What's New?

Our topics analysis tool has been enhanced with a new feature called "Describe Clusters." This feature significantly improves the way we group and name clusters of free text based on their similarity and the topics they cover.

Previous Method:

• Previously, clusters were named by combining significant terms from each cluster. While this method was functional, it often resulted in names that were difficult to read and did not effectively communicate the insights.

New Improvement:

• With the integration of OpenAI models, we now generate titles for clusters that are much more readable and contextually accurate. This enhancement takes into account the context of all paragraphs, ensuring that the titles are not only more human-readable but also more meaningful.

Example:

• When analyzing texts related to product management, if a cluster frequently mentions the word "design," the new feature will likely identify it as "UX/UI Design," aligning it more closely with the field of product management rather than general design.

Applications:

• This feature is highly beneficial for organizing and understanding reviews, transcripts, emails, survey answers, book paragraphs, and any other free text. It provides clear and concise cluster titles that enhance the overall analysis and communication of insights.

We are excited to bring you this update, which aims to make your text analysis experience smoother and more insightful.

Dear Graphext Users,

The Detail View 🔍 in the Graph and the New Node Cards🃏are now live for you to explore! 

🔍 Detail View in the Graph:

Introducing a brand new mode in the Graph - the Detail View! Now, when you dive into your data, you can open a convenient side drawer right on your screen. This feature allows you to explore detailed information about each node in your graph with ease. Imagine having a magnifying glass 🔎 for your data - you can hover over any node, and the side panel instantly updates to display comprehensive information, making it ideal for digesting longer text reviews, images or exploring complex data relationships effortlessly.

🃏 New Node Cards:

With the new Node Cards, you have the power to customize each node's information by adding as many variables as you need. Think of it like having your own personalized top trump card for every node in your graph. Whether it's age, gender, name, email, phone number, or even a profile picture, you can now tailor your nodes to capture precisely the data that matters most to you.

As always, we're committed to enhancing Graphext based on your feedback, so please don't hesitate to reach out with any thoughts or suggestions.

The Graphext Team 💙

Dear Graphext Users,

Value Labels are here to make your data visualizations shine! Now, you will be able to add informative labels to your plots, bringing clarity and insight to every visualization even when exporting outside of Graphext.

📊 Flexible Functionality:

With Value Labels, you're in control. This feature allows you to customize how your data is displayed. Whether you want to showcase total numbers, relative percentages, or specific values for each segment, Value Labels have you covered. Plus, you can choose the position of your labels - inside or outside the bars - to suit your preference and presentation style.

🔍 Supported Plot Types:

Value Labels are available across a range of plot types, including:

• Bar Plots
• Boxplots
• Heatmaps
• Scatter Plots

No matter what type of data you're working with, Value Labels make it easier than ever to communicate key insights and trends effectively.

📈 Easier Exporting, Clearer Insights:

Value Labels make exporting static charts much more powerful. When you export your visualizations, your carefully chosen labels will stay put, ensuring that your insights are crystal clear even outside of the Graphext platform.

The Graphext Team 💙

Dear Graphext Users,

We've Got Some Great New Features for You!

• 🌈 Customizable Plot Colors:
• 📊 Focus on What Matters - Top/Bottom N Categories:

🌈 Customizable Plot Colors:

Now, you can add a personal touch to your plots by choosing any color you like. This is perfect for aligning your visualizations with your company's branding or simply picking a color that fits the mood of your presentation. It's a small change, but we believe it can make a big difference in how your data is perceived and understood.

📊 Focus on What Matters - Top/Bottom N Categories:

We understand that sometimes less is more. That's why we're introducing the ability to show just the top or bottom N categories in your plots. This feature will help you create cleaner, more focused visualizations, making it easier for your audience to get the key takeaways without getting lost in the details.

We can't wait to see the amazing visualizations you'll create with these new tools. As always, we're here to listen to your feedback and make Graphext even better for you.

Cheers,
The Graphext Team 💙

Dear Graphext Users,

What’s New?

Enhanced Category Renaming and Merging:

• Direct Renaming: You can now rename categories directly within our interface. This straightforward functionality allows for quick adjustments to your dataset, ensuring that your categories accurately reflect your data.
• Efficient Merging: When you name two categories the same, Graphext will automatically combine them into one. This is particularly useful for cleaning up datasets where the same item might be listed under different names, like various job titles (Product Manager, PM, Product Mgmt, etc…)  that essentially mean "Product Manager."

