Oops! Something went wrong while submitting the form. Stuck? Email us directly on contact@sentisum.com.
⨉
In this guide, we'll teach you the ins and outs of feedback analysis so you can turn surveys, reviews and support conversations into actionable customer insight.
.png)
So, someone’s asked you to do a customer feedback analysis?
Here’s what they probably mean:
Feedback analysis is the process of breaking customer feedback down into something that’s easy to understand and insightful.
The way you break the data down depends on the goal you’re trying to achieve.
For example, let’s say you’ve got together as a team and want to kick off a new customer experience project. But, oh no! You don’t know which improvement areas to prioritize.
You think, “shouldn’t we be listening to our customers? Let’s fix the issue that impacts the most amount of customers.”
Customer support chat logs are a great place to find out why customers are frustrated, so you turn there to gather feedback.
A feedback analysis in this context would look like this:
Of course, this is just a shortened illustration of a customer support ticket feedback analysis. We've actually written a full guide for support conversation analysis which you can use to dive deeper.
The 5 step example we just gave is just one lens through which you can analyze customer feedback.
There are a number of different ways to do it. For example, you could instead choose to prioritize issues affecting high paying customers or issues that make customers most angry—even if there’s only a handful of cases like that.
Listening to your customers is probably the most important element of long-term success for a business.
You’ve probably heard companies like Amazon, Apple and Google called ‘the most customer-centric companies in the world’.
The business world holds attributes their success to how well they listen to people and build services that they want to buy.
But, the purpose of listening to customer feedback goes beyond identifying which products to build.
Customer feedback plays a critical role in customer retention and loyalty. Your customer’s pain or friction points when interacting with your brand are areas you must work to improve to keep customers for the long term.
Why does continuous improvement need to happen? Because as a consumer it has never been easier to switch to a new provider.
These days, if you want your customers to stay, they have to be HAPPY. Consumers know it, so brands need to catch up and ingest a customer-first philosophy if they’re going to become the next Amazon, Google or Apple.
Customer feedback is generally qualitative, written in surveys, reviews, customer service conversations and customer complaints.
To be confident in your analysis you’ll need to turn your qualitative feedback into something quantitative (e.g. ‘payment issue’ was mentioned 600 times).
To quantify the qualitative, companies typically use these methods:
There are a number of different techniques out there for feedback analysis.
We use these three advanced methods within our AI platform at SentiSum.
Sentiment analysis is the process of detecting positive or negative sentiment in text.
Since customers express their thoughts and feelings more openly than ever before, sentiment analysis is becoming an essential tool to monitor and understand that sentiment.
A keyword or aspect analysis identifies specific 'things' in the text. For example, if a customer mentions the word 'discount' it will label or categorize the feedback as being about discounts.
A keyword analysis is very dependent on the language used by the customer, making it prone to error and inaccuracies.
Topic analysis, or classification, is a form of AI-powered analytics that reads and analyses like a human does, but considerably faster.
A topic analysis doesn't simply see a keyword, and label the piece of feedback. It takes into account the context of that word and the meaning of the piece of text it sits within. Correct categorisation is not dependent on any specific words used, making the results much more accurate.
For example, a topic analysis tool can identify that a customer is complaining about 'discount code not working' even when they say something like 'the offer didn't apply at checkout'.
Before we get stuck into the step-by-step process of feedback analytics, it’s important to note that it’s time-consuming and subjective.
This method will work best with a small number of feedback pieces, a lot of time, and just one person doing the analysis—any more may change the results because everyone interprets feedback differently.
For larger volumes of feedback, it’s simple, affordable and provides significantly better results to automate the analytics process. Explore our product—which analyses surveys, reviews and all customer support channels in real-time—and book a demo with us here.
For those who endeavour to go on, let's get stuck in.
For this manual analysis, we’re going to do a high-level ‘topic analysis’ and a general ‘sentiment analysis’ (both defined above).
There's a ton of different feedback channels out there. Here's the main ones and their nuances:
Support conversations are the most useful data source for customer feedback. Support ticket logs (from emails, calls and live chats) contain unbiased, qualitative feedback that's an unbeatable source of customer insight.
We've written extensively about why support is the most valuable source of insight, here's one such example on support ticket insight.
Reviews are a core driver of sales as most customers look there before making a purchase. This makes understanding the reasons behind negative reviews important for business growth.
P.s. British Airways currently uses our sentiment analytics tool to analyse all their customer reviews.
NPS and CSAT are the most common ways to collect customer feedback. Understanding the drivers behind positive and negative sentiment at scale is a powerful use case for AI-powered sentiment analytics.
However, NPS surveys are now considered a biased form of feedback, so you'll need to work hard to ensure your results are actionable.
Export your feedback and collect all the raw data in one place (e.g. an Excel sheet).
With it, include any extra information that might help later on like...where did the feedback come from? Who is the customer? What CRM data can we pull on them?
You’ll want to collect the same data on each piece of feedback to have a complete dataset and a meaningful result ultimately.
Once your customer feedback data set is in one place, you need to think about how you’re going to categorise the data.
You’ll need two spreadsheets. One for the feedback you’ve already collated, and another to store the categories, themes and sentiments with which you’ll code the feedback.
For our feedback dataset—CSAT survey results—we decided to categorize the feedback into four tags: ‘delivery issues’, ‘payment issues’, ‘refund issues’ and ‘packaging issues’.
