As a follow up to my post on Cognitive Computing, I wanted to give a functional overview of how the IBM Watson integration works and discuss some of the items I have on the backlog for this project.
The personality insights service aims to calculate personality characteristics based digital communications. A personality model can be grouped on into the following
- Agreeableness: Is a persons tendency to be compassionate and cooperative towards others
- Conscientiousness: Is a persons tendency to act in an organised or thoughtful manner
- Extroversion: Is a persons tendency to seek stimulation in the company of others
- Emotional Range: Is the extent to which a persons emotions are sensitive to the individuals environment
- Openness: Is the extent to which a person is open to experiencing a variety of activities
- Needs (Curiosity, Ideal, Excitement, Self-Expression, Liberty, Love, Practicality, Stability, Challenge, Structure)
- Values (Self-transcendence / Helping others, Conservation / Tradition,Hedonism / Taking pleasure in life, Self-enhancement / Achieving success, Open to change / Excitement)
Personality Insights Service
The diagram below gives an overview of how the component works. On load of the Contact Detail page, the component checks for an existing Personality Profile (PP). If a PP exists, it is loaded otherwise a call is made to Twitter to get the tweets of the Contact and that is used as input to the IBM Personality Insights Service. The response is stored in Salesforce and displayed on the component.
The following is a list of ideas I have on how this can be extended to provide more useful insights.
- Similar Salespeople: Based on the personality profile of the contact and other sales users, we could display a list of sales users that are a close match in terms of personality
- Input from others sources: Whilst the service works with Twitter data intuitively, it does also accept plain text. This text can be sourced from Facebook, Blogs or even emails.