Tatiana Crisan

Using text analytics to guide product recalls

Tatiana Crisan — Sun, 14 Oct 2018 20:10:12 +0000

Text analytics platforms can empower big manufacturing companies to quickly assess their customers’ expectations, possible miscommunication issues, and the impact the company’s actions on customer sentiment. This approach to crisis management enable businesses to seamlessly align internally and to place their customers at the centre of their product recall strategy.

For instance, one of our clients detected a safety risk in one of their products and issued a product recall that affected 15,000 customers. When their customer experience manager, John, learned that the company’s engineers estimated it would take several months to fix the problem, he knew his department needed to act fast to guide the organization in providing the best service to their customers during the crisis.

Due to the magnitude of the product recall, several departments were involved, each with their own objectives. To respond to these objectives and to influence the internal stakeholders to support his cause – the customer – John needed reliable data. Upper management wanted proof of the benefits before investing in compensation for the customer. Engineering needed to be persuaded that fixing the technical issues was the top priority. This data would also assist him in communicating the issues in a way that would help the customers by answering their questions.

AI does the heavy lifting

John had been promoting Customer Experience (CX) internally for almost four years. He had already built the Voice of the Customer (VoC) program, which included sending surveys to customers and franchise managers to ensure a consistent brand experience regardless of where the customers were buying from. As a result, when the recall crisis hit, he didn’t have to start from scratch.

Keatext machine learning algorithm transforms customer feedback into an easy-to-understand report that allows him to take the pulse of his customer base at a glance.

An important part of the feedback these surveys collect are answers to open-ended questions, which John values highly for their rich insights. However, it can be problematic to analyze a large volume of answers during crisis management, when speed is vital. To analyze this type of feedback, John had been using Keatext for the past three years.

Keatext machine learning algorithm transforms customer feedback into an easy-to-understand report that allows him to take the pulse of his customer base at a glance. That’s customer care! John used this report and his previous experience with Keatext to help him manage the situation. He decided he would distribute two different surveys to the affected customers and franchise managers at two different moments in the product recall. In this way he would understand their needs and strategize accordingly with internal stakeholders.

A bird’s eye view on customer care and sentiment

During the early days of the product recall, John sent out the first survey. To get a 3600 view of customer opinion, he also collected data from social media, forum discussions, Salesforce case requests, and call transcripts. He consolidated the data from these sources into Keatext.

Right away he could see something that didn’t surprise him: the Customer Sentiment Score, a unique Keatext customer satisfaction rating extracted directly from feedback, was 68% lower than in other surveys done in the past. Additionally, during those first days of the recall, the feedback in the four categories changed significantly. He now had tangible proof to present to his internal stakeholders that customers were unhappy.

A typical survey (Chart 1) has a higher percentage of Praises (positive comments) than Problems (negative comments), and includes a few Suggestions and Questions.

The first survey distributed during the product recall (Chart 2) showed more Problems than Praises, as customers wanted to have their products returned as soon as possible. John found the Question category particularly interesting, having realized he could use the customers’ questions to advise the legal team. Based on the insights he presented, the company’s legal and communications teams crafted a recall updates announcement in tune with customer interests and expectations.

After the recall updates announcement, John sent the second survey to the same customers and dealers. In the feedback, he found that the announcement had improved the Customer Sentiment Score by 29%, but the percentages of Praises, Problems, Questions, and Suggestions remained almost unchanged. However, thanks to the comments aggregation feature offered by Keatext, John could see that the content of the Questions had changed.

Before the updates announcement, multiple customers asked questions that communicated their desire for updates about the recall, phrasing their questions in similar ways. After the updates announcement, not only had the variety of questions increased, they had become more specific. John communicated these results to the legal and communications teams, and together they concluded that a Recall FAQ would be the most appropriate way to address the uncertainties the feedback revealed.

With Keatext, John was able to guide his organization through a difficult time with the help of the voice of the customer.

Another insight that surfaced was that franchise managers didn’t know how to help their customers. Using this data, John advocated for a program that empowered franchise managers to assist their customers by providing compensation such as warranty extensions.

