Voice of the Customer is no longer a metaphor. A new wave of solutions allowing companies to literally hear and measure their business phone calls is here. This article is an introduction to conversation analytics.
Speech analytics has been around for a while. Since its first commercial appearance over a decade ago, it has evolved, matured and even diversified. One of its recent branches is the conversation analytics. Rather than just deciphering the semantic layer of speech it focuses on mapping an exchange between speakers in all its wealth. One of the greatest advantages of conversation analytics is the unprecedented ability to recognise both sentiment and emotion.
Why is this important? Because emotion defines experience. In an article titled “You can’t afford to Overlook Customer’s Emotional Experience” published by Forrester, author Megan Burn writes:
“In 2014, Forrester analyzed CX Index data to see which of the three dimensions of CX quality matters most to customer loyalty – effectiveness, ease, or emotion. We found that emotion, how an experience makes the customer feel, has a bigger influence on their loyalty to a brand than either of the other two factors.”
She later adds:
“Repeating that analysis with data from the first wave of our 2015 CX Index only strengthened that conclusion. Emotion was the #1 factor in customer loyalty across 17 of the 18 industries that we studied this time around.”
Research proves that the telephone is still customers favourite medium. 2015 U.S. State of Multichannel Customer Service Report showed that 81% of customers still use phones on a regular basis to connect with brands. Although enterprises strive to measure every aspect of their performance, calls still pose a mystery in comparison with other communication mediums such as social media, email or chat that can be easily quantified. Conversation analytics is a tool designed to decipher these conversations.
What is conversation analytics?
Conversation analytics is a study of live phone calls and call recordings. It focuses on a dialogue between two or more people. It taps into a largely undiscovered area, which constitutes one of the most reliable sources of honest and direct information. The combination of language and audio processing used in conversation analytics offers an unprecedented insight into speaker’s emotion and sentiment. It introduces the human aspect into the analytical landscape.
Conversation analytics draws on the solutions hiding behind two separate methods of speech processing. It combines them to create a full picture – what is being said, what is the language used, what are the emotions behind utterances. The analytic process can be broken up into two stages:
Acoustic Engine processing:
This phase starts by interpreting the sounds of speech. It takes into an account the environment of the speaker, the telephony used to connect, the language spoken, accent and tonality. Ideally in this stage there are about 4000 markers used to establish the properties of the individual words, including the human element – the emotions of the speaker.
Language processing gives a structure and meaning to the acoustic interaction. It uses episode based language models that account for the vernacular used in a particular industry, location and situation, to create the most natural and precise maps of conversations. The higher the tuning, the better the accuracy.
The key to successful conversational analytics program lies in choosing the vendor who is able to enrich the vocal stream and tune language, in order to offer the most relevant models.
Applications for conversation analytics
Conversation analytics has a range of applications. These types of solutions are scalable and tunable, meaning that analytics can be either applied to mine general data or resolve any particular queries. Furthermore, it can highlight recurring topics or focus on chosen areas of conversations.
Enhance Customer Experience
In a very literal sense, conversation analytics taps into a Voice of Customer. Data drawn from conversations is a direct account of client’s needs, expectations and feelings, and a use-ready roadmap to improving customer experience.
Conversation analytics quickly pinpoints the shortcomings of the script by spotting long pauses or negative emotions evoked by certain phrases or concepts.
By analysing every call enterprise gains access to very visible patterns. It highlights the elements that agents struggle with or find hard to adhere to. It also enables the creation of personalized training tracks.
The root cause, keywords and topics can be cross-referenced with other metrics to extract insights that engage customers the most.
Compliance and security
Conversation analytics enables monitoring of every conversation in real time, if required. This offers a unique opportunity to red flag certain phrases and prevent data leaks.
Example: A health insurance company was attempting to reduce attrition of the customers. Clients were offered a chance to cut down insurance costs by reducing coverage on services they did not use. A conversation analytics report discovered that their reaction to words ‘reduce’ and ‘savings’ was negative, while ‘hospital’ or ‘coverage’ had positive indicators. The company decided to change its script and instead of pushing downgrades started offering paid upgrades in the areas that evoked most positive emotions. As a result, attrition was reduced, and additional revenue source was created.
Conversation analytics is a technical answer to the Voice of Customer movement and a need to go beyond dry statistics. Its allure lies in its ability to recognise sentiment emotion and the immediate benefits of applications for these insights. Its growing popularity is destined to increase with the advance of voice processing technologies.