-->

Discovering sentiment and emotion analysis at KMWorld Connect 2020

At KMWorld Connect 2020, Seth Grimes, principal consultant, Alta Plana Corp., considered the use of new tools for evaluating sentiment, emotion and intent.

In recent years, sentiment, emotion, and intent analysis have been used for consumer, healthcare, and diverse other fields implemented via conversational interfaces, data science tools, and customer intelligence and market research applications.

KMWorld Connect, November 16-19, and its co-located events, covers future-focused strategies, technologies, and tools to help organizations transform for positive outcomes.

Unlike fielded transactional and operational data, text—social, online, and spoken—captures facts and feelings, conveying sentiment, opinion, intent, and emotion. Sentiment analysis and emotion AI technologies apply machine learning to extract hard data entities, aspects, events, relationship, and subjective evaluations from text sources.

Grimes presented use cases for sentiment analysis, such as suicide prevention, customer retention, and up-sell opportunities.

When we communicate, it is not just facts we are conveying, it is also feelings that we are expressing. Emotion and emotional states can be revealed by many different sources such as heart rate, facial expressions, voice tone, platforms used for communication (Twitter versus Facebook versus newspaper), and an understanding of who the person is (actor versus politician).

The more sources of data for analysis, the richer and more accurate the analysis will be, said Grimes. The goal is to understand and rationalize emotion in order to use it for business advantage.

Grimes cited a 1997 quote from Rosalind W. Picard of the MIT Media Lab about affective computing. According to Picard, "If we want computers to be genuinely intelligent, to adapt to us and to interact naturally with us, then they will need the ability to recognize and express emotions and to have what has come to be called 'emotional intelligence.'"

There are three key components of emotion AI, Grimes said:

Emotion mining is the science of detecting, analyzing, and evaluating humans' feelings toward different events, issues, services or any other interest,

Emotion synthesis enhances the ability of a machine to provide meaningful contextual responses, by conveying an appropriate emotional state through words, voice, and expression

Emotion induction aims to evolve a certain emotional response or affective state.

Grimes went on to showcase the Plutchik Wheel of Emotions that provides a model using colors visualizations for emotions such as disgust, envy, pride, and others, and highlighted a number of vendors providing a variety of analyses.

Vendors include:

  • Lexalytics, which provides sentiment analysis,
  • Clarabridge, which provide customer experience analysis,
  • Qualtrics which provides sentiment and emotion visual analysis, Adoreboard, a startup in the U.K. that provides emotional evaluation, and
  • Symanto, a German company that provides psychology AI to understand intent.

If you are doing text analytics and you are not doing emotion and sentiment analysis, you should be—and you should also be branching out into other areas to enhance your analysis, said Grimes

Replays of KMWorld Connect webinars will be made available for on-demand viewing.

KMWorld Covers
Free
for qualified subscribers
Subscribe Now Current Issue Past Issues