How are you gauging the quality of your customer experience? How are you deciding whether your customer is really satisfied or not at the end of each call?
- Is it part of your agents ACW? In that case, how objective is your agent in marking your customer mood?
- Or are you are using a survey system? Sadly, we know that surveys are not always answered. Besides, every customer judges on a personal scale. One customer’s 4 star rating can mean they’re not completely satisfied, whereas that may be the highest rating another customer gives. The scale just isn’t standardized.
- Or are you still using metrics such as first call resolution to judge satisfaction quality? Do these metrics give you a complete picture? For example, lets consider a customer who calls, speaks to your agent for 5 minutes, hangs up and doesn’t call again. Was that really a call resolution or have you just lost a customer?
- And, we all understand that even the best QA team can only go through a small sample set of call recordings. We don’t know how many unhappy (or happy) customers hide within the call recordings we missed.
What you really need is an objective and intelligent analysis of customer sentiment at the end of every single call. That’s where sentiment analysis comes in.
Sentiment Analysis is a function of your Speech Analytics system. Your Speech Analytics system first transcribes every word your customer speaks to text. Then it analyses the text using National Language Processing to to understand what they said, and what they meant. Based on the words used, and the context, Sentiment Analysis is able to gauge whether the customer mood was: a. Positive b. Neutral or c. Negative.
And here is why it helps:
- Fastest Feedback Loop. A great plus point is that results are instant. Your agent gets immediate feedback. Studies show that immediate feedback is the most powerful way of improving performance.
- 100% analysis. 100% of your calls are analyzed. You don’t miss out a single negative (or positive) remark. This makes judgment of agent performance 95% more accurate than before.*
- Deep Dive. The results can be further scanned with various keywords to find common causes and trends. For example, are the negative results all pointing to a product/service flaw? Are there common complaints that can be used to improve your product offering? Are there some triggers in your script that cause change in customer sentiment?
- Find your star players. Sentiment can also be scanned at the beginning and end of the call. Are there some star agents that can turnaround customer sentiment from negative to positive? You can automate call routing of certain customers to your star agents.
- Take immediate action. You can develop APIs that allow barge-ins, call redirects, whenever sentiment drops to negative.
- Go beyond first call resolutions. Lets go back to the customer who calls, speaks to your agent for 5 minutes, hangs up, and doesn’t call again. Was this a call resolution, or have you just lost a customer? Simple, if the customer mood was happy, you it’s a resolution. And if not, well, you need to work a little harder.
Customer experience is often referred to as a journey. Developing “Intelligent” contact center solutions will soon help pave a smooth path. With Speech Analytics, the journey has just begun.
* based on survey results that state most call centers use only 5% of their call recordings for detailed QA.