With Keatext, John was able to guide his organization through a difficult time with the help of the voice of the customer. Using data to back up his recommandations, he ensured that his company served its customers with transparency, responsiveness, and most importantly, customer care and empathy.

The post Using text analytics to guide product recalls appeared first on Keatext.

3 Steps to Use Text Analytics in Your Employee Listening Strategy

Tatiana Crisan — Thu, 19 Apr 2018 23:00:52 +0000

This guide was originally written in 2018. A lot has changed since then (does 2020 sound familiar?), so we’ve added some modern context to help you understand exactly how HR has progressed in its digital transformation.

In the 2010s, from Glassdoor reviews to the Best Place to Work awards, the corporate world developed a keen interest in gauging, rewarding and publicizing the health of company cultures. But beyond offering great opportunities for PR, fostering internal engagement and employee satisfaction was good business.

A study by Harvard-based consulting firm Kotter showed that companies with performance-enhancing cultures that “facilitate adaptation to a changing world” saw a 4x increase in revenue growth. And for those looking for top talent, a widely quoted 2012 study by Corporate Responsibility Magazine revealed that 69% of respondents wouldn’t take a job with a company that had a bad reputation, even if they were unemployed.

Today, we have data that shows that companies focusing on wellbeing see a 5% productivity increase, and for every dollar spent on wellness programs, a return of $3.27 in healthcare savings plus $2.73 in reduced absenteeism costs. And according to Gallup, engaged employees are up to 25% more productive and make 50% fewer mistakes, with sick leave rates dropping by 30-40%.

But a healthy corporate culture isn’t just about boosting productivity. On the negative side of things, it used to cost between 30% and 150% of an employee’s salary to fill a position. Now, replacing an employee can range from up to 90% of a yearly salary for an entry-level position, to 200% for professionals and leaders. Businesses spend more than $1 trillion a year replacing employees who voluntarily leave, and 48% of employees will look for a new job if they feel their corporate culture is going downhill—and that was back in 2018.

The ultimate outcome of this data is that the responsibilities of HR departments have shifted. Modern HR leaders have taken a people-centric approach that emphasizes the role of an employer in the wellbeing of its employees. That means mental health, development potential, work environment, leadership philosophy, compensationm, and more.

Yet, despite our increased understanding that corporate culture is an essential part of any management strategy, it often proves elusive to measure, manage, and maintain. This remains true even over the period of time we’re analyzing here—a period that has seen disruptions as massive as remote work, quiet quitting, and the entrance of a new generation into the workforce.

To put yourself on the path to creating a healthy company culture, it’s necessary to look at what defines corporate culture, its impact on profitability and the ways traditional culture frameworks, employee listening programs, and text analytics technology can help yield scalable shifts for organizations of all stripes and sizes.

Shifts in Corporate Culture from 2018 to 2025

Back in 2018, highly qualified millennials were more focused than ever on aligning with a company’s values and ethics. According to The Guardian, change was “being driven by the so-called millennials. Of those born between 1981 and 1996, 62% want to work for a company that makes a positive impact, half prefer purposeful work to a high salary, and 53% would work harder if they were making a difference to others.”

This remains true today for younger generations. In fact, these sentiments have expanded into new conversations such as those around mental health in the workplace. When it comes to attracting and retaining talent, HR leaders are looking at a hiring landscape in which 60% of Gen Z workers consider, among other things, mental health resources when choosing an employer.

Data from the WHO also shows that the global cost of mental health issues is astronomical: approximately 12 billion workdays are lost to depression and anxiety annually, costing an estimated $1 trillion loss in productivity, and projected to cost the global economy $6 trillion per year by 2030.

While the core components of what we understand as company culture remain, the context has radically changed. Rebuilding and nurturing company culture in a dispersed or hybrid work environment is a formidable task, with 47% of HR leaders uncertain about how to drive change. Now, more than ever, reinforcing trust between employees and leaders is essential for successfully reshaping company culture.

