11–20 of 29 posts
Can it work farther back in time? interesting if there are longer term trends. Happiness particularly can be indicative about the overall satisfaction from HN.
[1] http://blog.effectcheck.com/2011/05/31/do-social-news-sites-...
interesting idea. Doc here. I would organize them as 1. Depresssion 2. Anxiety 3. Hostility 4. Happiness 5. Confidence 6. Compassion Anxiety and Depression definitely go together, in the same way that hostility and happiness are actually similar in terms type of emotion, in terms of level of intellect, and confidence and compassion would be at the highest end of that spectrum. I would also change the colors to group…
My co-founders [1][2] actually did spend a decent amount of time thinking about this. The emotions are first sorted into negative on the left and positive on the right. The order is for symmetry of left/right side words:
- Anxiety is the opposite of Confidence
- Hostility is the opposite of Compassion
- Depression is the opposite of Happiness
As for the colors, each one is correlated to the typical psychological association for that color. The exception is Happiness which should be yellow but yellow doesn't render well on websites.
[1] Yanon Volcani (Clinical Psychologist): http://www.volcani.com
[2] David Fogel (AI Expert): http://www.natural-selection.com/people_dfogel.html
Too bad the EffectCheck API is not open for all. Looks like a well-parameterized sentiment analysis tool. What does this page tell us: http://effectcheck.com/pricing It can be used for a stock analysis and dampening or amplification caused from other firehose like sources like Twitter.
We are focused on B2B applications of our technology rather than the consumer/API side. However, if you have a cool idea for how you'd like to use EffectCheck, email me [1] and I'll be happy to discuss it with you.
[1] wesley.tansey@effectcheck.com
http://rawkes.com/blog/2011/04/19/finding-patterns-in-twitte...
It'd be nice to also see typical comments both with high and low scores in each category.
Do you expose the underlying data? For example, what are the most hostile articles about Microsoft?
So cool! This is what I had started working on for the HNSearch API Contest, but I hadn't gotten far. I'm SO glad someone did this. I feel as though this could be made into a useful and viable product, if marketed correctly and accurate enough.
Wow, how did this get discovered? I'm a co-founder at EffectCheck and I was working closely with Scott this weekend as he was building this. It wasn't really ready for viewing yet, but okay... :) Please note that the top graph is currently a mixture of two sets of data. The older points were using a less sensitive and improperly calibrated HN comment model, hence why everything is drifting around near "Typical." The…
It was neat when it came out years ago... Although still not sure how to make any meaningful use of this tool. I suppose it is more useful for content generators..