Open seminar: AI in public health research, starring ChatGPT

Seminar

Date: Wednesday 22 February 2023

Time: 13.30 – 14.30

Location: Lecture room 29, in house 4, Campus Albano

The focus of the seminar will be on if, what, how, and when we should use AI in research and related fields. On Athena there are two short and readable articles providing some background and discussions on these topics.

Please bring your own experience with AI in research and share it with your colleagues during the seminar. (If you have no direct experience, come anyway.)

For example, GPT-3 and ChatGPT are quite good at summarizing and translating texts, as well as writing code, but there are likely many other uses as well. Below* you find its reply when asked: "Write a short and convincing text for why ChatGPT might be useful in academic research".

If you want to get a deeper understanding of ChatGPT and related "large language models" before the seminar this is a nice (if somewhat demanding) text:

https://writings.stephenwolfram.com/2023/02/what-is-chatgpt-doing-and-why-does-it-work/

If you have not tried ChatGPT, sign up here:

https://chat.openai.com/

ChatGPT generated text

*ChatGPT is an incredibly versatile and powerful tool that can be immensely useful in academic research. As a large language model trained by OpenAI, ChatGPT has been designed to understand natural language inputs and generate coherent responses in a conversational manner. This makes it ideal for a wide range of research applications, including but not limited to:

  1. Data analysis and interpretation: ChatGPT can be used to analyze large volumes of text data, such as survey responses or social media posts, to identify patterns and trends. Researchers can ask ChatGPT to summarize the data, highlight key themes or topics, or even generate new insights based on the data.
  2. Literature reviews: ChatGPT can assist in conducting literature reviews by summarizing the main points and findings of research articles. This can save researchers a considerable amount of time and effort, allowing them to focus on analyzing and synthesizing the information.
  3. Hypothesis testing: Researchers can use ChatGPT to generate new hypotheses or test existing ones by providing it with relevant data and asking it to analyze and interpret the results. This can help to identify potential areas for further research and experimentation.
  4. Collaboration and brainstorming: ChatGPT can be used as a virtual research assistant, providing suggestions and insights to researchers as they work on their projects. It can also facilitate group brainstorming sessions, allowing researchers to collaborate and generate new ideas in real-time.

In summary, ChatGPT's ability to understand natural language inputs and generate coherent responses makes it an invaluable tool for academic research. It can save researchers time and effort, help to identify new insights and areas for further research, and facilitate collaboration and brainstorming. Its versatility and power make it an asset for researchers in many different fields.