Defining Your Culture in the New World of Work

Step 1: Identify your starting point

While the idea of corporate culture may be hard to pin down, there’s been extensive research on the different elements that shape and influence it. One particularly useful framework is the Johnson and Scholes Culture Web model, which helps deconstruct the often unspoken “way we do things around here” into six tangible elements that shape employee experience:

These six components, beyond helping you draw contours around the seemingly intangible cues you’re sending your employees on a daily basis, provide a structure that will guide you in defining the culture you want to foster in each of the spheres. Only then can you start strategically gathering data and creating a measurable framework for progress and success.

Step 2: Gather actionable data

With your company Cultural Web in place, it’s time to turn to your employees for an objective audit of how well it aligns with the existing cultural paradigm.

In 2018, we were thinking primarily about data that seems pretty static now, like traditional employee surveys and anonymous feedback forms. Although we knew that the richest insights are always found in unstructured feedback, this old model of traditional surveys is obsolete.

The new standard is dynamic, continuous listening: shorter surveys that are sent more frequently to collect feedback on specific topics or themes. This agile approach allows organizations to dive into the finer details of company culture that deserve attention in addition to the big, quarterly or annual ones.

This is where text analytics technology comes in. New capabilities of AI in 2025 are pushing boundaries, and this technology has become a crucial partner for HR leaders to automate analysis and reduce manual tasks in order to focus on insights and solutions.

Here are four key benefits of working with text analytics instead of manual analysis:

Speed: Text analytics drastically cuts down the time it takes to review and understand large volumes of open-ended employee comments. For example, manually sorting through feedback from thousands of employees could take months, but with text analytics, it can be done in as little as 10 minutes. This quick analysis allows HR leaders to stay constantly aware of employee feelings and involvement, making it possible to react swiftly to issues in a fast-changing work environment.
Accuracy: This technology can reach about 90% accuracy, which improves as a system processes more data and learns to spot trends and unusual patterns. The objective is to understand text with the same subtle and contextual understanding as a human reader.
Neutrality: Text analytics platforms offer consistently fair and objective information, whereas in manual analysis people will unconsciously project their own feelings or interpretations onto the feedback. This objectivity is important for guiding employee engagement plans and making sure that the insights used are unbiased and reliable.
Scalability: With text analytics, organizations can analyze complex, unstructured feedback from many different sources in just minutes—this includes open-ended surveys, transcripts of one-on-one meetings, focus group discussions, employee forums, and chat channels like Slack. As the amount of feedback has exploded since we moved to hybrid and remote work settings, many more digital feedback channels need to be covered than previously.

Since 2018, text analytics providers have come a long way to integrate generative AI into their core offerings. Keatext, for instance, now generates recommendations to improve employee experience in natural language thanks to LLMs. Report generation is another area that leverages this new technology to accelerate the delivery of insights and enable HR leaders to be more responsive to issues.

Step 3: Keep that feedback loop going

With text analytics, HR leaders can encourage employees to provide open-ended feedback without worrying about how to effectively analyze it all. While conducting this kind of analysis before could only be done manually once or twice a year, at most, text analytics allows you to keep a constant finger on the pulse of employee engagement and sentiment. This is true even as your company grows, pivots, downsizes, adds perks and benefits or implements new corporate hierarchies and processes. Corporate culture is a living, breathing thing, and it requires nonstop attention and care if you want everyone to stay in sync with your company’s values and objectives.

Now that your initial feedback loop is set up and various channels of unstructured feedback are continually streaming in, you can adapt quickly as issues arise. In today’s fast-paced marketplace, agility means you’ll have a better chance at keeping your brightest minds engaged, happy, productive and, most importantly, on your payroll.

The post 3 Steps to Use Text Analytics in Your Employee Listening Strategy appeared first on Keatext.

How to Choose the Right Next Generation Text Analytics

Tatiana Crisan — Mon, 19 Mar 2018 20:05:30 +0000

Did you know that 50 percent of Americans post at least one online review a day? Once those words are out there, they weigh heavily in a potential buyer’s decision to do business with your company. In fact, data shows that 88 percent of people trust online reviews just as they would a personal recommendation. Since most of these reviews contain unstructured feedback data, it’s become crucial for survey and VOC providers to supply platforms that are able to convey and contextualize unstructured customer feedback alongside the available structured data.

