I'm ranked first in:

  Cheerfulness   (Before or after morning coffee?)
  Orderliness    (Because of my 3rd normal form sock drawer?)
  Gregariousness (Before of after my 3rd beer?)
  Agreeableness  (I disagree! Watson needs debugging.)

  Imagination (No one I know could imagine how this could be.)
  Authority-challenging (My teachers & bosses would disagree.)
  Intellect (Before or after my mother dropped me on my head?)

Bad Medicine

http://www.gutenberg.org/files/9055/9055-h/9055-h.htm

In other words, you are ranked 148th out of like 100k really smart people.

So, maybe quitcherbitchin? :-)

Its not a top by category ranking of all HN posters, there's a merged list of top commenters and leaders, and then the ranking is from that. Being on the bottom of that (as I am for agreeability) doesn't mean you are still ahead of everyone on HN that didn't make the list.

I think the main gist of my point stands though: Ranking dead last on this list hardly equates to "dropped on your head." That's like saying "I only won one of the less important Nobel Prizes. God, I'm such a loser." Or something.

I like edw. I like a lot of people here. But sometimes folks here really suffer from tunnel vision in a bad way.

Cheers.

Watson didn't even remotely consider me. What do I have to do to get its attention?!

I know the data isn't perfect, but it would be nice to be able see who in a thread is a top HNer and which character traits are outliers from the norm. You get insulted by somebody ranked low in Sympathy? No need to worry.

I'm serious. Somebody do this. It would look great on the résumé.

I'm generally pretty suspicious of any sort of computer-generated personality profiles, and though I understand the appeal to techies of empathy-as-a-service I don't think it's something we should consider relying upon.

Hell, half the fun in life is trying to figure out who other people really are.

Imagine how it would affect people commenting if they saw that what they are supposed to post is aggressive, or passive-aggressive ;)

Because you totally need to worry if someone insults you on the Internet.

The ext basically matches my original vision now, so I'm thinking hard about what features to add next, but I'm not quite sure I understand what you're asking for. Are you saying that when the extension says "So and so replied to you", you want, say, a sympathy score shown with that user as well?

For instance: edw519 33 minutes ago | link Top: Cheerfulness, Orderliness, Gregariousness, Agreeableness Bottom: Imagination, Authority-challenging, Intellect

(I'd also something that shows me when a commenter is somebody important, even if not a karma king.)

This could even be true for the follow-feed mechanism. If you're following someone on Twitter or friends with them on Facebook and they write something that appears in your feed, you are already familiar with the author on some level. In the Hackbook extension, it's fairly common to follow people and not know much about them at all. Again, including some basic Watson-generated information along with the "a user you're following wrote a comment" newsfeed item could be helpful.

Let me give it some more thought and maybe I'll have time to work on it this week.

We humans each build models kind of like these when we interact with one another, so when I ask somebody, "do you think <name> is an agreeable person?" and they reply "sure I think he is!" they're consulting that model to provide me an answer. Humans can even do a kind of pairwise sorting on that model and tell you if person1 is more or less agreeable than person2.

However, even if our individual models may differ a bit, and the results of these kinds of questions to each other might differ a bit, there's an inherent "humanness" to the results because people generally have a pretty similar semantic understanding of what "agreeableness" means.

However, what does Watson think agreeableness means? I have no idea, nobody really knows. Watson can't really explain it. All we know is that there's a model that produces a scored (and thus rankable output) when asked to score a corpus on that model and somebody somewhere labelled that model as the "agreeableness" model, perhaps based on some heuristics or parameters that were intended to define that notion.

It's thus very hard for humans to trust scoring like this because when it doesn't make sense, it doesn't make sense for reasons that no human would have about the matter. For example, I would personally say pg is far more agreeable than I am, yet Watson scores our respective collection of comments exactly the same. I can't explain it, Watson can't explain it, and thus it feels "wrong" and now I can't trust the scores that Watson provides me.

There's also a lack of documentation from IBM as to what the results mean exactly and how solid they are.

So for all purposes that you, I or Watson can demonstrate, "do you think X is Y" and "do you think X's comments show Y" are functionally the same.

edit

I just checked what Watson thinks are my needs. Apparently I don't have many, and everybody on HN has an extreme need for Challenge.

I almost feel like these results require a lot of interpretation, and that interpretation is about as reliable as a horoscope.

I got a similar feeling from this - that's why I'd love to see some hard data behind the algorithm, or at least bits and pieces about the methodology used to arrive upon it.

2144 days into this experiement that is HN, I couldn't ask for a better analysis of myself than through empiricism. My online self may not be my "true self" but it certainly represents a portion of who I want to be.

Now to contextualize, I wonder how we trend together and apart from the median user model as individuals and the community? The distributions seem interesting -- for example at a glance we appear heavy on challenge seekers but light on stability!

Rayiner's doesn't make sense, though. An average of 0.75? So he has 57275 comments? Wow.

https://news.ycombinator.com/user?id=kolinko

Also, why is Libertatea (https://news.ycombinator.com/threads?id=Libertatea) ranking so high in many categories and yet he only has 5 posts?

