Many clients and partners have asked me about when the Personality Insights service will become generally available. The wait is over!

Today, we are pleased to announce the General Availability (GA) release of the IBM Watson Personality Insights service (formerly known as the IBM Watson User Modeling service in Beta). Like the other Watson services, Personality Insights is available on Bluemix, IBM’s open cloud development platform.

Here’s a brief introduction to what the Watson Personality Insights service is all about:

The Personality Insights service uses linguistic analytics to infer the personality characteristics, intrinsic needs and values of individuals from communications that a user opts to make available via mediums such as email, text messages, social media, forum/blog posts, and more. These insights help businesses better understand their clients and improve customer satisfaction by anticipating customer needs and recommending future actions. This allows businesses to improve new client acquisition, retention, and engagement, and strengthen their relationships with existing customers.

The following is a brief description of the three kinds of personality insights that are provided by this service:

  1. Personality characteristics: The service can build a portrait of an individual’s personality characteristics and how they engage with the world across five primary dimensions: Openness, Conscientiousness, Extroversion, Agreeableness, and Neuroticism (also known as Emotional Range).
  2. Needs: The service can infer certain aspects of a product that will resonate with an individual across twelve needs: Excitement, Harmony, Curiosity, Ideal, Closeness, Self-expression, Liberty, Love, Practicality, Stability, Challenge, and Structure.
  3. Values: The service can identify values that describe motivating factors which influence a person’s decision-making across five dimensions: Self-transcendence / Helping others, Conservation / Tradition, Hedonism / Taking pleasure in life, Self-enhancement / Achieving success, and Open to change / Excitement.

More details about this service are available here.  Documentation | Demo

PI service page pic


IBM Watson Personality Insights Updates since Beta

After working with clients who used the beta version of this service, we received valuable feedback that led to new enhancements, features and functional improvements that are delivered in the GA release of the Personality Insights APIs, such as:

  1. We added a textual summary of personality characteristics. Clients can use this description as-is or modify it when integrating the Personality Insights service into their business applications. The following is a  sample text summary from the sample application:
    PI text summary
  2. We enhanced the service to accept two new input formats, adding plain text and HTML inputs to JSON format that was already available in the profile API. These new types can be selected via the “Content-Type: text/plain” and “text/html” headers.
  3. We enhanced the profile API to return a new output format, adding CSV output to the profile API. This output format can be selected via the “Accept: text/CSV” header. It also adds an optional “headers” parameter to the profile API call.
  4. We provide many improvements to the ‘Needs’ model. To improve the sampling error of Needs characteristics, we updated the needs modeling by retraining with more ground truth data, and using additional dictionaries. We recommend that any results generated by the beta APIs should be recomputed. 
  5. We added a sampling error score. Language use varies naturally from document to document, and time to time. Given this variation, a small sample of text may not be representative of an individual’s overall language patterns. However, in some cases, users may only have a small amount of text from an individual and may still want to derive insights about that individual. In such cases, we understand that it’s important to know the sampling error associated with the percentile scores of characteristics that our service outputs. Therefore, we added a new output element to the profile API named Sampling Error Score. Because characteristics are reported in terms of population percentiles (which means that to say that a person scores in the 37th percentile means that he/she is higher in the score for that characteristic than 37% of the population), our API reports the sampling error in terms of percentiles. Sampling error can be reduced by analyzing more text from an individual: the more text that you provide, the lower the sampling error, and vice versa.
  6. The User Modeling Visualize API is deprecated in the Personality Insights service, in favor of the JavaScript library that is available in samples which are released with the service. The Visualize API, formerly used to graphically present results from the Profile API, will be removed entirely in a future release. 