The only way to achieve this is to integrate a text analytics component into your survey or VOC platform. But as you might expect, not all text analytics solutions are created equal or set up to provide the same level of customer insight. To help separate the wheat from the chaff, this blog post focuses on the technological aspects survey and VOC platforms product managers need to take into account before making a final decision on a text analytics partnership.

While the technologies and methodologies that inform text analytics – AI, machine learning, deep learning and natural language processing (NLP) – are in constant flux, most would agree there are only two approaches to capturing and deciphering VOC data. First, there’s the traditional way, which is the keyword- or dictionary-based technology used by dominant players in the market. Then there’s the new way, which involves continually implementing the very latest in academic research about machine learning and its subset, deep learning.

1. The traditional way: Text analytics based on rules, word counts and dictionaries

Many of the text analytics solutions used today are still built on those earlier incarnations of AI, which rely on rigidly programmed rules and predefined keywords. Those rules and keywords, in turn, are layered onto established industry verticals before being customized for each client. Plus, integration can take months to execute and be costly due to the need for specialized expertise. Finally, predefined keywords inevitably leave words out, creating blind spots when trying to understand customer feedback. As a result, once these complex systems are set up and ready to generate insight, you’re at risk of suddenly getting stuck: Any change, even the use of a new word in the marketplace, will require the solution to be entirely reconfigured.

For companies operating in stable industries that expect little variation in customer feedback, this traditional approach to text analytics might be adequate. But for companies overseeing large multipronged networks of user-feedback channels, a more sophisticated solution is required, one that focuses on continuous improvement, adaptation and agility.

2. The new way: Next-generation text analytics built around machine learning and deep learning

This type of text analytics offers a powerful early-warning system, allowing companies to take action before issues become critical.

The ideal text analytics solution for companies operating in dynamic, fast-paced marketplaces will infer nuanced meanings from key context data. This type of text analytics offers a powerful early-warning system, allowing companies to take action before issues become critical.

To continuously improve and adapt to new knowledge, AI needs to be flexible and agile. That’s why next-generation text analytics relies on machine learning and deep learning to build complex NLP algorithms trained to “understand” language in a human-like way – by extracting meaning and even sentiment from context. Armed with more comprehensive understanding, the algorithms are able to constantly spot, analyze and integrate new patterns.

Check out this comparison chart that shows how both types of text analytics technology handle VoC platform requirements:

3. Choosing the right product: Machine learning core vs. add-on

There are two main ways a product incorporates machine learning: It is a core part of the original architecture or is sprinkled on top later as an add-on. The recent rise in popularity of AI is primarily due to breakthroughs in machine learning and deep learning, and it’s become fashionable to throw that jargon around. In fact, most established text analytics markets that now thread these buzzwords through their marketing messages have opted for the add-on approach.

As a buyer, either solution might suit your needs. Nonetheless, it’s important to establish if the machine learning in the product you’re considering is core to it or has been added on as an attractive afterthought. Having this knowledge will equip you to make the right call for your company.

Ultimately, you can’t know how well a text analytics solution will work for you until you test it on your datasets and get a representative sample of the results. Make sure to use the kind of datasets you encounter most often in your analytics research, and once you identify them, compare the test results from several solutions against the same dataset. This is the only way to establish with certainty which solution is the right fit for your company.

The post How to Choose the Right Next Generation Text Analytics appeared first on Keatext.

How to Find the Right Text Analytics Solution for Your Platform

Tatiana Crisan — Mon, 22 Jan 2018 21:07:57 +0000

Adding text analytics and sentiment analysis capabilities to your VOC or survey platform is no easy feat. That’s why we chose to work on a series of blog posts aimed at helping VoC providers strategically pick and purchase the right text analytics partner. In this final blog post of the series, we’ll look at different types of text analytics vendors and the factors you need to consider when comparing them. As a special bonus, we’ll leave you with a party favour of sorts; a downloadable, editable comparison chart that’ll help you navigate through your options and define the most relevant buying criteria for your company.

