Prompting LLMs is very interesting and in my experience, you never know what you will get unless you are 100% specific on what you are looking for. This brings me to my point on the most helpful prompting strategy I have learned which is, “outlining exactly what you want and describing your ideal output. ” (Open AI Academy, 2025).

Using ChatGPT, I tested out how different the outputs will be if I were specific versus not specific in my prompts. The first prompt (non-specific) was “Explain vaccine hesitancy”. This was the output it then gave me: Vaccine hesitancy is when people are unsure about, delay, or refuse vaccines even when they are available. It’s not just “anti-vaccine” behavior, it’s more of a spectrum ranging from mild uncertainty to strong refusal.

At its core, vaccine hesitancy is shaped by three big factors:

1. Confidence (trust)
This is about how much people trust:

• the safety and effectiveness of vaccines
• healthcare providers
• institutions like governments and pharmaceutical companies

If trust is low, hesitancy increases. For example, misinformation about side effects or historical medical mistreatment can reduce confidence.

2. Complacency (perceived risk)
Some people don’t see diseases as a real threat anymore. Because vaccines have been so successful, illnesses like measles or polio feel “rare,” so people think:

• “I probably won’t get sick anyway”
• “It’s not that serious”

This lowers motivation to get vaccinated.

3. Convenience (access and barriers)
Even people who are willing may delay vaccines because of:

• cost
• transportation issues
• time constraints
• confusing healthcare systems

So hesitancy isn’t always about beliefs, it can also be about logistics.

---

Other important influences:

• Misinformation (especially on social media)
• Cultural or religious beliefs
• Personal experiences with healthcare
• Peer and family influence
• Political climate and trust in authority

---

Why it matters:
Vaccine hesitancy can reduce vaccination rates, which weakens herd immunity and increases the risk of disease outbreaks.

This was surprisingly detailed and included several examples to help with understanding. It was also quite easy to understand and overall the output had a good amount of depth. This first output would be very useful for people seeking a general and easy understanding of vaccine hesitancy, or for someone looking for a quick definition they can say or use. It even goes further than the basics, which is helpful because the examples it gives would allow for more understanding beyond the definition alone.

I then asked the more specific prompt: “Act as a public health educator. Explain vaccine hesitancy to college students in simple terms, include one real-world example, and briefly mention why it matters for community health.” This was the output it then gave me:

Think of vaccine hesitancy as being unsure about getting a vaccine, not necessarily being fully against it. It’s when people delay or question vaccines even when they’re available.

In simple terms, it usually comes down to three things:

• Trust: Do I believe this vaccine is safe and that the system behind it is honest?
• Risk perception: Do I think the disease is actually a threat to me?
• Access: Is it easy for me to get the vaccine?

A lot of college students fall into the middle, not strongly anti-vaccine, but influenced by things like social media, friends, or confusing information.

Real world example:
During the COVID-19 pandemic, many young adults delayed getting vaccinated. Some felt they were low risk, others were unsure because of things they saw online about side effects. Even when vaccines were free and available on campuses, hesitation still slowed uptake.

Why it matters for community health:
Vaccines don’t just protect you, they protect the people around you. When fewer people get vaccinated, diseases can spread more easily, especially to those who can’t be vaccinated or are more vulnerable. This can lead to outbreaks that affect entire communities, including college campuses.

This response was highly specific and tailored to college students just like I prompted. Like a public health educator, it explained simply and in a “teaching manner.” The example was also centered on college students and communal living on campus, and overall, the language was way more simple and easy to understand than the first general prompt. This prompt is useful for college students and contextualizes vaccine hesitancy specific to their experience. Compared to the first prompt, a college student might find this more relevant and specific to their situation.

All of this connects to Open AI’s prompting guide which talked about the importance of providing ChatGPT with background and what context you would like the output to be framed within. I was surprised to see how much detail the first prompt had but just like I expected, when I framed the second prompt, I got an output specific to the demographic (college students) that I was interested in.

Source: Admin. (2025, August 6). Prompting%20. OpenAI Academy. https://academy.openai.com/public/clubs/work-users-ynjqu/resources/prompting