V-Blaze and V-Cloud Online Help

Emotion and Sentiment Analysis

Voci's speech scientists have applied machine learning techniques to the analysis of emotion and sentiment. Emotion information is extracted from the acoustic features of speech, while Sentiment is determined by analyzing the text generated from speech.

Sentiment analysis of text evaluates a customer conversation and key words such as “great,” “cancel” or “dislike” to understand the caller’s sentiment. Emotional analysis is focused on acoustic speech characteristics, such as inflections or speed, to determine the caller’s emotion.

Computer models, trained using thousands of audio and text samples, are used to determine the emotion or sentiment of each utterance. Additional data indicate the words in the speech utterance that contribute to the computed sentiment. The separate emotion and sentiment values are then combined into a single Emotional Intelligence value that reveals the true voice of customers, so you can get to the heart of their concerns.

Since emotion and sentiment information is captured at the utterance level, Voci can determine how emotion is changing throughout the conversation, and whether the caller is in a more positive state at the end of the call than the beginning.

What is the difference between emotion and sentiment?

Sentiment and emotion are often used interchangeably, but are quite different. Emotion is a complex psychological state such as fear, anger, or happiness. Sentiment is a mental attitude produced by feelings. Emotions are raw, while sentiments are organized. Sentiment is expressing thoughts and feelings about a particular thing, thus it possesses social aspects that emotion lacks.

V‑Blaze JSON output files display the following information about emotion and sentiment:

Emotion is presented at the utterance level and consists of both acoustic (such as pitch, speed, tone, volume) and linguistic information. Emotion can be one of the following values: Positive, Mostly Positive, Neutral, Mostly Negative, Negative. Acoustic, or raw, emotion can be one of the following values: Angry, Neutral, Happy.

Sentiment is also provided at the utterance level, but only consists of linguistic information or words and phrases such as "happy", "upset", "frustrated", "cancel", "hate", "angry", and "thank you." Sentiment can be one of the following values: Positive, Mostly Positive, Neutral, Mostly Negative, Negative, Mixed (contains both Positive and Negative in the file).