Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Analyze Your HN Posts with Watson User Modeling

hn.mybluemix.net

Post reply on HN
Print view View original

31–40 of 56 posts

Re: Analyze Your HN Posts with Watson User Modeling

#31

Post by jonnathanson »

minimaxir wrote: post #2

Is there any insight as to how this works? I got an Openness rating of 97% and a Harmony rating of 100%, both of which I know are not true. (I also received a Love rating of 1% under my Needs, although that's pretty accurate.)

I, too, got a "Love" rating in the low single digits. That's probably not too far from the truth in a global sense, but remember that in this case, the API is working with a local context (HN comments). I'm probably unlikely to have discussed the subject of love on HN, or anything tangentially related to it, or anything that would somehow give an indication of my need for love. Now, if you were to run my Facebook history through the same process, I imagine you'd find a slightly different analysis.

To some extent, our personalities are our personalities. We behave, on some level, the same in every context and in every community. But the extent to which that's the case is up for debate. We probably use different approaches, or if you prefer, we show different aspects of our personalities, in different contexts and in front of different groups. That's why it's extremely difficult to take one context (HN, for instance), and extrapolate universal characteristics from it.

Even within the set of HN history, I got some oddball results. For instance, Watson considers me very "Fiery" (51%) here. There are plenty of areas in my life in which the word "Fiery" makes a bit of sense. HN isn't one of them.

Re: Analyze Your HN Posts with Watson User Modeling

#32

Post by tim333 »

aselzer wrote: post #20

Did this with Twitter: twurl "/1.1/statuses/user_timeline.json?count=200" | jq -r ".[] | .text" | pbcopy paste it into http://watson-um-demo.mybluemix.net/demo 87% Openness, 5% Agreeableness, that's funny.

I got 92% Openness, 10% Agreeableness on tim333, HN

Maybe they all come out a bit like that?

Re: Analyze Your HN Posts with Watson User Modeling

#33

Post by thegeomaster »

Does Watson internally use observations drawn from this study[1]?

And another question---is this applicable to non-native English speakers? Do they acquire the same language habits as if English was their mother tongue?

[1]: http://www.ncbi.nlm.nih.gov/pmc/articles/PMC3783449/

Re: Analyze Your HN Posts with Watson User Modeling

#34

Post by Kronopath »

It's worth keeping in mind that with things like these you get what you put in.

When the service first came up on the front page, I punched in some personal writings from my journal into it. Comparing my results from that to this HN assessment is like night and day. The HN assessment shows me as highly intellectual, imaginative, and adventurous, with a strong value for self-enhancement. The personal stuff showed me as being much more emotional, with a huge emotional range, because—surprise, surprise—I tend to write more about emotional parts of my life in my journal than on HN comments.

While this service might be useful to get a broad sense of people for marketing purposes, using it on an individual basis is like talking to a fortune teller—it could tell you nearly anything about yourself, and you'd be able to come up with an explanation to justify it.

Re: Analyze Your HN Posts with Watson User Modeling

#38

Post by eksith »

Kronopath wrote: post #34

It's worth keeping in mind that with things like these you get what you put in. When the service first came up on the front page, I punched in some personal writings from my journal into it. Comparing my results from that to this HN assessment is like night and day. The HN assessment shows me as highly intellectual, imaginative, and adventurous, with a strong value for self-enhancement. The personal stuff showed me a…

Exactly. We adopt a different tone based on the venue and, since no one shows the same face everywhere, even with the same name, these are going to be wildly different.

Ironically, this really did feel like a machine based cold-reading.

Post reply on HN