While every company in the text analytics space has it own, unique approach to identifying and extracting insight, there are three kinds of companies often found at the crossroads between text analytics and customer experience: customer experience platforms, API-only providers and full text analytics platforms.

1. Customer experience platforms: Industry-specific and difficult setup

As a VOC provider, you’re probably familiar with these vendors. Not only are their solutions well established in both the text analytics and the customer experience market, but there’s a high likelihood they’re your direct competitors.

In most cases, the leaders in this space use relatively rigid and rule-based keyword-based technology to extract context and meaning from unstructured data. This approach has a direct impact on accuracy; proving consistently good at recall, but not necessarily with precision or subtle nuances. Moreover, VoC providers are often surprised to find that once their CX platform has been implemented and set up, accuracy issues and blind sports become hard and labour-intensive to course correct.

Using a keyword-based solution means you’ll need to plan ample time and brainpower to set up each of your existing and potentially targeted client verticals.

In non-traditional verticals where customers don’t always express themselves in the ways documented in vendor-provided industry vertical libraries and augmented by your specifications, accuracy can be noticeably reduced. To get a sense of how well tailored the platform might be to your industry needs, we recommend asking vendors about their experience in your verticals before committing to a lengthy integration process.

Another element to consider with CX platforms is your data dashboard. Most text analytics users expect to see their data not categorized in buckets, but structured in an organic way reflective of the way customers usually express themselves. So unless you’ve set aside the time and resources to build your own, make sure you thoroughly evaluate whether results are presented

Additionally, using a keyword-based solution means you’ll need to plan ample time and brainpower to set up each of your existing and potentially targeted client verticals. To do so, the vendor will usually help you to define and configure the dimensions of your analysis while taking into account industry-specific terms, words and jargon related to your customers’ products or services. The entire cycle can take anywhere between 9 and 12 months to carry out. Moreover, you’ll need to ensure you meet the necessary infrastructure requirements to get started. If any of those requirements need to be added to your platform, you’ll need to budget for further time and costs.

Another element of resource allocation you’ll need to consider is training – which will be a prerequisite to anyone being able to use the platform, and is often offered at extra cost. The good news is, with built-in analysis tools and dashboards, trained users will usually find it quite easy to investigate results, identify insights and actions, and present their findings. You can also rest assured that most vendor agreements include an ongoing support contract, which allows you to request adjustments to your initial specifications. To avoid any surprises, you might want to request additional setups and feedback channels in your support contract.

2. API-only vendors: Limited functionalities, extra work required

While an API is simply a method of helping different softwares communicate with one another, it tends to connote something a little different in the text analytics industry. When vendors advertise text analytics or NLP APIs, they usually mean that they’re only providing a text analytics layer within a wider, more comprehensive text analytics solution. With this layer alone, initial functionality is typically reduced to just a few basic features like key topics, categories and tag clouds.

Here’s an example of a typical API-only solution vs. Keatext’s comprehensive stack (full text analytics solution):

If you choose to go with an API-only solution, you’ll likely need to internally build up the remaining layers for more advanced features and granular insights. Here’s an overview of the additional layers built into Keatext full stack solution in order to cover a higher level of use cases:

Administration layer: Helps organizations manage users, access levels and keep track of their usage.
Knowledge management layer: This layer has built-in logic that serves the right information to the user when they request it. Users can create custom categories and capture specific industry and company knowledge.
Normalization layer: Nimbly interprets the data provided by the analytics layer, allowing it to detect changes such as trends, events or improvements over time. Depending on the technology used, this is where advanced features like word grouping and automatic metadata correlations become possible.
Aggregation layer: Stores original metadata and analytics detected by the artificial intelligence pipeline for all of the documents. This means the user can perform advanced queries in a unified database across all of their datasets and communication channels, such as: “rising issues in the last week across all touch points”.
Application: An application containing a user interface needs to be built on top of the technological solutions. For a wider user base, this shouldn’t require specialist knowledge such as coding.

At first sight these API-only text analytics solutions seem particularly attractive and advantageous because of their low cost-per-comment rate. That said, the human labour and costs associated with internally building a fully-fledged solution to support a standalone layer of text analytics can be extensive and dangerously hard to scope at the beginning of the project.

