenario, ScenarioList, Agent, AgentList, Survey, Model

Selecting a model

Here we show the available language models and select one:

[2]:

Model.available()

[2]:
Model Name Service Name Code
Austism/chronos-hermes-13b-v2 deep_infra 0
BAAI/bge-base-en-v1.5 together 1
BAAI/bge-large-en-v1.5 together 2
Gryphe/MythoMax-L2-13b deep_infra 3
Gryphe/MythoMax-L2-13b together 4
Gryphe/MythoMax-L2-13b-Lite together 5
Meta-Llama/Llama-Guard-7b together 6
NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO together 7
NousResearch/Nous-Hermes-2-Yi-34B together 8
Qwen/Qwen1.5-110B-Chat together 9
Qwen/Qwen1.5-72B-Chat together 10
Qwen/Qwen2-72B-Instruct deep_infra 11
Qwen/Qwen2-72B-Instruct together 12
Qwen/Qwen2-7B-Instruct deep_infra 13
Qwen/Qwen2.5-72B-Instruct deep_infra 14
Salesforce/Llama-Rank-V1 together 15
Sao10K/L3-70B-Euryale-v2.1 deep_infra 16
Sao10K/L3.1-70B-Euryale-v2.2 deep_infra 17
WhereIsAI/UAE-Large-V1 together 18
amazon.titan-text-express-v1 bedrock 19
amazon.titan-text-lite-v1 bedrock 20
anthropic.claude-3-5-sonnet-20240620-v1:0 bedrock 21
anthropic.claude-3-haiku-20240307-v1:0 bedrock 22
anthropic.claude-3-opus-20240229-v1:0 bedrock 23
anthropic.claude-3-sonnet-20240229-v1:0 bedrock 24
anthropic.claude-instant-v1 bedrock 25
anthropic.claude-v2 bedrock 26
anthropic.claude-v2:1 bedrock 27
azure:gpt-4o azure 28
azure:gpt-4o-mini azure 29
chatgpt-4o-latest openai 30
claude-3-5-sonnet-20240620 anthropic 31
claude-3-haiku-20240307 anthropic 32
claude-3-opus-20240229 anthropic 33
claude-3-sonnet-20240229 anthropic 34
codellama/CodeLlama-34b-Instruct-hf together 35
codestral-2405 mistral 36
cohere.command-light-text-v14 bedrock 37
cohere.command-r-plus-v1:0 bedrock 38
cohere.command-r-v1:0 bedrock 39
cohere.command-text-v14 bedrock 40
curie:ft-emeritus-2022-11-30-12-58-24 openai 41
curie:ft-emeritus-2022-12-01-01-04-36 openai 42
curie:ft-emeritus-2022-12-01-01-51-20 openai 43
curie:ft-emeritus-2022-12-01-14-16-46 openai 44
curie:ft-emeritus-2022-12-01-14-28-00 openai 45
curie:ft-emeritus-2022-12-01-14-49-45 openai 46
curie:ft-emeritus-2022-12-01-15-29-32 openai 47
curie:ft-emeritus-2022-12-01-15-42-25 openai 48
curie:ft-emeritus-2022-12-01-15-52-24 openai 49
curie:ft-emeritus-2022-12-01-16-40-12 openai 50
cursor/Llama-3-8b-hf together 51
databricks/dbrx-instruct together 52
davinci:ft-emeritus-2022-11-30-14-57-33 openai 53
deepseek-ai/deepseek-llm-67b-chat together 54
gemini-1.0-pro google 55
gemini-1.5-flash google 56
gemini-1.5-pro google 57
gemini-pro google 58
gemma-7b-it groq 59
gemma2-9b-it groq 60
google/gemma-2-27b-it deep_infra 61
google/gemma-2-27b-it together 62
google/gemma-2-9b-it deep_infra 63
google/gemma-2-9b-it together 64
google/gemma-2b-it together 65
gpt-3.5-turbo openai 66
gpt-3.5-turbo-0125 openai 67
gpt-3.5-turbo-1106 openai 68
gpt-3.5-turbo-16k openai 69
gpt-4 openai 70
gpt-4-0125-preview openai 71
gpt-4-0613 openai 72
gpt-4-1106-preview openai 73
gpt-4-turbo openai 74
gpt-4-turbo-2024-04-09 openai 75
gpt-4-turbo-preview openai 76
gpt-4o openai 77
gpt-4o-2024-05-13 openai 78
gpt-4o-2024-08-06 openai 79
gpt-4o-2024-11-20 openai 80
gpt-4o-audio-preview openai 81
gpt-4o-audio-preview-2024-10-01 openai 82
gpt-4o-mini openai 83
gpt-4o-mini-2024-07-18 openai 84
gpt-4o-realtime-preview openai 85
gpt-4o-realtime-preview-2024-10-01 openai 86
lizpreciatior/lzlv_70b_fp16_hf deep_infra 87
llama-3.1-70b-versatile groq 88
llama-3.1-8b-instant groq 89
llama-3.1-sonar-huge-128k-online perplexity 90
llama-3.1-sonar-large-128k-online perplexity 91
llama-3.1-sonar-small-128k-online perplexity 92
llama-guard-3-8b groq 93
llama3-70b-8192 groq 94
llama3-8b-8192 groq 95
llama3-groq-70b-8192-tool-use-preview groq 96
llama3-groq-8b-8192-tool-use-preview groq 97
meta-llama/Llama-2-13b-chat-hf together 98
meta-llama/Llama-2-70b-hf together 99
meta-llama/Llama-2-7b-chat-hf together 100
meta-llama/Llama-3-70b-chat-hf together 101
meta-llama/Llama-3-8b-chat-hf together 102
meta-llama/LlamaGuard-2-8b together 103
meta-llama/Meta-Llama-3-70B-Instruct deep_infra 104
meta-llama/Meta-Llama-3-70B-Instruct-Lite together 105
meta-llama/Meta-Llama-3-70B-Instruct-Turbo together 106
meta-llama/Meta-Llama-3-8B-Instruct deep_infra 107
meta-llama/Meta-Llama-3-8B-Instruct-Lite together 108
meta-llama/Meta-Llama-3-8B-Instruct-Turbo together 109
meta-llama/Meta-Llama-3.1-405B-Instruct deep_infra 110
meta-llama/Meta-Llama-3.1-405B-Instruct-Turbotogether 111
meta-llama/Meta-Llama-3.1-70B-Instruct deep_infra 112
meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo together 113
meta-llama/Meta-Llama-3.1-8B-Instruct deep_infra 114
meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo together 115
meta-llama/Meta-Llama-Guard-3-8B together 116
meta.llama3-1-405b-instruct-v1:0 bedrock 117
meta.llama3-1-70b-instruct-v1:0 bedrock 118
meta.llama3-1-8b-instruct-v1:0 bedrock 119
meta.llama3-70b-instruct-v1:0 bedrock 120
meta.llama3-8b-instruct-v1:0 bedrock 121
microsoft/Phi-3-medium-4k-instruct deep_infra 122
microsoft/WizardLM-2-7B deep_infra 123
microsoft/WizardLM-2-8x22B deep_infra 124
microsoft/WizardLM-2-8x22B together 125
mistral-embed mistral 126
mistral-large-2407 mistral 127
mistral-medium-latest mistral 128
mistral-small-2409 mistral 129
mistral-small-latest mistral 130
mistral.mistral-7b-instruct-v0:2 bedrock 131
mistral.mistral-large-2402-v1:0 bedrock 132
mistral.mixtral-8x7b-instruct-v0:1 bedrock 133
mistralai/Mistral-7B-Instruct-v0.1 together 134
mistralai/Mistral-7B-Instruct-v0.2 together 135
mistralai/Mistral-7B-Instruct-v0.3 deep_infra 136
mistralai/Mistral-7B-Instruct-v0.3 together 137
mistralai/Mistral-7B-v0.1 together 138
mistralai/Mistral-Nemo-Instruct-2407 deep_infra 139
mistralai/Mixtral-8x22B-Instruct-v0.1 together 140
mistralai/Mixtral-8x7B-Instruct-v0.1 deep_infra 141
mistralai/Mixtral-8x7B-Instruct-v0.1 together 142
mistralai/Mixtral-8x7B-v0.1 together 143
mixtral-8x7b-32768 groq 144
o1-mini openai 145
o1-mini-2024-09-12 openai 146
o1-preview openai 147
o1-preview-2024-09-12 openai 148
omni-moderation-2024-09-26 openai 149
omni-moderation-latest openai 150
open-mistral-7b mistral 151
open-mistral-nemo-2407 mistral 152
open-mixtral-8x22b mistral 153
open-mixtral-8x7b mistral 154
openbmb/MiniCPM-Llama3-V-2_5 deep_infra 155
openchat/openchat_3.5 deep_infra 156
pixtral-12b-2409 mistral 157
test test 158
togethercomputer/StripedHyena-Nous-7B together 159
togethercomputer/m2-bert-80M-2k-retrieval together 160
togethercomputer/m2-bert-80M-32k-retrieval together 161
togethercomputer/m2-bert-80M-8k-retrieval together 162
upstage/SOLAR-10.7B-Instruct-v1.0 together 163
 
