FAQs

Yabble's automated AI solutions take the heavy lifting our of data coding. Just link or upload your data, and let our automated AI solutions do the rest. Using a combination of cutting-edge and proprietary algorithms and technology, it takes any unstructured text data and analyzes it for themes, sub-themes, and sentiment. 

The insights Count provides enable you to immediately identify the key things you can do to drive business growth. They also highlight opportunities for queries, guiding you to areas you can mine for even deeper insights. 

Count helps you pinpoint places for improvement, allows you to optimize your customer and brand experiences, and validates business strategy and decisions. 

Count is capable of analyzing data from nearly any source, including survey responses, product reviews, and unnested comments from social media. Future releases will include more advanced social media data and call center data. 

Theme and sub-theme counts allow you to unlock immense value from your text data. They enable you to see the most talked-about subjects within a particular dataset and can tell you instantly where the biggest drivers and inhibitors of your business lie. 

Themes are one- to two-word subjects that highlight the main areas of response within your dataset. These are high-level buckets such as management, customer service, online shopping, and shipping. 

Sub-themes add layers of rich detail to your themes. For each theme that Yabble Count generates from your dataset, you’ll see all the sub-themes that sit underneath it, be they positive, neutral, or negative. For example: 

Theme: Parking 

Sub-themes: Spacious parking spots, Good location, Expensive parking, Too busy/not enough availability  

Sub-themes are one of the true goldmines of Hey Yabble and allow you to: 

• Pinpoint the precise areas where you can improve to drive business growth. 
• Understand customers’ pain points and solve their problems. 
• Make data-driven decisions. 

Sentiment gives you an indication of how people feel about a particular subject. Yabble provides in-depth sentiment analysis, displaying it in the form of a sentiment score that gives you an immediate numerical snapshot of the positive, negative, and neutral feelings around a particular subject. The sentiment score on themes ranges from -100 to 100. 

Yabble generates two types of sentiment: 

• Overall sentiment. This indicates the sentiment breakdown within your entire dataset. It’s displayed as a donut chart at the top of your dashboard, separated into easily understandable, color-coded sections. Positive is green, neutral is orange, and negative is red. 
• Theme and sub-theme sentiment. Count calculates sentiment for each individual theme and sub-theme, displaying sub-theme sentiment in the form of an emoticon. Positive is green, neutral is orange, and negative is red. (For instance: you would see a red emoticon next to the Parking > Small spaces sub-theme.) If you hover over the emoticon, you’ll see a detailed count and percentage breakdown of the positive, neutral, and negative buckets.  

The filter functionality allows you to filter by different variables and to hone in on certain segments of your results. You can filter by: 

• Anything you upload (these data parameters come through as custom variables) 
• Response date 
• Comment sentiment 
• Themes
• Sub-themes
• Theme sentiment
• Demographics (pulled through from your data)
• Questions (pulled through from your data)

Your Explore page displays a clear, concise visualization of the analysis Yabble has performed on your dataset. 

Your overall sentiment score sits at the top, next to a box displaying correlation between themes and sentiment. Click on the Gen icon in the top right corner to run a Gen chat straight from your counting results. 

Below your sentiment score, you’ll see two tabs marked Themes and Sub-themes. You’ll also see the Comments/Filters sidebar to the right. 

The Themes tab displays the top-level themes from your dataset, alongside percentage and sentiment scores for each. Percentage indicates the frequency with which that theme arose during analysis. 

If you click the arrow (>) next to a theme, your sub-themes will populate underneath, alongside their own percentage counts and sentiment (displayed as emoticons). 

The Sub-themes tab displays all your sub-themes in one list. They’re ordered from highest to lowest count, irrespective of their parent themes — but you can see the corresponding theme listed next to each in parentheses (i.e. Spacious parking spots (Parking)). Note: the order of sub-themes in the overall Sub-themes tab may differ from the order of sub-themes under each parent theme. 

Hovering over the emoticon next to a sub-theme will generate that sub-theme’s individual sentiment score (counts and percentages for positive, neutral, and negative). 

Definitely! The current release of Count allows for simple data export via an easily shareable CSV  and SPSS format. Later product releases will include more export formats. 

No need. The Yabble AI uses its smarts to create custom code frames based on the data set. Ensuring things like emerging trends are not missed. Users can move, merge or edit anything after analysis if desired.

Yes, Count is fully flexible, with options to move or merge themes, sub themes or individual comments. You can also relabel data, so if for example the AI uses Staff but you prefer Employee simply make the change.

Summarize is designed specifically for analyzing in-depth interviews. Saving up to 80% of analysis time by synthesizing results into key challenges, opportunities, actions and conclusions.

Yes, once all interviews have been analyzed, an Executive Summary will provide all of the key areas of focus for the researcher to begin focusing on in their reporting.

Yabble Summarize is great for in-depth interviews, podcasts, media articles, meeting notes, speeches or focus group transcripts.

Yabble Summarize can process these files for you, just connect in with your customer service team member and we will organize to have these transcribed and loaded for you.

Upload your transcript in its raw format. You will need to clean out any images and tables and ensure your document is in the correct format. Otherwise, no additional cleaning is required.