Without a definition for what each of these things are, it's a little unclear what this is actually saying. I'm assuming there's some documentation on this somewhere?

http://en.wikipedia.org/wiki/Big_Five_personality_traits

One thing that we're wondering is whether a score 1% means that it believes that the person has little of this treat, or that it has little proof to believe that the person has this treat. If I'm not mistaken it's the former.

[0] http://similarminds.com/global5/g5-jung.html

For "challenges authority" all visible commenters were above .95.

It fits the medium. Just like one would expect HN comments to be full of more "head-y" discussions.

http://www.economist.com/blogs/economist-explains/2013/05/ec...

I'd assume that this might be the same algorithm, but I'm not really sure of that.

In case you're wondering, IBM's BlueMix is a public installation of Cloud Foundry, which is an opensource PaaS. Disclaimer: I work on Cloud Foundry at Pivotal.

One thing I know for sure is that Watson doesn't recognise irony - I posted this poem and it was marked as "cheerful" and "optimistic": http://bukowski.net/poems/a_smile_to_remember.php

You can run MBTI albeit as 4 separate API calls.

Not sure about the results, I'm pretty sur I value liberty more than Watson thinks I do.

Sorry for the confusion.

31. [0.95] whoishiring (threads) (about)

Is this a Human? Must be well rounded !

Most agreeable: https://news.ycombinator.com/threads?id=StavrosK Least agreeable: https://news.ycombinator.com/threads?id=dragonwriter

Selfishly, it would also be pretty cool to be able to select a person and see their rankings across the categories :-)

Oh, and your "top 100 users" link on the front page is broken as it's not an absolute link.

- rankings across all the categories. good idea - shouldn't be hard to do, but don't have the time to implement it today :)

- as for what the headings mean, from what I understand they are related to http://en.wikipedia.org/wiki/Big_Five_personality_traits - but yes, the IBM watson docs are very vague on this subject

Otherwise cool!

User Modeling analytics are developed based on the psychology of language in combination with data analytics algorithms. User Modeling extracts three types of personal characteristics from the data a person generates in social media or within their written/digital communications: Big 5 Personality - This is the most used personality model that generally describes how a person engages with the world by the following five dimensions: – Openness-to-Experience - associated with curiosity, intellect, and an appreciation for art and adventure – Conscientiousness - associated with organization and industriousness – Extraversion - associated with positive and outgoing attitudes toward other people – Agreeableness - associated with compassion and cooperation toward other people – Neuroticism - associated with a sensitivity to negative emotions Each of the five top-level dimensions has six sub-facets that further characterize an individual at a finer-grained level. Basic Human Values - this model describes motivating factors that influence a person's decision-making. Our current model includes five dimensions of human values based on Schwartz's work in psychology: – Self-Transcendence - motivated by helping others – Self-Enhancement - motivated by increasing social status – Hedonism - motivated by pleasurable experiences – Openness-to-Change - motivated by experiencing new things in the world – Conservation - motivated by tradition and conformity Fundamental Human Needs - this model is based on Maslow's hierarchy of needs and Ford's work on Marketing and consumer-related needs modeling. It describes, at a high level, which aspects of a product will resonate most with a person. – Ideal - the person likes high-end, finely crafted products – Self-Expression - the person likes products that express their individual identity – Closeness - the person likes products that help them establish closer relationships with family and friends – Excitement - the person likes products that provide exciting, adventurous experience – Practicality - the person likes products that simply get the job done

For more detailed information about the research and technical background behind the User Modeling service, see the following: You read what you value: understanding personal values and reading interests Gary Hsieh, Jilin Chen, Jalal Mahmud, Jeffrey Nichols; CHI 2014. 983-986. Understanding individuals' personal values from social media word use Jilin Chen, Gary Hsieh, Jalal Mahmud, Jeffrey Nichols; CSCW 2014. 405-414 Recommending targeted strangers from whom to solicit information on social media Jalal Mahmud, Michelle X. Zhou, Nimrod Megiddo, Jeffrey Nichols, Clemens Drews; IUI 2013: 37-48 Modeling User Attitude toward Controversial Topics in Online Social Media Huiji Gao, Jalal Mahmud, Jilin Chen, Jeffrey Nichols, Michelle Zhou; ICWSM 2014. Who will retweet this?: Automatically Identifying and Engaging Strangers on Twitter to Spread Information Kyumin Lee, Jalal Mahmud, Jilin Chen, Michelle Zhou, Jeffrey Nichols; IUI 2014. 247-256 KnowMe and ShareMe: understanding automatically discovered personality traits from social media and user sharing preferences Liang Gou, Michelle Zhou, Huahai Yang; CHI 2014. Identifying User Needs from Social Media Huahai Yang, Yanyuo Li; IBM Research Report. PersonalityViz: a visualization tool to analyze people's personality with social media Liang Gou, Jalal Mahmud, Eben M. Haber, Michelle X. Zhou; IUI Companion 2013: 45-46