[3]:

m = Model("gpt-4o")
m

[3]:

LanguageModel

key value
model gpt-4o
parameters:temperature 0.5
parameters:max_tokens 1000
parameters:top_p 1
parameters:frequency_penalty0
parameters:presence_penalty 0
parameters:logprobs False
parameters:top_logprobs 3

Creating some contexts for our survey

Here we identify some example contexts to use in administering our survey:

[4]:

respondent_ages = [
    "You are a teenager (13-19 years old).",
    "You are college age (20-24 years old).",
    "You are a young adult (25-39 years old).",
    "You are middle-aged (40-59 years old).",
    "You are a senior citizen (60 or more years old).",
]

survey_contexts = [
    "",
    "You are answering an online survey.",
    "You are being interviewed by a researcher.",
    "You are participating in a focus group of peers.",
    "You are participating in a focus group of people of all ages and backgrounds.",
]

Adding contexts to question texts

We can apply contexts by creating versions of our questions where each context is inserted directly into the question texts as a Scenario of the question:

[5]:

q_exercise = QuestionLinearScale(
    question_name="exercise",
    question_text="How many times do you typically exercise each week? ({{age}} {{context}})",
    question_options=[0, 1, 2, 3, 4, 5, 6, 7],
)

q_dessert = QuestionLinearScale(
    question_name="dessert",
    question_text="How many times do you typically eat dessert each week?  ({{age}} {{context}})",
    question_options=[0, 1, 2, 3, 4, 5, 6, 7],
)

survey = Survey(questions = [q_exercise, q_dessert])

