Difference between revisions of "Generative AI for Crowdfunding"
From REU@MU
Line 1: | Line 1: | ||
+ | |||
+ | == Research Goals == | ||
'''RQ1''': How do medical crowdfunding campaigns differ from AI-generated replications? | '''RQ1''': How do medical crowdfunding campaigns differ from AI-generated replications? | ||
* Step 1: Scrape GoFundMe's [https://www.gofundme.com/start/medical-fundraising medical] fundraising homepage. I should be able to adapt Alex Fischmann's script from last summer. | * Step 1: Scrape GoFundMe's [https://www.gofundme.com/start/medical-fundraising medical] fundraising homepage. I should be able to adapt Alex Fischmann's script from last summer. | ||
Line 6: | Line 8: | ||
* We need IRB approval to conduct experiments with human participants. | * We need IRB approval to conduct experiments with human participants. | ||
* Which factors contribute to a successful campaign? How do we quantify success? | * Which factors contribute to a successful campaign? How do we quantify success? | ||
+ | |||
+ | == Deliverables == |
Revision as of 17:51, 7 July 2023
Research Goals
RQ1: How do medical crowdfunding campaigns differ from AI-generated replications?
- Step 1: Scrape GoFundMe's medical fundraising homepage. I should be able to adapt Alex Fischmann's script from last summer.
- Step 2: Prompt an LLM (GPT-3 or GPT-4) to rewrite scraped campaigns. This may require fine-tuning. Write a script to replicate n campaigns n times. We want a 1-1 relationship between an original campaign and its replication. In other words, the output should adhere to the facts provided in the prompt.
- Step 3: Use natural language processing (NLP) techniques to compare original campaigns to their AI-generated counterparts. Analyze individual word associations with NRC or LIWC and overall tone with sentiment analysis.
RQ2: Which campaign is more successful with respect to medical crowdfunding?
- We need IRB approval to conduct experiments with human participants.
- Which factors contribute to a successful campaign? How do we quantify success?