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 Agent that allows you to have a conversation with your own structured and unstructured data in a chat format – all within Yabble’s secure, walled garden data environment. Gen uses natural language and SQL tools allowing you to ask your data all types of questions with Gen able to answer your question instantly and conversationally. 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, generate tables, filter by custom variables, 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’. 

Yes, Gen can chat with any type of qualitative and quantitative data you have in the Yabble platform, including raw transcripts, open-ends, quantitative studies, and more. 

While Gen can chat with data you upload through our Count tool, it has not been built to chat directly with the themes, sub-themes and sentiment generated by Count. Gen can identify themes from this data using the tools in its toolbox and via your natural language querying, but results may differ from the output from Yabble Count.

As Gen is an agent utilizing natural language processing, 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. 

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. 

Gen has its own context builder and should be able to handle most questions it receives. However, it is helpful to be as specific as possible.

As an example, I want to know what’s really driving people's opinion about the prices at Walmart. 

• 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 isn't specifically designed to extract verbatim quotes from transcripts, but it can provide varied responses when asked for examples of what respondents have said on a topic. The responses are randomized, meaning you may receive different quotes each time you ask. 

Try phrasing your question like: 

• "Can you give me a direct quote about X topic?"
• "Can you provide some examples of what respondents have said about Y topic?" 

Gen will aim to surface relevant responses, but the exact quotes may differ with each query. If you're looking for a broader selection, you can refine your request or ask multiple times. 

You can ask Gen about specific transcripts, but results may vary. It does not retrieve all responses at once, and the selection of quotes is randomized. 

To improve accuracy, try referencing details such as the respondent's name (if available) or the file name. For example: 

• "Can you tell me what [respondent name] said about [topic]?"
• "What are respondents saying about [Y topic] in the file 'interview.3'?" 

Gen will attempt to surface relevant responses based on the dataset, but results may differ each time you ask. 

Yes! While Gen started as a language model, we have now enabled an SQL querying process in Gen, allowing for you to get quantitative insights from your structured data conversationally. You can ask Gen for percentages and totals, as well as to present these in tables, and provide summaries. 

Note: This feature works on structured variables only, not unstructured question responses. 

Asking Gen an identical/similar question in the same chat will often give different responses due to the way Large Language Models work. Often the subsequent responses can add more detail, as Gen will not want to repeat itself. However, the insight that is extracted should remain consistent. 

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 to 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 is designed to analyze data in English. However, as Large Language Models are improving their multi-lingual capabilities, we have found that Gen will respond in other languages if prompted. Please watch this space while Gen becomes multi-lingual! 

To fully unlock and leverage the powerful Gen features within your projects, we strongly recommend re-importing your data, regardless of its original source (including Yabble Surveys). This ensures that the data is properly formatted and integrated within the Theme Counting Projects environment, allowing for optimal performance and access to all of the Gen features' capabilities. While it might seem redundant, this re-import process is the best approach for a seamless and comprehensive experience.

Chats are grouped chronologically, and you can organize your projects with editable chat titles that follow your naming conventions, so it’s easy to find what you’re looking for. Identify chats by chat name, project name, user icon, and time stamp for simple team collaboration.