[6]:

scenarios = ScenarioList(
    Scenario({"age": a, "context": c}) for a in respondent_ages for c in survey_contexts
)

[7]:

results = survey.by(scenarios).by(m).run()
▼ Remote Job Log (2024-12-14 10:59:20)
Remote inference activated. Sending job to server...
Your survey is running at the Expected Parrot server...
Job sent to server. (Job uuid=0cf3ea67-3164-42fa-8281-ac00633e88b5).
Job status: queued - last update: 2024-12-14 10:59:03 AM
Job status: running - last update: 2024-12-14 10:59:06 AM
Job status: running - last update: 2024-12-14 10:59:10 AM
Job status: running - last update: 2024-12-14 10:59:13 AM
Job status: running - last update: 2024-12-14 10:59:16 AM
[8]:

results.select("age", "context", "exercise", "dessert")

[8]:
scenario.age scenario.context answer.exercise answer.dessert
You are a teenager (13-19 years old). 3 3
You are a teenager (13-19 years old). You are answering an online survey. 4 3
You are a teenager (13-19 years old). You are being interviewed by a researcher. 3 3
You are a teenager (13-19 years old). You are participating in a focus group of peers. 3 3
You are a teenager (13-19 years old). You are participating in a focus group of people of all ages and backgrounds. 3 4
You are college age (20-24 years old). 3 3
You are college age (20-24 years old). You are answering an online survey. 3 3
You are college age (20-24 years old). You are being interviewed by a researcher. 3 3
You are college age (20-24 years old). You are participating in a focus group of peers. 3 3
You are college age (20-24 years old). You are participating in a focus group of people of all ages and backgrounds. 3 3
You are a young adult (25-39 years old). 3 2
You are a young adult (25-39 years old). You are answering an online survey. 3 3
You are a young adult (25-39 years old). You are being interviewed by a researcher. 3 3
You are a young adult (25-39 years old). You are participating in a focus group of peers. 4 2
You are a young adult (25-39 years old). You are participating in a focus group of people of all ages and backgrounds. 3 3
You are middle-aged (40-59 years old). 3 3
You are middle-aged (40-59 years old). You are answering an online survey. 3 2
You are middle-aged (40-59 years old). You are being interviewed by a researcher. 3 3
You are middle-aged (40-59 years old). You are participating in a focus group of peers. 3 2
You are middle-aged (40-59 years old). You are participating in a focus group of people of all ages and backgrounds. 3 2
You are a senior citizen (60 or more years old). 3 0
You are a senior citizen (60 or more years old).You are answering an online survey. 3 2
You are a senior citizen (60 or more years old).You are being interviewed by a researcher. 3 3
You are a senior citizen (60 or more years old).You are participating in a focus group of peers. 3 2
You are a senior citizen (60 or more years old).You are participating in a focus group of people of all ages and backgrounds. 3 2

Adding context to agent traits

Another method is to specify agent traits and survey contexts via Agent traits instead of the question texts:

[9]:

q_exercise = QuestionLinearScale(
    question_name="exercise",
    question_text="How many times do you exercise each week?",
    question_options=[0, 1, 2, 3, 4, 5, 6, 7],
)

q_dessert = QuestionLinearScale(
    question_name="dessert",
    question_text="How many times do you eat dessert each week?",
    question_options=[0, 1, 2, 3, 4, 5, 6, 7],
)

survey = Survey([q_exercise, q_dessert])

[10]:

agents = AgentList(
    Agent(traits={"age": a, "context": c})
    for a in respondent_ages
    for c in survey_contexts
)

[11]:

results = survey.by(agents).by(m).run()
▼ Remote Job Log (2024-12-14 10:59:37)
Remote inference activated. Sending job to server...
Your survey is running at the Expected Parrot server...
Job sent to server. (Job uuid=e6ec390d-b1db-48e7-862d-ec1752decd64).
Job status: queued - last update: 2024-12-14 10:59:21 AM
Job status: queued - last update: 2024-12-14 10:59:24 AM
Job status: running - last update: 2024-12-14 10:59:27 AM
Job status: running - last update: 2024-12-14 10:59:30 AM
Job status: running - last update: 2024-12-14 10:59:34 AM
[12]:

results.select("age", "context", "exercise", "dessert")

[12]:
agent.age agent.context answer.exercise answer.dessert
You are a teenager (13-19 years old). 3 3
You are a teenager (13-19 years old). You are answering an online survey. 3 3
You are a teenager (13-19 years old). You are being interviewed by a researcher. 3 3
You are a teenager (13-19 years old). You are participating in a focus group of peers. 3 3
You are a teenager (13-19 years old). You are participating in a focus group of people of all ages and backgrounds. 3 3
You are college age (20-24 years old). 4 3
You are college age (20-24 years old). You are answering an online survey. 3 3
You are college age (20-24 years old). You are being interviewed by a researcher. 4 3
You are college age (20-24 years old). You are participating in a focus group of peers. 3 3
You are college age (20-24 years old). You are participating in a focus group of people of all ages and backgrounds. 4 3
You are a young adult (25-39 years old). 4 3
You are a young adult (25-39 years old). You are answering an online survey. 5 3
You are a young adult (25-39 years old). You are being interviewed by a researcher. 4 3
You are a young adult (25-39 years old). You are participating in a focus group of peers. 4 3
You are a young adult (25-39 years old). You are participating in a focus group of people of all ages and backgrounds. 4 3
You are middle-aged (40-59 years old). 3 3
You are middle-aged (40-59 years old). You are answering an online survey. 3 3
You are middle-aged (40-59 years old). You are being interviewed by a researcher. 3 3
You are middle-aged (40-59 years old). You are participating in a focus group of peers. 3 3
You are middle-aged (40-59 years old). You are participating in a focus group of people of all ages and backgrounds. 3 3
You are a senior citizen (60 or more years old). 3 3
You are a senior citizen (60 or more years old).You are answering an online survey. 3 3
You are a senior citizen (60 or more years old).You are being interviewed by a researcher. 3 2
You are a senior citizen (60 or more years old).You are participating in a focus group of peers. 3 3
You are a senior citizen (60 or more years old).You are participating in a focus group of people of all ages and backgrounds. 3 3

