Your First Analysis

You have set-up your project and shared the invitation link to the portal with participants. Next, you can start analyse the conversations and extract insights as they are flowing into the Dashboard.

What You'll Learn

• How to access and view conversation transcripts in your dashboard
• How to create and use Libraries to get AI-clustered overviews of participant conversations
• How to create custom Views to organize conversations around specific research questions
• How to use the Ask feature to explore your data through conversational AI queries

Using the Dashboard for Analysis during or after a Session

Step 1: Accessing Transcripts

1. First, navigate to your dashboard and open the project that you want to be working in
2. If you want to, you can view individual real-time conversation transcripts by clicking on the unique conversation

In general, there are two ways how Dembrane lets you explore your data

Option 1: Creating a Library

 Libraries are a great way to get a broad overview, and a feeling for what participants were talking about, clustered around questions or topics of your choice!

1. In your dashboard, click the "Library" button in the sidebar. This will take you to your project library.
2. Initially, your library will be empty as indicated by the blue status message on top of the page. Here you will also see how many conversations are waiting to be processed
3. Now click "Create Library" By default, the library will create two so called "Views" - Topics and Sentiment. Views are the topics, questions, themes of your choice which the AI will use as basis for clustering the conversation quotes

4. Click "Create Library" and wait until the processing is complete. This can take a while
5. Once the library is generated you can start exploring the two default views - Topics and Sentiment - which should now have so called "Aspects" attached to them. Aspects are AI generated clusters surrounding the question or query of the view. Click into one of them to start exploring how conversation quotes were clustered around the aspect.
6. After creating your first library, you are ready to create your first unique views!

Note: You might find in the library that some cluster-themes have 100’s of quotes, whereas others have few or even zero. Often the clusters that have many quotes are the ‘open doors’, clusters you can expect in advance to appear. The quotes with fewer quotes are the ones the AI identifies as relevant, and can be interesting avenues to explore with your participants.

Step 1: Creating Views

1. In your project library, click "Create View"
2. Enter your query: Here you can ask your research question.
3. Additional context: This is about what you want the AI to pay particular attention too, or for example how many clusters you want (Like a top 10 list)
4. If you click "Create view" the AI will start gathering relevant quotes.

Step 2: Exploring Views

There are multiple ways to explore a view.

1. By clicking on the expand icon in the top right corner of your view, you will see a more detailed overview of the view.
2. You can at any point, click into one of the aspects to start exploring how conversation quotes were clustered around the aspect.
3. For each quote you will see the conversation source attached. Clicking it will take you straight to the "Analysis" tab of the conversation, which lists not only all extracted quotes but also AI generated Insights.

Note: Once you have generated your first library, the "Create Library" button in the top right corner will now say "Regenerate Library". This is especially relevant when after creating your initial library, you have more conversations which are being recorded. These will not automatically be added to the library which is why you will need to regenerate.

Option 2: Using the Ask Feature

If you want to have a more conversational way to explore your data click the "Ask" button in the sidebar of your dashboard. This will take you to an AI chat interface. Here you can ask specific questions to dig deeper and chat with your data. E.g. “What are the arguments that are presented when discussing X”, or, “What seem to be the biggest differences in values between recording X and recording Y”?

1. Importantly, if you are currently viewing a conversation in the dashboard and click "Ask", it will automatically select the conversation as context for the chat, making a blue tick-mark appear. Simply deselect if this was not your intention.
2. If you click "Ask" without currently viewing a conversation, it will take you to the chat interface without any specific context added.
3. You can always add context to your chat by checking the boxes next to the individual conversation.

Note: The system is designed to help you make sense of complex conversation data efficiently. The Library is your starting point, while the Chat helps you dive deeper into specific areas of interest.

Now you are well equipped to create a project, share it with your participants and start collecting data.

Are you looking for more tips and tricks? Check our Advanced use →

Need Help?

Contact Jules if you need help! jules@dembrane.com