These improvements are backwards compatible and are not expected to affect applications that are currently using the Personality Insights APIs. These improvements provide more flexibility and deliver improved analytic results.

visualizationsotu
Graphical representation of the Profile API results (see JavaScript available in samples)





Pricing and Freemium Tier

Trial Bluemix accounts remain free. If you don’t already have an account, you can go to www.bluemix.net, to register, and get free instant access to a 30-day trial without a credit card. Use of the Personality Insights service is free during this trial period. After the 30-day trial period, you can access the Personality Insights service free of charge for 100 API calls per month. If you need to make additional calls, you will be charged at a rate of 60 cents/API call. Additional Bluemix discounts may apply. Please check bluemix pricing here.


Transition Plan

We are looking forward to continuing to work with the many clients, business partners, and creative developers that built innovative applications using the beta version of the Personality Insights service. If you have done so, please migrate your applications to use the GA service in the next 30 days (by March 24, 2015), after which the beta User Modeling service will no longer be available. We’re eager to see what the next round of cognitive applications based on Personality Insights look like!





Personality Insights and our Partners

See how our partners are already using the Personality Insights service. Read more about eyeQ and how they’re improving the in-store shopping experience in the modern market.

13 comments on"IBM Watson Personality Insights General Availability Announcement"

  1. Luis A. Lastras February 23, 2015

    I have witnessed how well Personality Insights resonates with customers. I hope it does really well and that we learn during the course of this how to build compelling services.

    • Luis,

      I’d be interested in reading about real life examples where this technology has been used – any suggestions on where to find them?

      Thanks.

  2. Oh my goodness! Awesome article dude! Many thanks, However I am having troubles with your RSS.
    I don’t know why I cannot join it. Is there anyone else
    having the same RSS problems? Anyone who knows the solution will you kindly respond?
    Thanks!!

  3. Name *Stephen Hensley February 26, 2015

    The Demo mode will actually run your a report of your own personality if you clear the text box and replace Melville’s words with your own writings.

  4. Pretty! This was a really wonderful post. Thank you for providing this information.

  5. the link to demo does not work – I used https://watson-pi-demo.mybluemix.net/ and was OK

  6. Hi, and thank you for posting!

    I tried the self-assesment and am curious about the “Needs” section of your reports. Where do these needs come from? Are they part of some human needs theory or did you come up with them yourself?

    Thanks in advance for any details you might have!

    • Brenda Dietrich March 16, 2015

      Needs describe which aspects of a product will resonate with a person. Needs are an important aspect of human behavior. Research literature suggests that several types of human needs are universal and directly influence consumer behavior (Kotler, et al., 2013, and Ford, 2005). Our model includes twelve characteristic needs: Excitement, Harmony, Curiosity, Ideal, Closeness, Self-expression, Liberty, Love, Practicality, Stability, Challenge, and Structure from Ford, 2005. They are called “Universal Needs Map”. The twelve categories of needs reported by the service are described in marketing literature (Ford, 2005) as desires that a person hopes to fulfill when considering a product or service. Our model for Needs was learned from Twitter (Yang et al., 2013). You might find the following references helpful.

      References

      Ford, J. Kevin. Brands Laid Bare: Using Market Research for Evidence-Based Brand Management. John Wiley and Sons, 2005.
      Kotler, Philip, and Gary Armstrong. Principles of Marketing. Prentice Hall, 2013.
      Yang, Huahai, and Yanyuo Li. Identifying User Needs from Social Media. IBM Research Report, 2013.

  7. David Bryant August 18, 2015

    I find the concept fascinating and have experimented a little.
    I was wondering what your reaction is to the analysis of Hitler’s speeches.
    For example – from a 1939 speech

    You are inner-directed.

    You are empathetic: you feel what others feel and are compassionate towards them. You are calm-seeking: you prefer activities that are quiet, calm, and safe. And you are unconcerned with art: you are less concerned with artistic or creative activities than most people who participated in our surveys.

    Your choices are driven by a desire for efficiency.

    You are relatively unconcerned with tradition: you care more about making your own path than following what others have done. You consider helping others to guide a large part of what you do: you think it is important to take care of the people around you.

Join The Discussion

Your email address will not be published. Required fields are marked *