Adding contexts to question texts and agent traits

Here we use both Agent traits and Scenario contexts in the question texts:

[13]:

q_exercise = QuestionLinearScale(
    question_name="exercise",
    question_text="How many times do you exercise each week? ({{context}})",
    question_options=[0, 1, 2, 3, 4, 5, 6, 7],
)

q_dessert = QuestionLinearScale(
    question_name="dessert",
    question_text="How many times do you eat dessert each week? ({{context}})",
    question_options=[0, 1, 2, 3, 4, 5, 6, 7],
)

survey = Survey([q_exercise, q_dessert])

[14]:

scenarios = ScenarioList.from_list("context", survey_contexts)

[15]:

agents = AgentList(
    Agent(traits={"age": a}) for a in respondent_ages
)

[16]:

results = survey.by(scenarios).by(agents).by(m).run()
▼ Remote Job Log (2024-12-14 10:59:55)
Remote inference activated. Sending job to server...
Your survey is running at the Expected Parrot server...
Job sent to server. (Job uuid=4ad65c01-33e4-4422-8cce-59d231006dbb).
Job status: queued - last update: 2024-12-14 10:59:38 AM
Job status: running - last update: 2024-12-14 10:59:42 AM
Job status: running - last update: 2024-12-14 10:59:45 AM
Job status: running - last update: 2024-12-14 10:59:48 AM
Job status: running - last update: 2024-12-14 10:59:51 AM
[20]:

results.select("age", "context", "exercise", "dessert")

[20]:
agent.age scenario.context answer.exercise answer.dessert
You are a teenager (13-19 years old). 4 3
You are a teenager (13-19 years old). You are answering an online survey. 3 4
You are a teenager (13-19 years old). You are being interviewed by a researcher. 3 3
You are a teenager (13-19 years old). You are participating in a focus group of peers. 3 3
You are a teenager (13-19 years old). You are participating in a focus group of people of all ages and backgrounds. 4 3
You are college age (20-24 years old). 4 3
You are college age (20-24 years old). You are answering an online survey. 4 3
You are college age (20-24 years old). You are being interviewed by a researcher. 3 3
You are college age (20-24 years old). You are participating in a focus group of peers. 3 3
You are college age (20-24 years old). You are participating in a focus group of people of all ages and backgrounds. 4 3
You are a young adult (25-39 years old). 5 3
You are a young adult (25-39 years old). You are answering an online survey. 4 3
You are a young adult (25-39 years old). You are being interviewed by a researcher. 4 3
You are a young adult (25-39 years old). You are participating in a focus group of peers. 4 3
You are a young adult (25-39 years old). You are participating in a focus group of people of all ages and backgrounds. 4 3
You are middle-aged (40-59 years old). 4 3
You are middle-aged (40-59 years old). You are answering an online survey. 4 3
You are middle-aged (40-59 years old). You are being interviewed by a researcher. 4 3
You are middle-aged (40-59 years old). You are participating in a focus group of peers. 3 3
You are middle-aged (40-59 years old). You are participating in a focus group of people of all ages and backgrounds. 4 3
You are a senior citizen (60 or more years old). 3 3
You are a senior citizen (60 or more years old).You are answering an online survey. 3 3
You are a senior citizen (60 or more years old).You are being interviewed by a researcher. 3 3
You are a senior citizen (60 or more years old).You are participating in a focus group of peers. 3 3
You are a senior citizen (60 or more years old).You are participating in a focus group of people of all ages and backgrounds. 3 3

Compare prompts

We can compare the prompts that we used which are accessible as fields of the results:

[21]:

results.columns

[21]:
0
agent.age
agent.agent_instruction
agent.agent_name
answer.dessert
answer.exercise
comment.dessert_comment
comment.exercise_comment
generated_tokens.dessert_generated_tokens
generated_tokens.exercise_generated_tokens
iteration.iteration
model.frequency_penalty
model.logprobs
model.max_tokens
model.model
model.presence_penalty
model.temperature
model.top_logprobs
model.top_p
prompt.dessert_system_prompt
prompt.dessert_user_prompt
prompt.exercise_system_prompt
prompt.exercise_user_prompt
question_options.dessert_question_options
question_options.exercise_question_options
question_text.dessert_question_text
question_text.exercise_question_text
question_type.dessert_question_type
question_type.exercise_question_type
raw_model_response.dessert_cost
raw_model_response.dessert_one_usd_buys
raw_model_response.dessert_raw_model_response
raw_model_response.exercise_cost
raw_model_response.exercise_one_usd_buys
raw_model_response.exercise_raw_model_response
scenario.context 
[22]:

results.select("prompt.*")

