Warwick Analytics has been featured on Connections Magazine, the magazine for the call center industry . The article THREE PIECES OF KEY INFORMATION YOUR CALL CENTER IS MISSING WITHOUT MACHINE LEARNING will also appear in the March/April issue.
With the amplification of social media, as well as the ease and increase in the ability for customers to complain, issues can quickly turn into operational and PR crises. Yet this is just the beginning; issues happen every day that cause customers to interact with contact centers. The intended customer experience can be impacted by taking up unallocated resources to deal with day-to-day issues.
The article looks at three ways machine learning for text analytics can be applied within a contact center to unlock key data that can ensure the intended customer experience is achieved.
Warwick Analytics has been published in the latest volume of the peer reviewed journal Applied Marketing Analytics.
The paper ‘The Coming Democratisation of Emotions Analytics’ looks at the growing volume, diversity and complexity of customer feedback data and the increasing limitations with sentiment analysis. As a result, analysts are looking for the next steps in the capabilities of text analysis. We discuss these advancements later in this paper but first we look at the current limitations and opportunities that have acted as the drivers for a more emotional approach to AI text analytics.
Whilst sentiment analysis has served text
analytics well for a long time, the challenges and opportunities being
presented are becoming more significant. Machine learning has promised much in
the way of assisting text analytics to uncover more hidden customer data but
the skill required and complexity has thus far proved a barrier to the models
which can unlock true sentiment.
Now there are
techniques and methodologies appearing which can democratise data science, more
specifically voice of customer data, to enable business analysts rather than
data scientists to turn customer sentiment not just into charts but into
actions, satisfaction and profit. $3.1 trillion
is IBM’s estimate4 of the yearly cost of poor quality
data, in the US alone, in 2016. The Harvard Business Review5 also highlights
the following statistics:
50% — the amount of time that knowledge
workers waste6 in hidden data factories, hunting for data,
finding and correcting errors, and searching for confirmatory sources for data
they don’t trust.
60% — the estimated fraction of time that data
scientists spend cleaning and organizing data, according to CrowdFlower7.
Reducing these costs requires a new way of thinking. The latest in AI Emotions Analytics looks much deeper at the origins and overall content of the data and solves many more root causes of issues. The benefits of improving data quality with this latest technology go far beyond reduced costs though. Improving data quality is a gift that keeps giving — employing the right analytics and the right level of automation vs human in the loop will become a self-fulfilling cycle producing more efficiencies every day, enabling firms to more easily pursue other data strategies.
CEO of Warwick Analytics Dan Somers is featured on Compare the Cloud talking about how using concepts instead of keywords with the latest in machine learning and AI can transform your text analytics.
When different people are voicing different issues, they will use different words and sentiments. Current analytics typically identifies just the keywords used, but this runs the danger of failing to miss the entire context behind the communication. Often a customer will merely imply a sentiment or intention instead of explicitly expressing it with specific keywords e.g. a customer in a restaurant might say ‘by the time my meal arrived, the food was cold’, the keyword would be flagged as ‘cold food’, when in fact the main issue was the slow service. There are also other limitations with using just keywords such as sarcasm, context, comparatives and local dialect/slang. The overarching message can often be missed and so the alternative is to analyse text data using ‘concepts’ instead of ‘keywords’.