3. Full text analytics solutions: No blind spots, scalable

There has been a recent burst of innovation coming from small independent companies with close ties to the academic world. By leveraging the very latest research in NLP and AI, these next-generation text analytics providers have been able to move away from rigid keywords and rules in favour of more agile, iterative machine learning technologies. By maintaining such narrow ties with academia, full text analytics solutions are likelier to be built upon the most recent technology.

One of the biggest advantages of this kind of solution is that it’s less likely to leave you with blind spots. Rules and keywords-based solutions allow analysts to find what they’re looking for, but AI enables everyone – data expert or not – to find what they’re not looking for.

Rules and keywords-based solutions allow analysts to find what they’re looking for, but AI enables everyone – data expert or not – to find what they’re not looking for.

If your platform is also innovative and structure around industry best practices, you’re likely to integrate and implement these next-generation systems within a few days or a couple of weeks – depending on the complexity of the project.

As for the speed of data collation for a pure machine learning solution? It’s dramatically higher than competing solution categories. Once your initial system is implemented, you’ll be able to explore, analyze and segment your data efficiently and effectively by using the built-in analysis and visualization tools.

Full text analytics solutions are also much easier to scale. If, as with Keatext, there is no setup or configuration required, any increase in the volume of unstructured data from existing feedback sources is easily accommodated – as are new sources, products and markets.

If you’re looking to provide your clients with a self-service solution that allows for complete independence from costly data expertise, a full text analytics solution is likelier to supply a simple interface that makes it easy to interact with the results of the AI analysis, present findings, establish data-based recommendations and quickly share them with decision-makers.

4. Information is power

No matter which solution you decide is the best fit, we hope this series has given you the information and background you need to feel confident and clear-eyed in your final decision. With so many vendors vying for your attention, one of the biggest challenges has been fighting the market leaders to offer more transparency and visibility to the entire spectrum of text analytics solutions. So as you consider partnering with a text analytics provider, it’s important to do your due diligence. Here are a few questions to help your background check:

Do they have established customers?
Where are they getting their funding?
Do they have solid academic credibility?
Do they specialize in text analytics?
Do they have experience working in your verticals?
Will they be able to scale and grow with you throughout the years?
What kind of support and collaboration can you expect from their team?

As promised, we’ve got a few extra resources to help with your buying journey. Click here to download the text analytics vendor comparison sheet.

The post How to Find the Right Text Analytics Solution for Your Platform appeared first on Keatext.

4 Industry Applications of Customer Experience Analysis

Tatiana Crisan — Mon, 10 Apr 2017 20:01:30 +0000

In the era of social media, when the online sharing of our experiences and feelings about a product or service has become a daily routine, customer experience is a key brand differentiator. Sentiment analysis, also known as opinion mining, allows businesses to keep very close tabs on customer communication, so they can interpret their feedback and understand what customers want and need. From hospitality to finance & banking, this blog post analyzes how sentiment analysis tools improve customer experience in different industries.

Jump right into our article to learn about your industry:

Retail: Personalizing the e-commerce experience
Hospitality: Online reputation management
Healthcare: Understanding the patient experience
BFSI: Reducing churn and improving satisfaction

1. Retail: Personalizing the e-commerce experience

In retail, the industry’s embrace of digital avenues and big data has led to more personalized and customizable marketing strategies that make use of, for example, real-time recommendations for customers as they online shop and chatbots that support customers in their purchase decisions.

Sentiment analysis solutions put review data front and centre to obtain consumer insights – the kind of insights that directly enable businesses to accurately craft a customized e-commerce environment for customer engagement, conversion, and sales. Are retail brands ready for this transition today? The reviews are out there waiting for businesses to make a move towards stronger, sales-driving connections with their customers. Equipped with the ability to analyze reviews through an AI solution, brands can leverage each and every customer review today.

[2022 Report: How review data is changing the retail industry]

2. Hospitality: Online reputation management

Travel technology is booming as customers flock to the web to book their travel and accommodations. Travelers also typically conduct online research about their destination before deciding on their travel arrangements. According to two surveys of more than 2,000 American adults who identified as readers of online reviews of restaurants, hotels and various services, between 73% and 87% reported that reviews had a significant influence on their purchase.