Coming soon! The Future is ✨AI-Powered:

We're not stopping here! Get ready for an upcoming feature where our AI will suggest merging similar concepts. Imagine the AI detecting and suggesting merging "Advisor" and "Adviser" or "E-mail" and "Email," helping you to further clean and organize your data efficiently.

Seamless Integration:

These new category management tools are designed to fit smoothly into your existing Graphext workflow. Renaming and merging are straightforward, quick, and won’t interrupt your data analysis.

We hope these updates make your data work more efficient and straightforward. Your feedback is always welcome as we continue to improve Graphext.

The Graphext Team 💙

Dear Graphext users,

Say hi to interactive plot resizing! At Graphext, we understand that the impact of a good visualization is not just in the data it represents, but also in how it's presented. Recognizing that different visualizations require different aspect ratios for optimal clarity and impact, we've now made it possible for you to adjust the size of your plots interactively.

What's New?

• Interactive Resizing: You can now click and drag the edge of your plots to resize them. This means you can easily switch between landscape and portrait orientations or fine-tune the dimensions to get just the right ratio for your data visualization needs.
• Adaptable Visuals: Whether your data looks best in a wide, landscape format or a tall, vertical orientation, you have complete control over how your plots are displayed. This flexibility ensures that you can present your data in the most effective and visually appealing way.

Why This Matters:

We've all been there – tweaking numbers, trying to get the visualization size just right, only to end up with a format that doesn't quite do the data justice. It can be a frustrating and time-consuming process. That's why we prioritized developing a solution that not only saves time but also enhances your ability to present data in the best light possible.

Seamless Exporting:

Once you've configured the perfect size for your plot, exporting it is just as straightforward. This seamless transition from customization to export means your workflow is smoother and faster, allowing you to share your insights with others more efficiently.

Dear Graphext users,

This week at Graphext, we're introducing a series of keyboard shortcuts designed to make your filtering process in the cross filters significantly more efficient. We understand that working with data often involves dealing with variables that have a wide range of categories and selecting or deselecting these manually can be time-consuming. That's why we've implemented these shortcuts to streamline your workflow.

What's New?

• Selecting a Range of Categories: Now, you can easily select all categories between two points with just a couple of clicks. Click on the first category, then click on the last category while holding down the SHIFT key. This will select both categories and everything in between.
• Adding or Removing Categories: To add or remove a single category from your selection, simply hold down the CMD key (on Mac) or the CTRL key (on Windows) while clicking the category. This feature is particularly handy when you want to maintain most categories but exclude just a few, especially with variables that have a high number of categories.

Why This Matters:

These enhancements are all about saving you time and making your data analysis workflow smoother. By allowing for quicker selection and deselection of categories, we hope to significantly reduce the time you spend on manual tasks, freeing you up to focus on the more critical aspects of your analysis.

Dear Graphext users, 

We're rolling out an update to the correlations section, now called Correlations 2.0, for all our Graphext users. Here's a quick refresher on what the correlations section does: It's a handy tool within Graphext that lets you pick a variable you're interested in, and then it shows you how that variable correlates with others in your dataset, sorting the results by the highest correlation. This feature is pretty neat because it works with all kinds of variables, including categorical ones, thanks to the mutual information algorithm we use.

What's New in Version 2.0?

• Pearson Coefficient: We've added the Pearson coefficient to our toolbox, so now you have another way to measure how variables relate to each other, especially useful for linear relationships between continuous variables.
• More Ways to Visualize Data: Besides the bubble charts we had before, you can now use boxplots and heatmaps for a different look at the correlations in your data. These should give you more insights and make the correlations easier to understand at a glance.

Why We Made These Changes:

We wanted to give you more options and better tools to see and understand the relationships in your data. The Pearson coefficient is a classic statistical tool for a reason, and we think it's a great complement to the mutual information algorithm. As for the new visualizations, we know that a good chart can sometimes tell you more at a glance than a bunch of numbers, so we're excited to offer you more choices there.

Try It Out:

The updated correlations section is ready for you to explore. Check out the new features and see how they can help with your data analysis. We're here for any questions or feedback you might have.