Better service backed by better data means higher levels of customer satisfaction (CSAT) which is good for everyone 🤝
This guide will explore the best sentiment analysis methods currently available, in an effort to turn your surveys, reviews, and (extremely valuable) support conversations into actionable insights, ready to elevate your customer journey.
Here’s what we’ll get into:
For those ready to start building their dream feedback system - click here to book a free custom demo with our experts 🔨
What's in the guide:
1. What Is Customer Sentiment Analysis?
2. Why Is Customer Sentiment Analysis Important?
3. How to Analyse Customer Sentiment (Step-By-Step)
4. Customer Sentiment Analysis Template
5. Customer Sentiment Analysis Tools: The 5 Best Options
6. TL;DR - Takeaways
7. Customer Sentiment Analysis FAQ
👈 Click through our menu to the side here to jump around
What Is Customer Sentiment Analysis?
Customer sentiment analysis is the sorting and processing of customer feedback using machine learning automation. Essentially, it is the use of advanced software tools to better understand how your customers feel.
You have to know where the leaks are in order to plug them up - great customer sentiment analysis is key to locating and treating customer pain points efficiently.
Volume is also a consideration, with most companies archiving thousands and thousands of reviews, surveys, and support tickets, with more piling up on a weekly or monthly basis.
At this scale, it is best to use automation, aka machine learning-backed, software to empower the sentiment analysis of your customer interactions.
In addition to being able to scale with large amounts of interactions, automation can also keep your sentiment analysis objective and uniformly tailored to your needs.
Let’s take a peek at some types of sentiment you could try to detect:
1a. Types of Customer Sentiment Analysis
These are just the basics but, as you can see, a sentiment analysis tool can group a statement by a customer based on multiple types simultaneously.
For instance, if a customer leaves a Facebook comment that says, “Your order process is so complicated”
An advanced sentiment analytics tool would automatically pick up multiple ‘sentiment aspects’ from that simple sentence, e.g. ‘complicated’ is usually interpreted as both negative and frustrating - and that’s just a start, with two sentiment types.
This approach is known as ‘aspect-based sentiment analysis’.
Aspect-based sentiment analysis aims to identify both emotions and the ‘why’ behind them.
At scale, say across 50,000 customer support conversations or customer complaints each month, this can be an incredibly useful way for a brand to get a real-time, complex understanding of their customer’s experiences.
Understanding and accurately triaging your pain points will raise satisfaction and curb churn - let’s look at the potential results and methodology.
Why Is Customer Sentiment Analysis Important?
CX Statistics has provided us with three relevant statistics to demonstrate the bottom-line impact of customer sentiment analysis:
1. Customer experience (CX) will be 45% of companies top priority over the next 5 years ✅
2. Investing in CX has the potential to double your revenue within 36 months 📈
3. 86% of buyers are willing to pay more for great CX 💪
You probably catch our drift - CX will be the competitive difference for the majority of brands going forward - and customer sentiment analysis is the key to improving CX.
We’ve distilled the 3 essential components that any successful sentiment analysis approach requires:
2a. Customer Sentiment Analysis Essentials
- Real-time Insight
As we touched on above, manual analysis works for limited, single-channel data. But automated tools are required for modern, multi-channel approaches with tons of data to sort.
Taking ‘data samples’ from a select number of customers in the hopes of drawing sentiment conclusions is no longer best practice. Handling the entirety of your data ensures both accuracy and a nuanced, deep understanding of data that would otherwise be invisible.
This leads us to another clear benefit of automation’s horsepower 💪:
2. Real-time Insight
Speed, speed, speed – best-in-class analysis tools will allow you to identify, address, and fix customer issues in real-time.
Say a negative tweet comes out about your product – with real-time analysis capability you’ll be flagged and able to have your social team respond quickly, remedying the situation and demonstrating your care for your customers.
With a rapid response, you can patch up negative sentiment, and possibly even win loyalty - both outcomes prevent churn and improve your image.
Actionable insights are results drawn from a dataset that can be directly applied to your existing business practices.
Whether it’s the smoothing out of an area of your customer journey or a direct change to your product, these insights are worth their weight in gold as they result in happier customers overall.
For a more detailed look at what actionable insights are and how you can create them, check out our breakdown here 👇
Related read: What are actionable customer insights?