In the midst of this digital revolution, the hospitality industry is all about online reputation management. Sentiment analysis tools enable hospitality brands to quickly analyze and understand large volumes of customer views expressed across various channels such as email, discussion forums, travel-review websites, website feedback forms and surveys.

Here’s an example of how Keatext can be used to analyze customer sentiment:

Keatext turns feelings into actionable data that can help improve customer experience. It allows you to quickly see what your guests love about your offering and to figure out what updates and policy changes can be made and which aspects of your business don’t require immediate attention.

3. Healthcare: Understanding the patient experience

The healthcare industry is undergoing a major shift in current practices, and big data is top of mind for many organizations. Big data doesn’t only help save on basic expenses and improve profits, it assists in predicting and preventing epidemics, curing diseases and improving quality of life. According to Dr. Amy Abernethy, Chief Medical Officer, Chief Scientific Officer, and SVP of Oncology at Flatiron Health, “Big data in context is going to be the most important data set [for patient care] in our future.”

Thanks to advancements in technology, healthcare professionals can deepen their understanding of the patient experience. With this goal in mind, sentiment analysis can be used to analyze patient responses on satisfaction surveys. With text analytics tools like Keatext, patient comments are segmented and classified by topic, meaning and frequency, and identified as positive, negative or neutral. When analyzed, patient responses provide key insights that help hospitals identify what’s working, what’s not, and where the opportunities for improvement lie.

The level of satisfaction patients feel about the treatment they received while in the care of nurses and doctors is a very important aspect of the patient experience. A recent study led by David Costello, former Chief Analytics Officer at Press Ganey, found that only 20% of a particular hospital’s patients responded in a survey that staff reacted quickly to their pain. This data revealed the need for better pain responsiveness to improve patient satisfaction in that hospital (the name was not revealed).

4. BFSI: Reducing churn and improving satisfaction

The financial industry is still plagued by high customer churn rates. Customers have an abundance of options and they choose when they want to bank and which financial services they wish to use. Competition is fierce and companies rely heavily on CX sentiment analysis tools to track customer sentiment in real time.

For example, the customer service departments at the multinational Spanish banking group BBVA are increasingly using text analysis techniques to improve their customer experience. On average, BBVA receives more than 80,000 unstructured client comments per month. As part of their ongoing efforts to understand their clients’ needs, approximately one million comments were analyzed to identify frequent topics of discontent such as branch waiting times and the response time for questions. As a result, they were able to determine action areas with high-potential impact, and the Mexico office improved by 10 points in the customer satisfaction index.

There are many other real-life examples of how sentiment analysis tools have helped companies salvage their brand reputation and bounce back from bad business decisions. These examples illustrate the importance of tuning in to the customer conversation and, more importantly, recognizing how quickly customer comments can impact the viability of a business.

The post 4 Industry Applications of Customer Experience Analysis appeared first on Keatext.

When word clouds are not enough: Using AI text analytics to reveal insights within data

Tatiana Crisan — Fri, 03 Feb 2017 21:21:07 +0000

As data visualizations, word clouds have a place in brainstorming sessions and creating stylish infographics. Yet when strategists and decision-makers really want to get to the bottom of a business issue or understand what’s on customers’ minds, they’ll have to level up with innovative data analysis.

Word clouds vs. text analytics

A quick and easy visualization option for highlighting the frequency of key words within text-based data, word clouds can spark ideas and conversations. Looked at from the perspective of AI text analytics tools like Keatext, which just as quickly and easily analyze qualitative and verbatim data, word clouds fall far short of providing insights into that data.

In an article about exploring historical data, a word cloud based on the text of War and Peace demonstrates that though word clouds highlight key words and main topics, they lack the vital context to make sense of the narrative, the nuances of characters and what is culturally and politically at play in the book’s main themes.

Rather than providing accuracy and insight into the text-based data, the word cloud picks out the most used words and ranks them by size. For someone who hasn’t read War and Peace, the tool isn’t of much use in understanding the novel. Analyzing the novel using a text analytics tool, however, offers more meaningful and complex insight into the story, its themes and relationships.