We also added which department will find the feedback most relevant, and will apply a sentiment score using a basic 1-5 scale.
You can expand these to as much as you like, the more detailed you can go the more complex your analysis will be but also the more actionable the results will be.
Here’s an example of our basic taxonomy applied to one survey result:
A root cause analysis requires you to go deep with your analysis, getting to the heart of the issue at scale.
Unlike in our example above, which uses a flat tagging structure, you’ll want to use a hierarchical tagging taxonomy.
A hierarchical taxonomy allows you to categorize feedback at multiple levels (e.g. Payment issue → Paypal isn’t working) so you can draw patterns even at a granular level.
If you’re looking to do a really granular analysis, you should create a clear, codified taxonomy with which to categorise your feedback.
We interviewed a number of experts to write a guide to building a tagging taxonomy here.
How you report your feedback analysis is almost as important as the analysis itself.
Your feedback analysis report needs to be not only understood by others but acted upon. The customer feedback you present should strike a chord with the audience emotionally, while filling them with confidence that they can take this feedback seriously.
Read our eBook here to see how industry experts like yourself are making it easy to understand the value of CX data.
Let’s also take a look at some examples of how you can report your feedback analysis results.
These are taken from the SentiSum platform:
If you’ve done an aspect-based sentiment analysis like you can with the SentiSum analytics platform, you can easily present the topics along with how customers feel about those topics.
If you’re working on a new project to improve a particular feature, a report on changing sentiment can help you track performance.
Furthermore, this report can help your team identify dramatic swings in sentiment that could do with a root cause analysis.
This graph shows how customer sentiment has changed over time for a topic, in this case ‘shopping experience’.
It’s helpful at a high level to understand how customer sentiment is improving for a topic and a visual graph shows clear progress to your team.
Here’s how we present it. Lots of visuals, time series, patterns, ability to deep-dive. Those are some ideas, you can attempt within google sheets.
In the example below, taken from the Sentisum deep-dive view, one of our customers is able to report to their team which topics are driving customer support contact and in what volume.
You can use help statistics like % of Contact Per Order (CPO) to give context to your colleagues. In this example, customers contacted support about ‘recipe feedback’ nearly 10,000 times, which contributes 0.87% of their overall CPO.
You might want to include a core statistic you’re tracking, or a more simple one like ‘what % of overall customer feedback is about this topic?’.
It’s useful to know that in your survey ‘payments’ were mentioned 100 times, but if you started with 10,000 surveys then 100 mentions of this topic makes up just 1% of the issues mentioned.
We built a very simple feedback analysis template to get you started.
Download it for free below 👇
When leveraging the template created for this article, you should start by reaching out to colleagues across your company.
Every team has different interests and needs from feedback, and with their help you can create a tagging taxonomy (tab 2 of the template) that's genuinely useful to your company.
If other departments are involved early, and their goals are taken into account, they’re also much more likely to listen to and take action on your final analysis findings. It's a win-win.
Download it here 👇
We're lucky enough to be able to use our tool in-house to analyse unlimited volumes of customer feedback.
To show what our tool can do, we recently ran our topic and sentiment analysis tool across 100,000s of Trustpilot reviews for companies in two sectors: banking & delivery.
Here's what we did:
"We leveraged Text Analysis to understand this large volume of data, identifying topics and corresponding sentiment automatically.
As part of this text analysis, each review was automatically tagged with one or more topics and corresponding sentiment. For each sector, we discovered which topics customer were talking about most, and
In one of our analyses, we compared the public reviews for two banking technology companies, Revolut vs. Transferwise.
Looking at sentiment over the last two years, both Transferwise and Revolut customers show high satisfaction with Security (>80%).
This analysis is high-level, focusing on only four categories that mattered to customers.
In our topic analysis of food delivery companies, we also took a granular approach to our feedback analytics.
As you can see, our sentiment analytics software discovered which 8 topics which were most mentioned in the customer reviews. 'Taste' was a critical driver of customer feedback—it was mentioned in more than 30% of customer reviews.
There is a wealth of feedback analysis tools to choose from, which can make it difficult to choose.
We suggest booking a number of product demos to look for a tool that can help you with your problem—you’ll get a good insight into the company and how they work through their sales process. A company you want on your side will invest time in teaching you about the market and solutions available.
When choosing a tool, we suggest asking yourself these three questions:
SentiSum uses AI technology to completely automate your feedback analytics at a root cause level. We specialise in customer support conversations, but have solutions across NPS, surveys and almost all feedback channels. Learn more here.
Qualtrics is an SAP owned enterprise software that enables organisations to collect feedback at every stage of the customer journey. They enable enterprises to uncover trends and drive customer loyalty across multiple channels.
Chorus captures and analyses all customer calls, meetings, and emails to identify top performers and uncover insights that could be used as testimonials.
IBM offers many APIs for sentiment analysis based on NLP. The Watson Tone Analyzer, for example, which focuses on support tickets and satisfaction surveys and monitors agent sentiment – whether they’re polite and eager to help, and if they truly solved the customer’s issue.
Rosette has an API that uses AI to analyse natural language. They've branched out from social media to analyse entire documents, for example, the sentiment expressed by customers when they mention a specific product, company, or person.
