Photo: MinnPost.
Cynthia Tu of Sahan Journal is using Chat GPT to improve revenue streams.
A few times in the past, I’ve had reason to link to a story at Sahan Journal, a nonprofit newsroom serving immigrants and communities of color in Minnesota. Now NiemanLab, a website about journalism, links to an article on a surprising development at the small publisher.
Lev Gringauz, reporting at MinnPost via NiemanLab, writes “As journalists around the world experiment with artificial intelligence, many newsrooms have common, often audience-facing, ideas for what to try.
“They range from letting readers talk to chatbots trained on reporting, to turning written stories into audio, creating story summaries and, infamously, generating entire articles using AI — a use case vehemently rejected by many journalists.
“But Sahan Journal, the nonprofit newsroom serving immigrants and communities of color in Minnesota, wanted to try something different.
“ ‘We’re less enthusiastic, more skeptical, about using AI to generate editorial content,’ said Cynthia Tu, Sahan Journal’s data journalist and AI specialist.
“Instead, the outlet has been working on ways to support internal workflows with AI. Now, it’s even testing a custom ChatGPT bot to help pitch Sahan Journal to prospective advertisers and sponsors. …
“While AI has plenty of ethical and technical issues, Tu’s work highlights another important aspect: The intended users — in this case, the Sahan Journal team.
“ ‘A lot of … this experiment is less of a technical challenge,’ Tu said. ‘It’s more like, how do you make [AI] fit in the human system more flawlessly? And how do you train the human to use this tool in a way that it was intended?’
“Sahan Journal’s AI experimentation, and Tu’s job, are supported by a partnership between the American Journalism Project, a national nonprofit helping local newsrooms, and ChatGPT creator OpenAI. …
“Liam Andrew, technology lead for the AJP’s Project & AI Studio, sees part of his job as helping newsrooms overcome hesitancy around AI. …
“Tu joined Sahan Journal fresh from a Columbia Journalism School master’s program in data journalism. She had played a little with chatbots, but otherwise didn’t have much experience working with AI. …
“For one investigation, Tu used a Google AI tool to process the financial data of charter schools in Minnesota. Thinking about how to save time on backend workflows, Tu then helped Sahan Journal generate story summaries, tailored for Instagram carousels, with ChatGPT. …
“ ‘You need to know what the workflow of the organization looks like…[and how] you push for change within a department when they’ve already been doing [something] for the past five years using a manual or human labor way.’
“That knowledge came in handy when finally tackling Tu’s core AI project: improving Sahan Journal’s revenue.
“The project stemmed from an anonymized database of audience insights, which included demographic information and interests. While an important resource, Sahan Journal’s small revenue team didn’t have the time to figure out how to leverage it. …
” ‘What if AI could feed two birds with one scone? A custom ChatGPT bot could process the audience data and personalize a media kit for clients. But it needed to work without being an extra burden on the revenue staff. …
“The magic of AI chatbots like ChatGPT is that you don’t need to know how to code to use them. Just type in a prompt and get rolling. …
“Less magically, AI chatbots can be hard to keep in line for specific tasks. Designed to be eager helpers, they hallucinate false results and stubbornly twist instructions in an attempt to please.
“Troubleshooting those issues was no simple task for Tu.
“The custom revenue chatbot struggled to keep Tu’s preferred formatting, and hallucinated audience data. The bot would also intermix results from the internet that Tu had not asked for. None of that was ideal for a tool that should work reliably for the revenue team.
“ ‘I was kind of jumping through hoops and telling it multiple times, “Please do not reference anything else on the internet,” ‘ Tu said. …
“Working with chatbots is an exercise in prompt engineering — mostly a trial-and-error process of figuring out what specific instructions will get the preferred result. As Tu said, ‘lazy questions lead to lazy answers.’ … Eventually, Tu settled on a reliable set of prompts.
“The custom chatbot takes about 20 seconds to find relevant data from the audience database — for example, pulling up how much of Sahan Journal’s audience cares about public transportation. Then it creates a summary for a media kit tailored to potential clients.
“The chatbot also double-checks its work by referencing the database again, making sure its output matches reality. And part of the database is shown for users to manually see the chatbot isn’t hallucinating. …
“Earlier this year, Tu introduced the final version of the revenue bot to Sahan Journal’s team. …
“By mid-April, the Sahan Journal revenue team had used the custom chatbot on six sales pitches, with three successfully leading to ads placed on the site. …
“But there’s a larger question hanging over this work: Is it sustainable? In a way, newsroom experiments with AI exist in a bubble.
“ ‘Everything is kind of tied to a grant,’ Tu said, referencing the AJP-OpenAI partnership that supports her work. But grants come and go as donor interests (and financials) change.”
The other unknowns are weighed at NiemanLabs, here.
Suzanne's Mom's Blog 