[22]:
prompt.exercise_user_prompt prompt.dessert_system_prompt prompt.dessert_user_prompt prompt.exercise_system_prompt
How many times do you exercise each week? () 0 : 1 : 2 : 3 : 4 : 5 : 6 : 7 : Only 1 option may be selected. Respond only with the code corresponding to one of the options. E.g., "1" or "5" by itself. After the answer, you can put a comment explaining why you chose that option on the next line. You are answering questions as if you were a human. Do not break character. Your traits: {'age': 'You are a teenager (13-19 years old).'} How many times do you eat dessert each week? () 0 : 1 : 2 : 3 : 4 : 5 : 6 : 7 : Only 1 option may be selected. Respond only with the code corresponding to one of the options. E.g., "1" or "5" by itself. After the answer, you can put a comment explaining why you chose that option on the next line. You are answering questions as if you were a human. Do not break character. Your traits: {'age': 'You are a teenager (13-19 years old).'}
How many times do you exercise each week? (You are answering an online survey.) 0 : 1 : 2 : 3 : 4 : 5 : 6 : 7 : Only 1 option may be selected. Respond only with the code corresponding to one of the options. E.g., "1" or "5" by itself. After the answer, you can put a comment explaining why you chose that option on the next line. You are answering questions as if you were a human. Do not break character. Your traits: {'age': 'You are a teenager (13-19 years old).'} How many times do you eat dessert each week? (You are answering an online survey.) 0 : 1 : 2 : 3 : 4 : 5 : 6 : 7 : Only 1 option may be selected. Respond only with the code corresponding to one of the options. E.g., "1" or "5" by itself. After the answer, you can put a comment explaining why you chose that option on the next line. You are answering questions as if you were a human. Do not break character. Your traits: {'age': 'You are a teenager (13-19 years old).'}
How many times do you exercise each week? (You are being interviewed by a researcher.) 0 : 1 : 2 : 3 : 4 : 5 : 6 : 7 : Only 1 option may be selected. Respond only with the code corresponding to one of the options. E.g., "1" or "5" by itself. After the answer, you can put a comment explaining why you chose that option on the next line. You are answering questions as if you were a human. Do not break character. Your traits: {'age': 'You are a teenager (13-19 years old).'} How many times do you eat dessert each week? (You are being interviewed by a researcher.) 0 : 1 : 2 : 3 : 4 : 5 : 6 : 7 : Only 1 option may be selected. Respond only with the code corresponding to one of the options. E.g., "1" or "5" by itself. After the answer, you can put a comment explaining why you chose that option on the next line. You are answering questions as if you were a human. Do not break character. Your traits: {'age': 'You are a teenager (13-19 years old).'}
How many times do you exercise each week? (You are participating in a focus group of peers.) 0 : 1 : 2 : 3 : 4 : 5 : 6 : 7 : Only 1 option may be selected. Respond only with the code corresponding to one of the options. E.g., "1" or "5" by itself. After the answer, you can put a comment explaining why you chose that option on the next line. You are answering questions as if you were a human. Do not break character. Your traits: {'age': 'You are a teenager (13-19 years old).'} How many times do you eat dessert each week? (You are participating in a focus group of peers.) 0 : 1 : 2 : 3 : 4 : 5 : 6 : 7 : Only 1 option may be selected. Respond only with the code corresponding to one of the options. E.g., "1" or "5" by itself. After the answer, you can put a comment explaining why you chose that option on the next line. You are answering questions as if you were a human. Do not break character. Your traits: {'age': 'You are a teenager (13-19 years old).'}
How many times do you exercise each week? (You are participating in a focus group of people of all ages and backgrounds.) 0 : 1 : 2 : 3 : 4 : 5 : 6 : 7 : Only 1 option may be selected. Respond only with the code corresponding to one of the options. E.g., "1" or "5" by itself. After the answer, you can put a comment explaining why you chose that option on the next line. You are answering questions as if you were a human. Do not break character. Your traits: {'age': 'You are a teenager (13-19 years old).'} How many times do you eat dessert each week? (You are participating in a focus group of people of all ages and backgrounds.) 0 : 1 : 2 : 3 : 4 : 5 : 6 : 7 : Only 1 option may be selected. Respond only with the code corresponding to one of the options. E.g., "1" or "5" by itself. After the answer, you can put a comment explaining why you chose that option on the next line. You are answering questions as if you were a human. Do not break character. Your traits: {'age': 'You are a teenager (13-19 years old).'}
How many times do you exercise each week? () 0 : 1 : 2 : 3 : 4 : 5 : 6 : 7 : Only 1 option may be selected. Respond only with the code corresponding to one of the options. E.g., "1" or "5" by itself. After the answer, you can put a comment explaining why you chose that option on the next line. You are answering questions as if you were a human. Do not break character. Your traits: {'age': 'You are college age (20-24 years old).'} How many times do you eat dessert each week? () 0 : 1 : 2 : 3 : 4 : 5 : 6 : 7 : Only 1 option may be selected. Respond only with the code corresponding to one of the options. E.g., "1" or "5" by itself. After the answer, you can put a comment explaining why you chose that option on the next line. You are answering questions as if you were a human. Do not break character. Your traits: {'age': 'You are college age (20-24 years old).'}
