Want to see some AI?
Check this out.
Exhibit A: a creative process actually driven by what people think and feel
1. Start with story, review or other text data from surveys, questionnaires or focus groups.
This is anonymized response data from a 2024 Michigan United/Michigan League of Public Policy survey on economic well-being. I analyzed these 321 responses using IBM Watson NLU. From there I uploaded the data into a custom GPT from ChatGPT. I used that tool for data processing, topic modeling and content creation. I also used the data to create visualizations in MongoDb. Click here for the full dataset.
2. Use IBM Watson to turn responses into data on five emotions, sentiment, context and intent.
IBM Watson turns survey responses into data on five emotions, entities, relations, and more. Click here to see the full dataset.
3. Put the data in a custom GPT .
ChatGPT is by far the most powerful tools out there. I took all of the NLU datasets and used them to create two reports, one for semantic analysis and the other topic modeling. The semantic analysis report finds the top five themes found in the words and concepts in the data. Topic modeling reveals the top unique topics found in the words of people's responses. Together, they help us see the feelings underlying the opinion in their quantitative responses.
4. Use the machine to reveal new insights
Above are the first few lines of an Emotions Report, created by our custom GPT. This is one of six reports I generate as part of a regular analysis. These in-depth reports provide usable insights for understanding the impact and influence of emotion in the responses. We can use the data to create visualizations, data picture stories that provide insights visually. Click here for the full report.
5. Create data visualizations to help see what's important.
Two Ways to Look at Living Wage: first by relevance and race
Now by relevance and income level
Interesting how things change when you get money involved
These are the most popular and relevant terms found in the keywords and sentence subjects of people's responses. In this case, the responses are filtered by the respondents' race and income level. Similarities across income levels are as fascinating as the range and intensity of subjects. For example, "a living wage" is important to both White and Black people But through an economic lens, it is least relevant to "not reported", then poor, then the working poor, middle class, upper class and the working class (not surprisingly). It's also the only subject shared by almost all income levels. Another thing easy to see that topics important to the working class are really, really important to them. Check out the size and score of that green "I".
6. Model the top five topics and create personas for each.
I used the semantic analysis to create personas and topic analysis for persona variants. By personalizing the top five themes and various subtopics, it becomes easier to contextualize them. For example, you and I can frame the findings as personal to Rachel or people like Rachel. Or we can think about a punch list of demographic and psychographic values. It's easier to write and advocate for a person.
7. Integrate the persona data into writer-friendly creative briefs.
First, an observation. There is no way a human is going to glean this by reading 321 responses. The machine analyzes and retains at scale. Second, is knowing that the primary creative document is supported by a firm foundation of data; presented in a practical way. Click here for the full creative brief. Tap here for a brief on a different topic with hotlinks to a data report.
Digital strategy is just one way to use AI
Using AI for comms is just one way I can help
I can build interactive information portals for members, supporters, voters and residents
If you answer the same set of questions a lot. I can show you an automated, new and highly accurate way to answer their questions
I can teach your team to use ChatGPT as a set of tools
The best reasons to use new technology lie in solving the daily problems facing your team. I can help you find organic uses for ChatGPT and AI.
I can create widgets and appliances for user-education and support
I can help you build a significantly better owners manual, support page or how-to guide. No pdfs and is built for digital.
AN AFFORDABLE ALL-IN-ONE SOLUTION