Importantly, insights are only ‘actionable’ if they are accurate.
Manual analysis tends to be inaccurate due to unavoidable human error. Despite best efforts, humans always operate with a small amount of subjective bias. On the other hand, automated analysis (meaning analysis using software) ensures that each and every entry gets viewed through a uniform, objective lens which guarantees consistent and accurate results. Further enhancing the value of accurate, automated results:
Actionable insights are useful for more than just customer experience teams.
Cross-pollinating your insights across your support teams, customer service representatives, product teams, and allowing them to inform your larger strategy will help you to give your customers what they want at every contact point with your business.
Check out our guide to accurately tagging and routing tickets to see this in action and supercharge your support ticket approach 👀🚀
Next, we’ll get our hands dirty with our how-to guide for basic customer sentiment analysis.
How to Analyse Customer Sentiment (Step-By-Step)
This guide to manual sentiment analysis is meant to illustrate the basic machinery behind sentiment analysis.
We may have mentioned that manual analysis is a labour-intensive process - you’ll see why - but hopefully also be able to understand how it’s done and better implement your tool of choice.
For those less interested in a quicker, less granular process, jump ahead to our Top 5 Sentiment Analysis Tools further below. Pair that knowledge with a free demo with one of our customer sentiment experts and you’ll be well-equipped to kickstart a new, revamped feedback process.
Without further ado, here is our step-by-step approach to manual sentiment analysis 💡:
3a. Manually Analysing Customer Sentiment in Excel
Our approach breaks down into 4 critical steps:
- Choose Feedback Channels
- Collect Feedback
- Tag Feedback By Sentiment
- Report Results: Present Analysis and Drive Insights
Step 1: Choose Feedback Channel
The 3 most common feedback channels are Support Conversations, Customer Reviews, and NPS and CSAT Surveys - here’s some background on each.
Support Conversations are an incredibly underutilised feedback channel, which is a shame considering they can be the most useful source of customer feedback.
Support ticket logs (emails, calls, live chats) contain unbiased, qualitative feedback and we've written extensively about why support is the most valuable source of insights - start here with our walkthrough of the potential value of support tickets. .
Customer Reviews are a core driver of sales as most customers look there before making a purchase. This makes understanding the reasons behind negative or positive review sentiment important for business growth.
P.S. – British Airways currently uses our sentiment analytics tool for their customer reviews, check out this case study to help their NPS score take off ✈️
Speaking of customer satisfaction scores…
Surveys - NPS and CSAT surveys have long been industry standards. However, with questions being asked about potential bias in NPS scores, you’ll need a discerning customer sentiment analysis tool to validate your survey campaigns.
Step 2: Collect Feedback
Next, you’ll want to collect all your raw data in one place. For our purposes here, we’re using Google Sheets, but Excel or other graphing software can work just as well. Going forward, we’ll use this simple example template:
As you can see, we qualified feedback with 3 taxonomies - Channel, Positive Topic(s), and Relevant Department.
To come up with these taxonomies you can, and should, mould your taxonomical classification to your specific needs.
This is called ‘taxonomical tagging’, meaning creating new labels for your data based on your brand’s specific needs. This process is an art unto itself – it requires careful fine-tuning and attention as its results directly affect the quality of your output.
Both the nature and the complexity of the data you gather is up to you. Think carefully about how you’re going to categorise the data - what’s best for another business might not suit yours. So, ask what groups/ types of customers interest you, then target those channels.
Complexity-wise, if your process can handle starting off with more information, go for it. For instance, you might consider gathering more aspect-based sentiment information - you remember the four types from earlier – Polarity, Urgency, Intent, Emotion – to unlock more advanced results downstream.
The best tagging approaches also invent novel taxonomies to suit their own needs:
Tagging Tip 🎯– One favoured tag by our customers is the “ChurnRisk” tag which helps us to identify in real-time when a customer is experiencing a problem or emotion that will likely lead them to cancel their account or leave for a competition – utilising this tag makes prioritising those customers faster and simpler.
No matter what you do, take the time you need to create your own best practice – remember, ‘Quality in = Quality out’. Looking for more guidance? We got you with our extensive taxonomy best practices guide.
