We received an email from Dan Zarrella, regarding the launch of his new site called TweetPsych (beta). You can read Dan’s blog post about the launch, or check out TweetPsych yourself.
From the site:
“TweetPsych uses two linguistic analysis algorithms (RID and LIWC) to build a psychological profile of a person based on the content of their tweets. The service analyzes your last 1000 tweets and works best on users who have posted more than 1000 updates. It also works best on accounts that are operated by a single user and use Twitter in a conversational manner, rather than simply a content distribution platform.”
This does sound very interesting, and you can see Darren’s results below:
Cognitive Content
- Occupation & work
- Senses
- Present tense
- Time
- Upward motion
- Media, entertainment & celebrities
- Social processes
- Past tense
- Insight
- Cognitive processes
- Future tense
- Tentative
Primordial, Conceptual and Emotional Content
- Constructive behaviors
- Social behavior
- Abstract thought
- Order
And for giggles, here are my results:
Cognitive Content
- Present tense
- Social processes
- Tentative
- Past tense
- Self reference
- Upward motion
- Cognitive processes
- Positive Feelings
- Certainty
- Negative emotions
- Time
Primordial, Conceptual and Emotional Content
- Social behavior
- Abstract thought
- Temporal References
- Affection
- Glory
- Anxiety
- Order
- Audio sensations
- Moral imperative
Looks like Darren’s pretty much all on the same alignment with his tweets, and I’m kind of all over the place! What do you think about your TweetPsych analysis?

@billbolmeier
Interesting. I’ll check it out in more detail but at the moment I can’t help but think Dan should create a site called “Twitter CSI”. You fill in the tagline.
@Jesus_de_Christ
So this is who you say I am
JC
@MeredithGould@twitter.com
My favorite part? Reading this disclaimer: “The results presented here are for entertainment purposes only and the terms used are psychological and may not equate with their normal, english language usage.” Wish I’d seen this before posting about the misuse and abuse of sociological terms by healthcare communicators.
@stacyharp
I thought my results were pretty funny, especially since I’m a trained therapist and it said I have basically no insight! LOL
@docjohng
Yes, there are tons of problems with this tool and I wonder why Zarrella spent so much time and effort promoting it, and very little effort on understanding the results he was producing. See the full critique and analysis here:
http://psychcentral.com/blog/archives/2009/06/18/putting-cool-ahead-of-science-tweetpsych/