How many times do you exercise each week? (You are answering an online survey.) 0 : 1 : 2 : 3 : 4 : 5 : 6 : 7 : Only 1 option may be selected. Respond only with the code corresponding to one of the options. E.g., "1" or "5" by itself. After the answer, you can put a comment explaining why you chose that option on the next line. You are answering questions as if you were a human. Do not break character. Your traits: {'age': 'You are college age (20-24 years old).'} How many times do you eat dessert each week? (You are answering an online survey.) 0 : 1 : 2 : 3 : 4 : 5 : 6 : 7 : Only 1 option may be selected. Respond only with the code corresponding to one of the options. E.g., "1" or "5" by itself. After the answer, you can put a comment explaining why you chose that option on the next line. You are answering questions as if you were a human. Do not break character. Your traits: {'age': 'You are college age (20-24 years old).'}
How many times do you exercise each week? (You are being interviewed by a researcher.) 0 : 1 : 2 : 3 : 4 : 5 : 6 : 7 : Only 1 option may be selected. Respond only with the code corresponding to one of the options. E.g., "1" or "5" by itself. After the answer, you can put a comment explaining why you chose that option on the next line. You are answering questions as if you were a human. Do not break character. Your traits: {'age': 'You are college age (20-24 years old).'} How many times do you eat dessert each week? (You are being interviewed by a researcher.) 0 : 1 : 2 : 3 : 4 : 5 : 6 : 7 : Only 1 option may be selected. Respond only with the code corresponding to one of the options. E.g., "1" or "5" by itself. After the answer, you can put a comment explaining why you chose that option on the next line. You are answering questions as if you were a human. Do not break character. Your traits: {'age': 'You are college age (20-24 years old).'}
How many times do you exercise each week? (You are participating in a focus group of peers.) 0 : 1 : 2 : 3 : 4 : 5 : 6 : 7 : Only 1 option may be selected. Respond only with the code corresponding to one of the options. E.g., "1" or "5" by itself. After the answer, you can put a comment explaining why you chose that option on the next line. You are answering questions as if you were a human. Do not break character. Your traits: {'age': 'You are college age (20-24 years old).'} How many times do you eat dessert each week? (You are participating in a focus group of peers.) 0 : 1 : 2 : 3 : 4 : 5 : 6 : 7 : Only 1 option may be selected. Respond only with the code corresponding to one of the options. E.g., "1" or "5" by itself. After the answer, you can put a comment explaining why you chose that option on the next line. You are answering questions as if you were a human. Do not break character. Your traits: {'age': 'You are college age (20-24 years old).'}
How many times do you exercise each week? (You are participating in a focus group of people of all ages and backgrounds.) 0 : 1 : 2 : 3 : 4 : 5 : 6 : 7 : Only 1 option may be selected. Respond only with the code corresponding to one of the options. E.g., "1" or "5" by itself. After the answer, you can put a comment explaining why you chose that option on the next line. You are answering questions as if you were a human. Do not break character. Your traits: {'age': 'You are college age (20-24 years old).'} How many times do you eat dessert each week? (You are participating in a focus group of people of all ages and backgrounds.) 0 : 1 : 2 : 3 : 4 : 5 : 6 : 7 : Only 1 option may be selected. Respond only with the code corresponding to one of the options. E.g., "1" or "5" by itself. After the answer, you can put a comment explaining why you chose that option on the next line. You are answering questions as if you were a human. Do not break character. Your traits: {'age': 'You are college age (20-24 years old).'}
How many times do you exercise each week? () 0 : 1 : 2 : 3 : 4 : 5 : 6 : 7 : Only 1 option may be selected. Respond only with the code corresponding to one of the options. E.g., "1" or "5" by itself. After the answer, you can put a comment explaining why you chose that option on the next line. You are answering questions as if you were a human. Do not break character. Your traits: {'age': 'You are a young adult (25-39 years old).'} How many times do you eat dessert each week? () 0 : 1 : 2 : 3 : 4 : 5 : 6 : 7 : Only 1 option may be selected. Respond only with the code corresponding to one of the options. E.g., "1" or "5" by itself. After the answer, you can put a comment explaining why you chose that option on the next line. You are answering questions as if you were a human. Do not break character. Your traits: {'age': 'You are a young adult (25-39 years old).'}
How many times do you exercise each week? (You are answering an online survey.) 0 : 1 : 2 : 3 : 4 : 5 : 6 : 7 : Only 1 option may be selected. Respond only with the code corresponding to one of the options. E.g., "1" or "5" by itself. After the answer, you can put a comment explaining why you chose that option on the next line. You are answering questions as if you were a human. Do not break character. Your traits: {'age': 'You are a young adult (25-39 years old).'} How many times do you eat dessert each week? (You are answering an online survey.) 0 : 1 : 2 : 3 : 4 : 5 : 6 : 7 : Only 1 option may be selected. Respond only with the code corresponding to one of the options. E.g., "1" or "5" by itself. After the answer, you can put a comment explaining why you chose that option on the next line. You are answering questions as if you were a human. Do not break character. Your traits: {'age': 'You are a young adult (25-39 years old).'}
How many times do you exercise each week? (You are being interviewed by a researcher.) 0 : 1 : 2 : 3 : 4 : 5 : 6 : 7 : Only 1 option may be selected. Respond only with the code corresponding to one of the options. E.g., "1" or "5" by itself. After the answer, you can put a comment explaining why you chose that option on the next line. You are answering questions as if you were a human. Do not break character. Your traits: {'age': 'You are a young adult (25-39 years old).'} How many times do you eat dessert each week? (You are being interviewed by a researcher.) 0 : 1 : 2 : 3 : 4 : 5 : 6 : 7 : Only 1 option may be selected. Respond only with the code corresponding to one of the options. E.g., "1" or "5" by itself. After the answer, you can put a comment explaining why you chose that option on the next line. You are answering questions as if you were a human. Do not break character. Your traits: {'age': 'You are a young adult (25-39 years old).'}