Gen is an AI Research Assistant that allows you to have a conversation with your own data in a similar way to how you use ChatGPT’s technology – all within Yabble’s secure, walled garden data environment. You can prompt Gen to query your dataset to provide an insight. Gen can even suggest actions if you ask it to.

Gen uses a natural language model which means you can ask your data all types of questions and Gen will be able to answer your question instantly and conversationally. While ChatGPT is asking questions of the internet up to 2021, Gen allows you to ask questions on your own proprietary dataset – whatever topic that might be. Once your dataset is uploaded into the Yabble platform you can prompt Gen to query your dataset and provide high level insights or dive deeper to explore your data holistically – all with data security peace of mind.

Simply type a question related to your own dataset, and Gen will do all the work for you.

You can specify which particular part of your project your question relates to, or for more general questions, ask them across ‘All Questions’. 

As Gen is a natural language model, it will understand what you are trying to achieve even if you do make the odd spelling mistake. However, Gen will not like characters such as ‘[' or '>' as these are not generally used in conversational text.

Where you have a large dataset, you are likely to get a deeper insights by selecting a specific Question. Selecting ‘All Questions' will factor in more than may be required.

Further, being specific always helps. Rather than asking ‘What are the main complaints people had?’, ask something like ‘What are the main comments people made with respect to pricing?’. By saying the word ‘pricing’ in the question, Gen is able to apply a hybrid search that picks up the word pricing, and everything related, allowing for a better response. 

As a user, I want to know about what’s really driving peoples opinion about the prices at Walmart form their responses to a survey question.

OK: Why?

Good: Why did people say that?

Better: Why did people say that about pricing?

Best: Why did people have those concerns about pricing at Walmart?

Gen has its own context builder and should be able to handle most questions it receives. However, it is helpful for a user to be as specific as possible if they want to dial in to the insights they want from their data.

There are multiple ways to approach getting actionable insight from Gen. One of the most effective ways is to structure your questions in a way that leads Gen toward the outcome you want. This is done by building context. Say you want to know what you could do about some customer feedback, you might input as follows:

• Input 1: Tell me about the feedback related to online shopping.
• Input 2: Why did customers say that?
• Input 3: What could we do about it to help our customers?

This method is effective in that Gen will not only have the context of the survey/interview question, and the responses behind it but now also some conversation history it can use as context.

Alternatively, you could also ask:

• Input 1: With regards to negative customer feedback on online shopping, I want to understand why customers gave those responses, and what we could do about it to improve the customer experience?

Both are valid methods and will arrive at a similar output. However, the first method allows Gen more capacity to respond and breaks up the question set. The user may even learn something about their data that they weren’t expecting along the way.

Yes, Gen can chat with any type of qualitative data you have in the Yabble platform.

While Gen can talk to data that has been theme counted, at present it does not yet factor in the results of the theme counting. 

Gen is a language model, and for the time being doesn’t like counting. Gen can however give you an answer like ‘most’ or ‘the main topics people discussed'.

Asking Gen an identical / similar question in the same chat will give different responses. Often the subsequent responses can add more detail, as Gen will not want to repeat itself. 

The more detail you give, the more information Gen has to work with. However, you can simply ask a question like ‘Why?’ and Gen will go and find context from your previous conversation. 

Gen will find responses related to your question in order to give an insightful answer. It may not need your entire dataset before it can give an answer like ‘most people preferred…’

Further, survey data can contain irrelevant answers. Gen will filter these answers out, or ignore them in its response generation

For now, Gen only likes data that is in English. Please watch this space while Gen becomes multi-lingual!

Gen is designed to be a Market Research AI Agent

This means that as a request comes in, Gen will review the request and then:

• Allocate the task to one of a series of MRX agents Yabble has built to complete the request.
• This allows Gen to do lots of different tasks e.g. name the top 3 mentions, summarize, work with short form as well as long for data etc
• However, if a request comes in that Gen deems to not be Market Research related or related to the project, but straight fact, it will bi-pass the agents and the project data and ask the LLM directly - that is why it can do things like tell you who Joan of Arc is.
• The problem is that LLMs by their generative nature have an element of randomness, and sometimes they won’t answer the question. This unfortunately isn’t something we have a lot of control over.
• The probability of this happening is also likely to increase with the number of questions we have asked Gen in a single chat, as the history and context becomes more complex.  

As more of our customers use Gen and we collate feedback we see different use cases they would like Gen to help them with. Every use case (eg finding direct quotes) is a different ‘tool' we need to build - which Gen's agent framework can then call on to answer. For example, pulling 'Direct quotes’ is not a tool we currently have but obviously one we would like to look at in a future state.

In short Gen and Count are totally different processes and were designed for different purposes.

An Explore shows ‘counted’ responses for a related Question and is intended more as a statistical analysis of the data, while Gen has all information in a project at its disposable to review in order to answer the users question (and this could also include ‘all responses, for all questions’).

When Gen talks about, for example the ‘top 3 things about this topic’, it is a much more holistic answer based on all the information it has available.

Gen will aim to find responses/comments related to your question in order to give an insightful answer. It may not need your entire dataset before it can give an answer like ‘most people preferred xyz’. Comments (e.g. in survey data) can also contain irrelevant answers, so Gen may filter these answers out, or ignore them in its response generation. This is the main reason why Gen won’t have ‘referenced' 10,000 comments in its answer like you may see on the Explore.