Sounds exhausting? Luckily, automation offers a more accurate, less overwhelming shortcut.
The data we presented above probably seem basic– because it is. Machine learning offers an easier and more advanced approach to sentiment classification. Sentisum’s automated sentiment tool, for example, uses complex automated labelling practices to speed up the process, empowers it with automation (it comes up with potential groupings for you!), and ensures its insights are both granular (deeper and more detailed) and actionable - continue reading about how it accomplishes this.
Step 3: Categorise Feedback by Sentiment
We've pair our classified feedback with a numeric score - focus on the 'Sentiment' pillar on the far right from our previous table:
See those 1’s and 5’s on the far right? We’ve recorded the negative and positive sentiments detected, but also paired them with a sentiment score on a 1-5 scale. Here’s how we measured those numbers:
More complicated for a reason 😏: Customer experience experts will notice the similarity to NPS scoring. Our ratings here are determined using a similar scale but are uniquely useful in this case as they complicate our data in a useful manner.
Here’s how: These ratings allow us to determine the best approach for each variety of sentiment. A ‘1’ rating, meaning Happy feedback, should be noted for its success and applied to future business practices. A ‘5’ rating, meaning ‘Angry’ feedback, on the other hand, indicates an issue that requires an immediate fix.
By doing this, we’ve taken our categorised feedback – the feedback we broke into groups by sentiment – and further understood it, breaking it into micro-groups, by type of sentiment.
At this point, you’ve collected our data, classified it, and ranked it by sentiment. You’re ready, at long last, react to use complex customer sentiment analysis to distil your data for results 😎
Step 4: Report Results: Present Analysis and Drive Insights
If you use the right taxonomies to rediscover your data, then rank their sentiment, you’re ready to take the final step and uncover new, previously-unknown nuggets of knowledge - aka insights. A good rule of thumb for reporting sentiment analysis data is that:
Accessible insights are actionable insights 🙌
The final step of the process, ‘reporting’ your insights, means making them understandable to everyone that might need them, from highly technical employees to those without much knowledge in the area. Your results need to be clear and trustworthy.
How can you test for this? We will get into some examples, given that reporting techniques are one of our specialties at SentiSum, we’d be remiss not to set you up with a few in-depth resources first 👀:
For experts looking for deep knowledge, we’ve compiled an ebook on presenting analysis results internally.
Or, for those looking for a quicker fix, here’s our outline of our survey report examples.
Check either for explainers on everything customer sentiment reporting - your teams and your brand will thank you.
On to our example 😤:
4a. Time-Series Report:
Take a look at a 'Time-Series Report' - this report tracks the percentage change of tags over a given period of time - here's a sample report generated by our sentiment analysis tool:
Time-series change is a great place to start because it offers clear data that should spark direct action - or that’s the hope.
If an untrained eye looked at this graph the Absolute Change +/- and the graphs that accompany it jump off the page. It’s clear that Ease of Booking is doing great and that Staff Conduct and Covid Rules Following are drawing complaints.
Using this chart, any level of employee would be able to conclude that the Conduct and Covid Rules Following need improvement and should be able to start putting a plan into action, treating the new pain point uncovered by your analysis 🩹 - a superb example of accessibility transforming insight into actionable insight.
Customer Sentiment Analysis Template
Before we get into our rundown of the best sentiment analysis tools out there, we’ve provided a link to the template we used for the above section for you to play around with.
Click below 👇 to download the Google Sheet template and mould it to your team's needs.
Customer Sentiment Analysis Tools: The 5 Best Options
Automation makes sentiment analysis a million times easier - but the right automation can transform your whole relationship with your customers.
Choosing the right sentiment analysis tool should be approached like any big purchase - a bed, a car, a house, etc:
You’re going to be using your sentiment analysis tool a lot so the right fit is important. Think about not only what you need, but its place in your workflow amongst your other business software, such as the Sentisum x Zendesk pairing 👀
In this case, you are a special and unique snowflake - you’ll need a tool that can do the heavy lifting and deliver results that are suited to your business, not others.
Before you buy, we recommend booking a number of demos and listening to as many experts as possible
In addition to being best practice, this kind of thorough approach will help you gauge how well you fit with the tool’s company. You want a responsive, attentive company that will cater to your needs for the lifetime of your business, not just at point of sale.