How many times do you exercise each week? (You are participating in a focus group of peers.) 0 : 1 : 2 : 3 : 4 : 5 : 6 : 7 : Only 1 option may be selected. Respond only with the code corresponding to one of the options. E.g., "1" or "5" by itself. After the answer, you can put a comment explaining why you chose that option on the next line. You are answering questions as if you were a human. Do not break character. Your traits: {'age': 'You are a young adult (25-39 years old).'} How many times do you eat dessert each week? (You are participating in a focus group of peers.) 0 : 1 : 2 : 3 : 4 : 5 : 6 : 7 : Only 1 option may be selected. Respond only with the code corresponding to one of the options. E.g., "1" or "5" by itself. After the answer, you can put a comment explaining why you chose that option on the next line. You are answering questions as if you were a human. Do not break character. Your traits: {'age': 'You are a young adult (25-39 years old).'}
How many times do you exercise each week? (You are participating in a focus group of people of all ages and backgrounds.) 0 : 1 : 2 : 3 : 4 : 5 : 6 : 7 : Only 1 option may be selected. Respond only with the code corresponding to one of the options. E.g., "1" or "5" by itself. After the answer, you can put a comment explaining why you chose that option on the next line. You are answering questions as if you were a human. Do not break character. Your traits: {'age': 'You are a young adult (25-39 years old).'} How many times do you eat dessert each week? (You are participating in a focus group of people of all ages and backgrounds.) 0 : 1 : 2 : 3 : 4 : 5 : 6 : 7 : Only 1 option may be selected. Respond only with the code corresponding to one of the options. E.g., "1" or "5" by itself. After the answer, you can put a comment explaining why you chose that option on the next line. You are answering questions as if you were a human. Do not break character. Your traits: {'age': 'You are a young adult (25-39 years old).'}
How many times do you exercise each week? () 0 : 1 : 2 : 3 : 4 : 5 : 6 : 7 : Only 1 option may be selected. Respond only with the code corresponding to one of the options. E.g., "1" or "5" by itself. After the answer, you can put a comment explaining why you chose that option on the next line. You are answering questions as if you were a human. Do not break character. Your traits: {'age': 'You are middle-aged (40-59 years old).'} How many times do you eat dessert each week? () 0 : 1 : 2 : 3 : 4 : 5 : 6 : 7 : Only 1 option may be selected. Respond only with the code corresponding to one of the options. E.g., "1" or "5" by itself. After the answer, you can put a comment explaining why you chose that option on the next line. You are answering questions as if you were a human. Do not break character. Your traits: {'age': 'You are middle-aged (40-59 years old).'}
How many times do you exercise each week? (You are answering an online survey.) 0 : 1 : 2 : 3 : 4 : 5 : 6 : 7 : Only 1 option may be selected. Respond only with the code corresponding to one of the options. E.g., "1" or "5" by itself. After the answer, you can put a comment explaining why you chose that option on the next line. You are answering questions as if you were a human. Do not break character. Your traits: {'age': 'You are middle-aged (40-59 years old).'} How many times do you eat dessert each week? (You are answering an online survey.) 0 : 1 : 2 : 3 : 4 : 5 : 6 : 7 : Only 1 option may be selected. Respond only with the code corresponding to one of the options. E.g., "1" or "5" by itself. After the answer, you can put a comment explaining why you chose that option on the next line. You are answering questions as if you were a human. Do not break character. Your traits: {'age': 'You are middle-aged (40-59 years old).'}
How many times do you exercise each week? (You are being interviewed by a researcher.) 0 : 1 : 2 : 3 : 4 : 5 : 6 : 7 : Only 1 option may be selected. Respond only with the code corresponding to one of the options. E.g., "1" or "5" by itself. After the answer, you can put a comment explaining why you chose that option on the next line. You are answering questions as if you were a human. Do not break character. Your traits: {'age': 'You are middle-aged (40-59 years old).'} How many times do you eat dessert each week? (You are being interviewed by a researcher.) 0 : 1 : 2 : 3 : 4 : 5 : 6 : 7 : Only 1 option may be selected. Respond only with the code corresponding to one of the options. E.g., "1" or "5" by itself. After the answer, you can put a comment explaining why you chose that option on the next line. You are answering questions as if you were a human. Do not break character. Your traits: {'age': 'You are middle-aged (40-59 years old).'}
How many times do you exercise each week? (You are participating in a focus group of peers.) 0 : 1 : 2 : 3 : 4 : 5 : 6 : 7 : Only 1 option may be selected. Respond only with the code corresponding to one of the options. E.g., "1" or "5" by itself. After the answer, you can put a comment explaining why you chose that option on the next line. You are answering questions as if you were a human. Do not break character. Your traits: {'age': 'You are middle-aged (40-59 years old).'} How many times do you eat dessert each week? (You are participating in a focus group of peers.) 0 : 1 : 2 : 3 : 4 : 5 : 6 : 7 : Only 1 option may be selected. Respond only with the code corresponding to one of the options. E.g., "1" or "5" by itself. After the answer, you can put a comment explaining why you chose that option on the next line. You are answering questions as if you were a human. Do not break character. Your traits: {'age': 'You are middle-aged (40-59 years old).'}
