Welcome to the comprehensive guide for Go Vocal's new AI Analysis feature. This innovative tool aims to revolutionize the way you understand, categorize, and analyze the plethora of input from residents participating in your community engagement initiatives. Compatible with both ideation methods and surveys, the AI Analysis tool offers a user-friendly interface and a range of functionalities to help you derive actionable insights from community feedback.

Our AI analysis tool can be used to perform two types of analysis:

The AI Analysis interface is divided into four main columns, each serving a specific purpose:

1. This is your control panel for creating and managing tags. Tags are essential for clustering inputs and facilitating more nuanced analysis.

2. This column displays a list of all the input you wish to analyze. It serves as your data pool.

3. Here, you can:

4. This is where you can generate summaries and ask questions to the AI for further clarification or insights. These summaries will be applied to the filter you selected in the third column. If you for example selected for Question 2: Age = 25 - 39 years, the summary that is created will be a summary based on inputs given by respondents that have selected this specific attribute.

To access the AI Analysis feature, navigate to the input manager of your project that employs an ideation method. Here, you'll find the option to launch the AI Analysis tool.

With the AI Analysis feature you can create textual summaries of both the inputs given by the users as well as the comments that were given to the input.

To get to the comments section of an idea in the ideation AI analysis, you click in the second column on the idea you want to analyse, and when you scroll down in the third column. You’ll see the comments given to this idea. When there are more than 5 comments on a specific idea/input, you can create a summary of the comments, which can be useful especially in very long threads.

In the 4th column “summarize” and “ask a question” also has commenting included.

We also show more advanced details on correlations between tags and demographic data, you can find more information in the ‘Auto Insights’ section.

For survey-based projects, the AI Analysis feature can be accessed directly from the survey results page. You’ll see above the responses a blue widget that has in the right ‘Open AI Analysis’. Upon launching the tool, you'll be prompted to select the questions you wish to analyze. You can also add follow-up questions to the initial question for a more holistic analysis.

Tagging is a crucial part of the analysis process, and our tool offers multiple ways to do it:

The second & third column help you with exploring the input:

As part of our latest update to the AI analysis feature, we’ve introduced Auto-Insights, a tool located just below the demographics section (see picture).

Auto-Insights connects the dots between tags, demographic data, and survey questions to help you uncover meaningful patterns.

Here we display the most relevant insights we could find in your data. To dive deeper, click ‘Explore’ in the Auto-Insights section. This opens a heatmap view where you can spot correlations between different metrics. For example, the image shows how the demographic group ‘age’ correlates with specific tags used in the project.

This view provides a fast and detailed overview of how different demographic groups engage with various topics. A checkmark in the top-right corner of a box (like the dark green ones in the image) signals that the correlation is statistically significant.

You can also select the unit of analysis (top right) to customize how labels and demographics are compared:

Hover over any box to get detailed insights into what the data represents, as shown in the example image.

Differences between ideation and surveys:

The fourth column is your go-to place for summaries and further inquiries:

When a summary is generated, it will include clickable references to related ideas, allowing you to delve deeper into the context.

Our AI summarization tool aims to provide accurate and concise summaries with appropriate in-line references. Occasionally, however, absence of references occurs for a few reasons:

1. Contextual Relevance: In some cases, the summaries produced do not require specific references, as they may pertain to general knowledge or widely accepted information. Our AI is designed to discern when a reference may not add substantial value, thus omitting it to maintain the summary's clarity and conciseness.

2. Balancing Reference Inclusion: Initially, our AI tended to include references extensively, sometimes resulting in overly lengthy lists that were not always helpful. To improve the utility and readability of the summaries, we refined the system to include references more selectively. This adjustment sometimes means that a summary might miss out on a reference that could be deemed useful, although it was an intentional design choice to prevent overwhelming the user with unnecessary citations.

3. Continuous Improvement: We recognize the importance of in-line references and are continually working to fine-tune our AI's performance in this area. The current system represents a balance we've struck based on extensive testing and user feedback. While we aim to include references where they add value, the dynamic nature of language and context means some omissions are inevitable.

You can either copy the summary from the AI Sensemaking interface or you can directly integrate into a report, via the report builder. You will find your AI summaries in the AI tab on the left and you can simply drag the summary you need and drop wherever you need it into the report.

There is no clearly defined maximum number of inputs the AI can analysis, as it's not about input count but about total characters. So it depends on the length of the inputs as well. (although we do cut off very long ones to not eat up the whole summary).In total, we can send something around ~ 400.000 words at once, but it depends on many factors like the language, the number of questions that are sent at the same time, the content in those questions and answers etc. For almost all projects this should be enough, but in case you would be experiencing issues on this matter, you could try to already split it in 2 and see if that reduced characters so it does not go over "400.000 words at once".

The biggest difference between price plans is that on a standard price plan you can only do AI summaries of 30 inputs at a time while all higher price plans can summaries unlimited number of inputs at a time.

Any further questions or in need of support? Get in touch with us via the chat bubble on your platform. 💬