That said, you’ll need somewhere to start, and we’re happy to help,
We’ve ranked our five top choices based on the following criteria, which our experts find to be crucial:
- Preferred Feedback Channels - How is your data coming in? Single channel or multichannel?
- Analytic Depth - How granular of results do you need? Surface level or deep?
- Reporting Format - How are you going to display your reporting? Powerpoints or advanced, multi-team datavis?
Keep in mind that what works best for you might not always be the most expensive or resource-intensive option. You know your feedback, and if it doesn’t need a certain bell-and-whistle, skip it as it could skew your input and corrupt your end results. Deeper results also take a more careful approach in order to be made accessible (aka comprehensible) to all.
Let’s hop to it, including a ranking of what we find each option to be best for.
1. SentiSum- Best for Deep Insight, Support Analytics
Hey, that's us! Here are our ratings, followed by a quick explanation - we’ll follow this format throughout.
Preferred Feedback Channels: Support, Survey, Review
Analytic Depth: Deep (Best in class)
Reporting Format: API Integrated (Zendesk, Freshdesk, Intercom, & many more)
SentiSum uses AI technology to completely automate your sentiment analytics at a root cause level. We specialise in customer support conversations but offer solutions across all feedback channels, from surveys to CSAT scores to reviews and much more 🏋️– Learn more here.
2. Talkwalker - Best for Social Media
Talkwalker's quick search looks at your mentions, comments, engagements, and other data to provide your team with an extensive breakdown of how customers are responding to your social media activity.
Preferred Feedback Channels: Social Media, Review
Analytic Depth: Medium
Reporting Format: Real-time, Datavis suite
3. Brandwatch - Best for Entertainment and Media
Preferred Feedback Channels: Social Media, Media Content
Analytic Depth: Deep - nuanced and outreach-focused
Reporting Format: Real-time
Similar to TalkWalker but aimed at marketing cutting-edge entertainers and influencers. Businesses use Brandwatch to monitor mentions online and understand voice of customer (VoC), detecting fluctuations in sentiment, and measure brand visibility 24/7 in real-time.
4. MeaningCloud - Best for Multichannel, Multilingual
Preferred Feedback Channels: Text/documents, Social Media, Support
Analytic Depth: Medium but broad
Reporting Format: Multilingual into omnichannel
MeaningCloud is your best option for multilingual sentiment analysis, able to merge all your diverse feedback into a database all your employees can understand. This online tool runs aspect-based sentiment analysis to decide whether specific topics are mentioned in a positive, negative, or neutral way.
5. Rosette - Best for Customer Relationship Management (CRM)
Preferred Feedback Channels: Text/document
Analytic Depth: Deep text analysis
Reporting Format: API integrations
Rosette offers an advanced innovative API that uses AI to analyse documents using natural language processing (NLP). They've branched out from social media to analyse entire documents offering topic/subject/name indexing, relationship extraction, and language/semantic similarity detection among other novel functionalities.
There you have it - of course, other options exist but those five offer a good snapshot of the length and breadth of the industry, each excelling in its specialty.
TL;DR - Takeaways
Look, if you made it this far, you’re ready to get out there, armed with the right tools and tricks, and elevate your sentiment analysis process.
If you just skipped to the end (understandable) here’s what happened:
1) Great customer sentiment analysis can transform your customer satisfaction, increase loyalty, and cement your business ahead of the competition.
2) However, your analysis needs to be accurate and actionable - manual analysis, due to inherent bias, makes this difficult
3) Automated customer sentiment analysis can handle this for you by using machine learning to tag customer feedback for you.
4) So, you’ll need to choose the right customer sentiment analysis tool (software) to fit your business, taking honest stock of what feedback you take in, and what you’re looking to do with it.
However, SentiSum can make that choice easy for you - our support analysis engine offers multichannel capacity - it can simultaneously the absolute most out of your support logs and comb your reviews and customer satisfaction surveys.
We should also mention we feed all that data into the most advanced and comprehensive customer experience management (CXM) software out there - check out our array of integrations.
Have more questions about customer sentiment analysis? Check out our FAQs below. Or, if you’re looking for other downloads about customer feedback analysis in general - take a look at our blog 🤓