• Background Image

    The Conversation

    analyzing online conversations

March 14, 2017

Why Tag Clouds and Topic Wheels Hold You Back

One of the most common forms of data visualization among social listening softwares is the tag cloud. The graphic representation of which topics are the most common organized by word, size and color is easy for the layman to decipher so it is dangled at the end of the software company’s string like top sirloin.

But it’s just a chicken nugget. Or, more aptly, just the breading around the chicken nugget.

Tag Cloud

Topic wheels are a bit more informative methods of data visualization. They enable you to see subtopics easily. But the data visualization is still just a superficial layer around the insights your data contains. They help you see one layer down.

Topic Wheel

But insights are seldom found one layer down. Understanding of the conversation — the why behind the emerging topics and themes — means drilling down deeper.

Take our study of Dirt Devil, for instance. We may notice looking at Tag Clouds and Topic Wheels of data visualization that durability is an issue that surfaces in the negative conversations around the brand. But why does Dirt Devil have durability issues? To know that, you have to drill down into the negative, then into the durability topic, then analyze and understand the various issues there.

Conversation Research breakdown

The level of detail that can provide a product manager with actual insights to improve the product is not found using a tag cloud or a topic wheel. It’s found by diving in and analyzing and understanding the full context of the conversation. With this information — certainly represented visually for ease of understanding — we can tell the product manager that there are structural issues in quality of construction, weakness in the unit handles and motor issues, particularly when used for pet hair. These insights give the product team direction so they can either A) Ask deeper questions in further research or B) Focus on the opportunities to improve the product.

The overarching point is that if you’re relying on visualizations of your data rather than analysis of it, you’re missing a lot. In fact, we would surmise you’re missing everything.

We would love to help understand your data. Want to know more about what customers say about your brand? Your products? What you can do better? Drop us a line. We can help.

February 16, 2017

How Analyzing Online Conversations Builds a Better Brand

The fun for me in analyzing online conversations is the proof points the data provides. No longer do product, experience or marketing communications decisions have to be left to assumptions. The data allows you to turn them into assertions.

In our recent report on senior living, we analyzed online conversations of people discussing the major types of senior care facilities. We found hundreds of conversations mentioning nursing homes, assisted living facilities, independent living facilities and long-term care options. We broke each of those conversations down by facility, sentiment and topic.

When you do this, you get a glimpse into what consumers truly think. Not only are we not prompting them for answers, which in and of itself biases the information, but we’re simply recording when they talk about the topic in question voluntarily and freely.

What does this type of analysis tell us? Take for instance this visualization:

Assisted Living Family Experience Negative Conversations

This is a breakdown of the conversation topics within the posts we categorized as focusing on assisted living facilities where the main topic was the experience of the family of the patient (which is important since the primary buyer is the adult children of the patient), and those experiences were scored as having a negative sentiment. So 30% of all negative conversations about assisted living facilities (represented in the circle to the left) were determined to be about the family experience. The right hand circle breaks those down by specific topic.

What this tell us is that 32% of the negative family experience conversations were about shopping for the facility overall. What is it that is so bad about it? We’d need to move a layer farther in analysis to discover that, but since we have the data, we can! Another 32% mentions they prefer an alternative to an assisted living facility. Further analysis shows that they don’t prefer independent living or nursing homes, but rather staying home and not needing a care facility at all.

While this may seem a logical conclusion if you understand the consumer, that has not been statistically proven before, to our knowledge. Now it has. But that insight can also give assisted living marketers more pointed insights to develop better copy, sales materials or even sales strategies, enhancing conversions and driving more customers.

Emotions while enrolling and family in-fighting are significant portions of the negative family experience, too. What can that tell an assisted living marketer hoping to land more clients? Those conversations can be further vetted to see if common threads run throughout.

The more you peel back the layers on analyzing online conversations, the more interesting nuggets you discover to fuel decisions for marketing, user experience or even product development. And those can build a better, more profitable brand.

The only question left to answer is why haven’t you started?

For more analysis of online conversations around the senior living industry, including a mapping of the buyer journey for senior care, see our Conversation Report. For more about how CRI can help you in analyzing online conversations around your brand or market, drop us a line.

September 27, 2016

Why small samples matter in Conversation Research


Conversation research is distinct from traditional market research in that it is largely unstructured. We use a variety of softwares and tools to process the data sets to produce some degree of organization – topics, sources, themes, etc. – but you’re not pulling a sample of 1000 people of a certain demographic and asking them the same questions here. You’re casting a wide net looking for similarities in random conversations from around the world.

So when your review comes back with 100 conversations out of 23,000, it’s easy to dismiss this percentage (less than 0.02) as not valid. But let’s look at an example and see if validity needs to be reconsidered.

CRI recently conducted a high-level scan of the online conversations around work-life balance with our friends at Workfront. The project management software company focuses a lot of its content on work-life balance as its solution helps bring that result to marketing agencies and brand teams around the world.

Over the 30-day period ending September 19, we found 23,021 total conversations on blogs, social networks, news sites, forums and more – essentially any publicly available online source where people could post or comment – about work-life balance.

If you focus on the 23,021 as your total pool of conversations, it might frustrate you that only eight percent (1,827) could be automatically scored for sentiment. (One can manually score much more, and CRI typically does a fair amount of work to close that gap, but it is an exercise in time and resources that for this project both parties elected to set aside.)

But if you take that eight percent – those 1,827 conversations – and now consider them your sample set, you’ve got something. There, we discover that 79 percent of the scored conversations were positive – people are generally in favor of or have good reactions to the concept of work-life balance. But that means 21 perent of them don’t.

And this is where our curiosity is piqued.


It turns out the predominant driver around the negative conversations on work-life balance is that the concept itself is a myth. Out of the 382 total negatively scored conversations found, 98 of them indicated in some way that work-life balance was a lie, a farce, an illusion and so on.

Another 10 were tied to a conversation around a piece of content exposing the “lies” of work-life balance, also indicating there’s some level of mistrust that it is attainable. And 10 more revolved around a reference to work-life balance being overrated.

So while the negatively scored conversations were just 0.02% of the total conversation set, they were 21% of the total subset that could be scored for sentiment. And of that subset, more than one quarter were focused on the concept not being real at all.

This is where deeper analysis can help us synthesize true insight. Why do people think it’s a myth? Is it that the naysayers are likely cynics who cannot draw hard lines between their work time and focus and that which they spend away from work? Or do the demands of most jobs actually make it impossible to separate work from life? Or is it something else?

The bottom line is that one shouldn’t be dismissive of small data sets from big data, especially when it comes to conversation research. Remember that while we may only be talking about 100 conversations out of 23,000, but those 100 conversations are from people who are proactively discussing the topic at hand, not people being led down a Q&A path by an interviewer or a survey.

This brings delightful structure to that unstructured world.

Interested in learning more?
Subscribe to our free newsletter and get a free style advice every week. We will also notify You about new offers and discounts. Check it!