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()

/Users/a16174/edsl/edsl/inference_services/AvailableModelFetcher.py:139: UserWarning: No models found for service ollama
  warnings.warn(f"No models found for service {service_name}")

[2]:

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

[3]:

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

[3]:

LanguageModel

	key	value
0	model	gpt-4o
1	parameters:temperature	0.500000
2	parameters:max_tokens	1000
3	parameters:top_p	1
4	parameters:frequency_penalty	0
5	parameters:presence_penalty	0
6	parameters:logprobs	False
7	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()

▼ Job Status (2024-12-28 11:08:30)

Job UUID	bb28a74b-106e-4371-aa93-49244dfea185
Progress Bar URL	https://www.expectedparrot.com/home/remote-job-progress/bb28a74b-106e-4371-aa93-49244dfea185
Error Report URL	None
Results UUID	faf58276-59ae-4e8b-b38e-6c4ebd8cc747
Results URL	None

✓Current Status: Job completed and Results stored on Coop: https://www.expectedparrot.com/content/faf58276-59ae-4e8b-b38e-6c4ebd8cc747

[8]:

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

[8]:

	scenario.age	scenario.context	answer.exercise	answer.dessert
0	You are a teenager (13-19 years old).	nan	3	3
1	You are a teenager (13-19 years old).	You are answering an online survey.	4	3
2	You are a teenager (13-19 years old).	You are being interviewed by a researcher.	3	3
3	You are a teenager (13-19 years old).	You are participating in a focus group of peers.	3	3
4	You are a teenager (13-19 years old).	You are participating in a focus group of people of all ages and backgrounds.	3	4
5	You are college age (20-24 years old).	nan	3	3
6	You are college age (20-24 years old).	You are answering an online survey.	3	3
7	You are college age (20-24 years old).	You are being interviewed by a researcher.	3	3
8	You are college age (20-24 years old).	You are participating in a focus group of peers.	3	3
9	You are college age (20-24 years old).	You are participating in a focus group of people of all ages and backgrounds.	3	3
10	You are a young adult (25-39 years old).	nan	3	2
11	You are a young adult (25-39 years old).	You are answering an online survey.	3	3
12	You are a young adult (25-39 years old).	You are being interviewed by a researcher.	3	3
13	You are a young adult (25-39 years old).	You are participating in a focus group of peers.	4	2
14	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
15	You are middle-aged (40-59 years old).	nan	3	3
16	You are middle-aged (40-59 years old).	You are answering an online survey.	3	2
17	You are middle-aged (40-59 years old).	You are being interviewed by a researcher.	3	3
18	You are middle-aged (40-59 years old).	You are participating in a focus group of peers.	3	2
19	You are middle-aged (40-59 years old).	You are participating in a focus group of people of all ages and backgrounds.	3	2
20	You are a senior citizen (60 or more years old).	nan	3	0
21	You are a senior citizen (60 or more years old).	You are answering an online survey.	3	2
22	You are a senior citizen (60 or more years old).	You are being interviewed by a researcher.	3	3
23	You are a senior citizen (60 or more years old).	You are participating in a focus group of peers.	3	2
24	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()

▼ Job Status (2024-12-28 11:08:45)

Job UUID	3b7951d6-0fc3-44df-bc61-4d9b5061c15b
Progress Bar URL	https://www.expectedparrot.com/home/remote-job-progress/3b7951d6-0fc3-44df-bc61-4d9b5061c15b
Error Report URL	None
Results UUID	62b4ff85-dad8-4b3a-9306-98d857a5b771
Results URL	None

✓Current Status: Job completed and Results stored on Coop: https://www.expectedparrot.com/content/62b4ff85-dad8-4b3a-9306-98d857a5b771

[12]:

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

[12]:

	agent.age	agent.context	answer.exercise	answer.dessert
0	You are a teenager (13-19 years old).	nan	3	3
1	You are a teenager (13-19 years old).	You are answering an online survey.	3	3
2	You are a teenager (13-19 years old).	You are being interviewed by a researcher.	3	3
3	You are a teenager (13-19 years old).	You are participating in a focus group of peers.	3	3
4	You are a teenager (13-19 years old).	You are participating in a focus group of people of all ages and backgrounds.	3	3
5	You are college age (20-24 years old).	nan	4	3
6	You are college age (20-24 years old).	You are answering an online survey.	3	3
7	You are college age (20-24 years old).	You are being interviewed by a researcher.	4	3
8	You are college age (20-24 years old).	You are participating in a focus group of peers.	3	3
9	You are college age (20-24 years old).	You are participating in a focus group of people of all ages and backgrounds.	4	3
10	You are a young adult (25-39 years old).	nan	4	3
11	You are a young adult (25-39 years old).	You are answering an online survey.	5	3
12	You are a young adult (25-39 years old).	You are being interviewed by a researcher.	4	3
13	You are a young adult (25-39 years old).	You are participating in a focus group of peers.	4	3
14	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
15	You are middle-aged (40-59 years old).	nan	3	3
16	You are middle-aged (40-59 years old).	You are answering an online survey.	3	3
17	You are middle-aged (40-59 years old).	You are being interviewed by a researcher.	3	3
18	You are middle-aged (40-59 years old).	You are participating in a focus group of peers.	3	3
19	You are middle-aged (40-59 years old).	You are participating in a focus group of people of all ages and backgrounds.	3	3
20	You are a senior citizen (60 or more years old).	nan	3	3
21	You are a senior citizen (60 or more years old).	You are answering an online survey.	3	3
22	You are a senior citizen (60 or more years old).	You are being interviewed by a researcher.	3	2
23	You are a senior citizen (60 or more years old).	You are participating in a focus group of peers.	3	3
24	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()

