The limitations of using text analytics to analyze conversations
October 15, 2020
We are often asked about the difference between traditional text analytics tools and the type of conversation analytics Tethr provides.
If audio recordings can be transcribed into text, can’t we just throw that text into the same tools we’ve successfully used in the past to analyze survey verbatims or customer reviews? Won’t that be sufficient for understanding what is happening in our service and support channels?
Gaining true business intelligence from your customer support contact center or customer calls with sales team should analyze the conversation, not just the words exchanged.
There are some obvious functional reasons relying on simple chat analytics or speech analytics doesn’t really work all that well. First, the data sets involved in customer conversations tend to be massive.
Most text analytics engines–even enterprise-grade tools capable of true scale in aggregate–are built to understand smaller pieces of text. Think of it like reading a tweet compared to reading a long-form essay.
Second, most text analytics software is built for one-sided feedback channels, or what we sometimes refer to as “mono.” Conversation analytics are purpose-built for deriving insight from two-sided exchanges between a customer and the agent or rep (i.e. “stereo” data).
But on a more fundamental level, the main difference lies in how data is classified and organized. To illustrate, let’s use an example with which we’re all familiar: forests and oceans.
Text analytics vs. conversation analytics
Imagine for a moment you are a park ranger in charge of managing a forest. It’s your job to keep the forest healthy and all of the trees well maintained. How do you know you’re doing well? You probably start by counting all of the trees, grouping by species. And then track over time how many trees are living, how many new trees are planted, and maybe the rate of growth.
It’s not an easy job and there are plenty of complicating factors like climate, weather patterns, and a host of animals to consider. But all easily observed and feels reasonably natural. After all, you can see and count each tree - even in large forests, if more time consuming - and there are well-established and identifiable taxonomies you can rely on: an oak tree has oak leaves, an elm has specific seeds, etc.
Text analytics involves counting keywords
More simply, counting is a relatively straightforward analytic approach. Many traditional text analytics tools aim to bring structure to unstructured text by essentially the same process: counting word frequency. The best tools will still add a lot of value in organizing words into hierarchies and topics, serving up trends and patterns. But it’s still primarily about text analysis of the letters and words.
Now let’s change your job. Instead of managing a forest, you’re now an oceanographer tasked with keeping all the plants in a particular sea healthy. It is so big you couldn’t possibly ever physically observe it all.
Some parts involve very intricate ecosystems on their own, like those surrounding coral reefs. In fact, oceans are so unexplored, you’d have to imagine each observation is much harder to classify precisely because it’s new: just as likely to be a new species or new version of an existing species that you’ve never before encountered.
As such, counting, as an analytic method, can only get you so far. Rather than bucketing all information into predictable and known groups, oceans require processing new information in ways that allow you to understand the relationship it has with what is already known. How does this fit; where does it fit; how should I interpret it; does this new information change any previous interpretations?
Oceans of unstructured data require processing new information in ways that allow you to understand the relationship it has with what is already known
Human speech is complex and complicates analytics
Analyzing the ocean of unstructured data found in conversation requires a similar approach.
Human speech is complex and often unnatural, interspersed with any number of conversational shortcuts (resulting, in effect, in situations like “you get my point” but without explicit articulation).
With at least two parties involved, interpretation can change based on a given context.
On top of that, converting speech to text often results in mistranscriptions (even from the most accurate automatic speech recognition technology in the world); and asynchronous messaging such as chat and email similarly produce misspelled words and shorthand descriptions. It adds up to increasing interpretation difficulty.
Most text analytics rely on Natural Language Processing. This focuses primarily on detecting specific words or, in some cases, basic word groups.
This makes sense when counting works. But when aimed at human interactions you end up with a word cloud full of and’s, uh’s, and what’s?.
Knowing a lot of customers said the word “what?” might be interesting, but what the heck does it mean? Why did they say it more this month than last?
Moreover, analyzing information using word counts often fails to capture the broader context of utterances within conversations and, as a result, can be limited to relatively few concepts.
Beyond counting – scoring concepts for meaning
Tethr’s approach to conversation analytics captures more abstract concepts that are expressed in more complex utterances. We also look at customer interactions and the combinations of utterances within a conversation.
The result is like the difference between detecting a specific sentence and detecting the idea that sentence conveys in every possible way it can be said, in any language.
It's the difference between detecting a specific sentence and detecting the idea that sentence conveys in every possible way it can be said, in any language.
The most powerful way to classify concepts, rather than counting words, is to use scores. Scoring full interactions pairs concepts with meaning, building an understanding of relationships to larger business goals such as customer loyalty or agent performance.
Tethr + text analytics
At Tethr, we score data on three levels:
This is how we connect unstructured data to concepts.
Scoring concepts (categories) in conversation data:
The Tethr library categories reflect years of training a machine to recognize whole concepts in syntax, as represented by compilations of phrases and utterances.
In any number of chats, there are dozens of ways a customer can convey a simple concept, like they don’t have their account number. We’ve grouped them into categories so we know in any given social interaction, what the customers’ intent was.
We measure the strength of the relationship between the phrase and concept using scores that range from 0 – 1 (with 1 being high) on two parameters: a) precision, which reflects possible false positives; and b) recall, which reflects possible false negatives.
Give Tethr any new phrase – any given utterance – and we can quantify within seconds the strength of its relationship to any one of hundreds of known concepts.
2. Score the relationship between an interaction and individual concepts/categories:
This maps concepts to interactions. Tethr measures the degree to which each concept is detected as present across each individual interaction.
Some concepts like Customer Frustration can be articulated in thousands of different ways. New articulations do occur, some very specific to a company or industry. Leaders require accurate classification to make confident decisions.
Tethr users can easily add and modify phrases and utterances. Then, machine learning automatically serves up new similar-but-not-exact matches to those new phrases. Again, on a numerical scale, one can view the similarity of meaning amongst a large number of phrases. This allows us to accurately detect entirely new utterances that represent a given category, without ever having to create a rule. As a result, our system can generalize from examples of a category, rather than simply identify what it has been trained to recognize.
3. Score entire interactions to reflect the relationship to structured outcomes:
Scoring the entire interaction allows Tethr to unearth context hidden in the course of a conversation. The scores also reflect the relative intensity of given events.
It’s common for some individual variables to have a positive effect when paired with certain other variables, and then have a negative effect when paired with others.
This type of nuanced understanding isn’t about counting–it’s about insight packed into combinations and the strength of different relationships. We have to unique scores that we give to each customer interaction: The Tethr Effort Index (TEI)and Agent Impact Score (AIS).
We apply these scores to all interactions flowing through Tethr. They are built on a scale from 0 – 10 and predict how customers would have responded to the Customer Effort Score (CES) survey, based on interaction events and, where applicable, several audio features.
Tethr customers use TEI and AIS to easily find the best and worst interactions, using such filters as a way to compare and contrast category frequency associated with each end of the spectrum. With this type of wide-scale, predictive and accurate understanding of behavior, automated actions can be set up to create important alerts, drive workflows, improve escalation processes, and enact targeted and tailored customer feedback loops.
Want to learn more about how Tethr analyzes conversations? Schedule a demo today!