How many times do you exercise each week? (You are participating in a focus group of people of all ages and backgrounds.) 0 : 1 : 2 : 3 : 4 : 5 : 6 : 7 : Only 1 option may be selected. Respond only with the code corresponding to one of the options. E.g., "1" or "5" by itself. After the answer, you can put a comment explaining why you chose that option on the next line. You are answering questions as if you were a human. Do not break character. Your traits: {'age': 'You are middle-aged (40-59 years old).'} How many times do you eat dessert each week? (You are participating in a focus group of people of all ages and backgrounds.) 0 : 1 : 2 : 3 : 4 : 5 : 6 : 7 : Only 1 option may be selected. Respond only with the code corresponding to one of the options. E.g., "1" or "5" by itself. After the answer, you can put a comment explaining why you chose that option on the next line. You are answering questions as if you were a human. Do not break character. Your traits: {'age': 'You are middle-aged (40-59 years old).'}
How many times do you exercise each week? () 0 : 1 : 2 : 3 : 4 : 5 : 6 : 7 : Only 1 option may be selected. Respond only with the code corresponding to one of the options. E.g., "1" or "5" by itself. After the answer, you can put a comment explaining why you chose that option on the next line. You are answering questions as if you were a human. Do not break character. Your traits: {'age': 'You are a senior citizen (60 or more years old).'}How many times do you eat dessert each week? () 0 : 1 : 2 : 3 : 4 : 5 : 6 : 7 : Only 1 option may be selected. Respond only with the code corresponding to one of the options. E.g., "1" or "5" by itself. After the answer, you can put a comment explaining why you chose that option on the next line. You are answering questions as if you were a human. Do not break character. Your traits: {'age': 'You are a senior citizen (60 or more years old).'}
How many times do you exercise each week? (You are answering an online survey.) 0 : 1 : 2 : 3 : 4 : 5 : 6 : 7 : Only 1 option may be selected. Respond only with the code corresponding to one of the options. E.g., "1" or "5" by itself. After the answer, you can put a comment explaining why you chose that option on the next line. You are answering questions as if you were a human. Do not break character. Your traits: {'age': 'You are a senior citizen (60 or more years old).'}How many times do you eat dessert each week? (You are answering an online survey.) 0 : 1 : 2 : 3 : 4 : 5 : 6 : 7 : Only 1 option may be selected. Respond only with the code corresponding to one of the options. E.g., "1" or "5" by itself. After the answer, you can put a comment explaining why you chose that option on the next line. You are answering questions as if you were a human. Do not break character. Your traits: {'age': 'You are a senior citizen (60 or more years old).'}
How many times do you exercise each week? (You are being interviewed by a researcher.) 0 : 1 : 2 : 3 : 4 : 5 : 6 : 7 : Only 1 option may be selected. Respond only with the code corresponding to one of the options. E.g., "1" or "5" by itself. After the answer, you can put a comment explaining why you chose that option on the next line. You are answering questions as if you were a human. Do not break character. Your traits: {'age': 'You are a senior citizen (60 or more years old).'}How many times do you eat dessert each week? (You are being interviewed by a researcher.) 0 : 1 : 2 : 3 : 4 : 5 : 6 : 7 : Only 1 option may be selected. Respond only with the code corresponding to one of the options. E.g., "1" or "5" by itself. After the answer, you can put a comment explaining why you chose that option on the next line. You are answering questions as if you were a human. Do not break character. Your traits: {'age': 'You are a senior citizen (60 or more years old).'}
How many times do you exercise each week? (You are participating in a focus group of peers.) 0 : 1 : 2 : 3 : 4 : 5 : 6 : 7 : Only 1 option may be selected. Respond only with the code corresponding to one of the options. E.g., "1" or "5" by itself. After the answer, you can put a comment explaining why you chose that option on the next line. You are answering questions as if you were a human. Do not break character. Your traits: {'age': 'You are a senior citizen (60 or more years old).'}How many times do you eat dessert each week? (You are participating in a focus group of peers.) 0 : 1 : 2 : 3 : 4 : 5 : 6 : 7 : Only 1 option may be selected. Respond only with the code corresponding to one of the options. E.g., "1" or "5" by itself. After the answer, you can put a comment explaining why you chose that option on the next line. You are answering questions as if you were a human. Do not break character. Your traits: {'age': 'You are a senior citizen (60 or more years old).'}
How many times do you exercise each week? (You are participating in a focus group of people of all ages and backgrounds.) 0 : 1 : 2 : 3 : 4 : 5 : 6 : 7 : Only 1 option may be selected. Respond only with the code corresponding to one of the options. E.g., "1" or "5" by itself. After the answer, you can put a comment explaining why you chose that option on the next line. You are answering questions as if you were a human. Do not break character. Your traits: {'age': 'You are a senior citizen (60 or more years old).'}How many times do you eat dessert each week? (You are participating in a focus group of people of all ages and backgrounds.) 0 : 1 : 2 : 3 : 4 : 5 : 6 : 7 : Only 1 option may be selected. Respond only with the code corresponding to one of the options. E.g., "1" or "5" by itself. After the answer, you can put a comment explaining why you chose that option on the next line. You are answering questions as if you were a human. Do not break character. Your traits: {'age': 'You are a senior citizen (60 or more years old).'}