▼ Job Status (2024-12-28 11:09:01)

Job UUID	d9788a05-e9e3-4bfe-9c5c-6b8c8497978b
Progress Bar URL	https://www.expectedparrot.com/home/remote-job-progress/d9788a05-e9e3-4bfe-9c5c-6b8c8497978b
Error Report URL	None
Results UUID	ef745e9f-fe3a-42d2-aa8e-7f76b7f79cbe
Results URL	None

✓Current Status: Job completed and Results stored on Coop: https://www.expectedparrot.com/content/ef745e9f-fe3a-42d2-aa8e-7f76b7f79cbe

[17]:

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

[17]:

	agent.age	scenario.context	answer.exercise	answer.dessert
0	You are a teenager (13-19 years old).	nan	4	3
1	You are a teenager (13-19 years old).	You are answering an online survey.	3	4
2	You are a teenager (13-19 years old).	You are being interviewed by a researcher.	3	3
3	You are a teenager (13-19 years old).	You are participating in a focus group of peers.	3	3
4	You are a teenager (13-19 years old).	You are participating in a focus group of people of all ages and backgrounds.	4	3
5	You are college age (20-24 years old).	nan	4	3
6	You are college age (20-24 years old).	You are answering an online survey.	4	3
7	You are college age (20-24 years old).	You are being interviewed by a researcher.	3	3
8	You are college age (20-24 years old).	You are participating in a focus group of peers.	3	3
9	You are college age (20-24 years old).	You are participating in a focus group of people of all ages and backgrounds.	4	3
10	You are a young adult (25-39 years old).	nan	5	3
11	You are a young adult (25-39 years old).	You are answering an online survey.	4	3
12	You are a young adult (25-39 years old).	You are being interviewed by a researcher.	4	3
13	You are a young adult (25-39 years old).	You are participating in a focus group of peers.	4	3
14	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
15	You are middle-aged (40-59 years old).	nan	4	3
16	You are middle-aged (40-59 years old).	You are answering an online survey.	4	3
17	You are middle-aged (40-59 years old).	You are being interviewed by a researcher.	4	3
18	You are middle-aged (40-59 years old).	You are participating in a focus group of peers.	3	3
19	You are middle-aged (40-59 years old).	You are participating in a focus group of people of all ages and backgrounds.	4	3
20	You are a senior citizen (60 or more years old).	nan	3	3
21	You are a senior citizen (60 or more years old).	You are answering an online survey.	3	3
22	You are a senior citizen (60 or more years old).	You are being interviewed by a researcher.	3	3
23	You are a senior citizen (60 or more years old).	You are participating in a focus group of peers.	3	3
24	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:

[18]:

results.columns

[18]:

	0
0	agent.age
1	agent.agent_instruction
2	agent.agent_name
3	answer.dessert
4	answer.exercise
5	comment.dessert_comment
6	comment.exercise_comment
7	generated_tokens.dessert_generated_tokens
8	generated_tokens.exercise_generated_tokens
9	iteration.iteration
10	model.frequency_penalty
11	model.logprobs
12	model.max_tokens
13	model.model
14	model.presence_penalty
15	model.temperature
16	model.top_logprobs
17	model.top_p
18	prompt.dessert_system_prompt
19	prompt.dessert_user_prompt
20	prompt.exercise_system_prompt
21	prompt.exercise_user_prompt
22	question_options.dessert_question_options
23	question_options.exercise_question_options
24	question_text.dessert_question_text
25	question_text.exercise_question_text
26	question_type.dessert_question_type
27	question_type.exercise_question_type
28	raw_model_response.dessert_cost
29	raw_model_response.dessert_one_usd_buys
30	raw_model_response.dessert_raw_model_response
31	raw_model_response.exercise_cost
32	raw_model_response.exercise_one_usd_buys
33	raw_model_response.exercise_raw_model_response
34	scenario.context

[19]:

results.select("prompt.*")

[19]:

	prompt.exercise_user_prompt	prompt.dessert_system_prompt	prompt.dessert_user_prompt	prompt.exercise_system_prompt
0	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).'}
1	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).'}
2	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).'}
3	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).'}
4	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).'}
5	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).'}
6	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).'}
7	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).'}
8	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).'}
9	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).'}
10	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).'}
11	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).'}
12	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).'}
13	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).'}
14	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).'}
15	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).'}
16	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).'}
17	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).'}
18	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).'}
19	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).'}
20	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).'}
21	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).'}
22	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).'}
23	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).'}
24	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).'}