What is Sentiment?
Tethr’s Sentiment model is designed to provide insight against your overall customers’ sentiment, as well as individual emotions that drive it. With Tethr Sentiment, you can identify the participants emotions expressed during the conversation resulting in an overall sentiment of positive, neutral or negative. By identifying factors that are influencing overall customer sentiment, businesses can provide tailored coaching against agent behaviors that maximize positive customer emotions, thereby improving overall customer sentiment.
Early Adopters help Tethr:
- Validate and improve model accuracy
- Understand how the data is being applied to your organization
- Shape the product experience
What you can do with Sentiment:
- Easily identify your positive and negative conversations
- Identify individual emotions that drive the overall sentiment
- Monitor and track your sentiment over time to measure improvement
- Track sentiment within different levels of your organization (i.e. line of business, team, service, product, offer)
- Analyze individual emotions and overall sentiment by different participants (i.e. agent vs customer)
How it works
The Tethr sentiment model includes an overall sentiment rating ranging from negative to positive and 30+ individual emotions that are identified within a conversation. Different participants in a conversation are rated separately to provide a more detailed representation of the emotional context.
Sentiment modeling and analysis involves taking unstructured text and identifying one or more emotions represented by the text. To accomplish this, a large collection of example phrases, labeled with the emotions they represent is used as training data since any given emotion may be expressed in a variety of ways. For example, to accurately model the emotion of “anger”, a large number of phrases must be provided, some of which represent anger and some of which do not. Mathematical relationships between words and word sequences in the phrases and the emotional label of anger, represented as a probability of 1 or 0, are then solved.
Once created, fully trained models representing different emotions can then be applied to phrases and conversation text. These models provide values for each phrase representing the likelihood of each emotion being present which are further used to calculate overall sentiment representing the overall positive or negative sentiment for a conversation.
1. After reviewing interactions ask yourself "If I were the customer, would I personally feel positive or negative about this interaction?"
Apply feedback through Tethr labels
2. During review, @commentmention User: Sentiment on emotions you disagree with in the transcript
3. During review, @commentmention User: Sentiment on utterances you believe a Sentiment emotion was not captured and include the emotion
It's important to review an equal amount of interactions from each Sentiment range, Tethr's recommendation on total # of interactions to review is 10-15 per week per reviewer.