In the process of a few different word cloud tools on a digital text of War and Peace, the three major strengths and associated weaknesses of word clouds stand out:

While word clouds are easy to create, taking as little as two minutes with a free word cloud tool and available text-based data, they are also full of blind spots, especially for a user looking for any deeper research or argument.
Because word clouds rank word value by size to create an easy-to-grasp image, they are simple to understand. However, since the visibility of words changes across the different cloud styles, especially for smaller words, the value placed on text is often inaccurate.
A word cloud typically piques interest by being a casual and visually appealing way to visualize data, but their attractiveness can’t make up for a lack of context: word clouds simply can’t decipher the relationship between words or topics.

Why brands need text analytics, not word clouds

Today, companies are faced with a truly enormous amount of data – customer data alone comes from multiple sources now, from tried-and-true NPS surveys to customer reviews on major retail sites to conversational data from chatbots and customer service interactions. What companies really need to compete in this data-rich climate are tools for data analysis, tools that provide meaningful context and actionable insights.

Uploading the entire text of War and Peace into Keatext’s AI-powered text analytics platform results in more accuracy, context and even sentiment.

While word clouds have their strengths and place in summarizing some kinds of data, they aren’t capable of drawing out further value in it. Uploading the entire text of War and Peace into Keatext’s AI-powered text analytics platform results in more accuracy, context and even sentiment. Analyzing half a million words in less than 15 minutes, Keatext processes this famed work of literature just as it would analyze thousands of product reviews from a retail website’s feedback portal, finding top topic results and much more.

For example, Keatext’s top word, “man”, barely showed up in word clouds, yet ranked much higher thanks to the AI tool’s ability to automatically bundle similar terms (such as “man” and “men”). While Keatext displayed “Prince Andrew” as one topic, the word cloud seemed to suggest that “Pierre” and “prince” go hand in hand – able to provide context to both words, Keatext showed the real relation between them.

In addition to providing context, Keatext includes a sentiment analysis feature. In its analysis of the novel, Keatext found Natasha to be quite balanced as a character, while Pierre and Andrew are slightly more negative. In essence, Keatext analyzed the text as if it were analyzing the words of real people to determine their behaviours and needs – much like it would with a brand’s own customers.

Learn more about text analytics

Read our complete guide to text analytics here.

The business use case for text analytics

Keatext’s AI data analysis is about prioritizing the valuable insights within an organization’s data. As data analysis becomes integral to tracking KPIs and meeting key objectives, the stronger the insights, the more competitive the business advantage. In our current climate, new AI platforms are the strongest tool for uncovering insights within customers’ own words.

Keatext’s advanced features offer something a word cloud truly can’t, including data collection from multiple sources, streamlined data integration, and reconfiguring the Keatext dashboard with Keatext’s development and analysis team.

Comprehensive data analysis that provides a high level of insight is able to help uncover topics and problems that might never have been recognized. From there, insights can be applied to CX strategies that span the customer journey, new marketing campaigns and assessment of previous ones, day-to-day operations and employee management. They can contribute to new directions and solutions to specific issues, from how customers want to shop to what employees need to maintain retention. After all, if a company doesn’t understand what’s going on with its customers, clients or employees, it can neither fix those problems or offer the right solutions.

While Keatext’s web-based AI text analytics platform can be easily used on its own by CX strategists, marketing teams, operations managers and other decision makers, Keatext’s advanced features offer something a word cloud truly can’t. That includes data collection from multiple sources and streamlined data integration with Zendesk, Surveymonkey, Salesforce, Intercom or any other of our 400+ integrations.

What was once the biggest strength of word clouds – data visualization – has progressed into a new realm in the hands of powerful analytics technology. Tied directly to both analyzed data and insights, Keatext’s visualization capabilities highlight topics, sentiments and any combination of factors that a company requires. With each analysis comes insights tailor-made to inspire action and decision making that can make a difference to a company’s bottom line.

The post When word clouds are not enough: Using AI text analytics to reveal insights within data appeared first on Keatext.