Slashdot Mirror
Human Language Is Biased Towards Happiness, Say Computational Linguists
KentuckyFC (1144503) writes The idea that people tend to use positive words more often the negative ones is now known as the Pollyanna hypothesis, after a 1913 novel by Eleanor Porter about a girl who tries to find something to be glad about in every situation. But although widely known, attempts to confirm the hypothesis have all been relatively small studies and so have never been thought conclusive.
Now a group of researchers at Computational Story Lab at the University of Vermont have repeated this work on a corpus of 100,000 words from 24 languages representing different cultures around the world. They first measured the frequency of words in each language and then paid native speakers to rate how they felt about each word on a scale ranging from the most negative or sad to the most positive or happy. The results reveal that all the languages show a clear bias towards positive words with Spanish topping the list, followed by Portuguese and then English. Chinese props up the rankings as the least happy. They go on to use these findings as a 'lens' through which to evaluate how the emotional polarity changes in novels in various languages and have set up a website where anybody can explore novels in this way. The finding that human language has universal positive bias could have a significant impact on the relatively new science of sentiment analysis on social media sites such as Twitter. If there is a strong bias towards positive language in the first place, and this changes from one language to another, then that is obviously an important factor to take into account.
Now a group of researchers at Computational Story Lab at the University of Vermont have repeated this work on a corpus of 100,000 words from 24 languages representing different cultures around the world. They first measured the frequency of words in each language and then paid native speakers to rate how they felt about each word on a scale ranging from the most negative or sad to the most positive or happy. The results reveal that all the languages show a clear bias towards positive words with Spanish topping the list, followed by Portuguese and then English. Chinese props up the rankings as the least happy. They go on to use these findings as a 'lens' through which to evaluate how the emotional polarity changes in novels in various languages and have set up a website where anybody can explore novels in this way. The finding that human language has universal positive bias could have a significant impact on the relatively new science of sentiment analysis on social media sites such as Twitter. If there is a strong bias towards positive language in the first place, and this changes from one language to another, then that is obviously an important factor to take into account.
Hang on a minute, that didn't end too well for that guy did it?
Science advances one funeral at a time- Max Planck
Isn't that just wounderfull. Ice cream and cake for everyone.
Context is everything.
John McAfee 'It was like that time I hired that Bangkok prostitute; to do my taxes, while I fucked my accountant'
Overuse of negative language is positively correlated with lack of reproductive success. No one sleeps with sad-sacks.
this:
http://www.theonion.com/video/...
Remember kids, if you're not paying for the service, YOU ARE THE PRODUCT THAT IS BEING SOLD.
Feed it Hemmingway, and watch the computer melt into a puddle of despair.
Lost at C:>. Found at C.
How come the hacker's jargon contains so many negative words for misbehaving hard- and software?
"... then paid native speakers to rate how they felt about each word on a scale ranging from the most negative or sad to the most positive or happy."
It couldn't have anything to do with the state of mind of said speakers being paid, right?
However a follow-up study indicates that human existance is biased towards sadness. Scientists are still trying to determine whether there is a causal relationship between the two.
Crazy, would have guessed that German would be the least tendency towards happy words. Imagine them as a very serious, dour people. (who get shit done, unlike the Spanish or Portuguese.)
Context would mean a lot here. More than just simple double negatives.
I see "good" and I flag a plus. You'd probably filter for "not good" easily enough. How about "it seemed very good at the time, but..."
Positive words are a long way from positive sentiment, and vice versa.
China, huh? Doesn't Mandarin have this thing where the word isn't conclusive without others. "Hao" is good. But you kind of need "hao hao" to be sure. "Bu hao" isn't good, but "hao bu hao" is rather open to interpretation.
Fuck computational linguists
“It is of course perfectly natural to assume that everyone else is having a far more exciting time than you. Human beings, for instance, have a phrase that describes this phenomenon, ‘The other man’s grass is always greener.’
The Shaltanac race of Broopkidren 13 had a similar phrase, but since their planet is somewhat eccentric, botanically speaking, the best they could manage was, ‘The other Shaltanac's joopleberry shrub is always a more mauvy shade of pinky-russet.’ And so the expression soon fell into disuse, and the Shaltanacs had little option but to become terribly happy and contented with their lot, much to the surprise of everyone else in the Galaxy who had not realized that the best way not to be unhappy is not to have a word for it.”
Everything is angry and depressing in the german language.
Disclaimer, I have heavy german ancestory and my Grandma was right off the boat. I know when I am being sworn at in german and loved in german, to the outsider they both sound the same.
Do not look at laser with remaining good eye.
Two questions about this research:
(1) How did the researchers account for operational language profiles? Language A may have more negative words than positive words, but maybe the one happy word is used 80% of the time. To me, the incidence of positive vs. negative usage is much more important than the histogram of the available vocabulary.
(2) How did the researchers compare the same word in different languages? Is this comparison possible without the introduction of bias in the selection of words for each of the two languages. From the paper authors' website, "This is a comparison between the average user reported happiness scores between several languages. The "happiness" of each word is rated by 50 distinct users on a scale of 1(sad) to 9 (happy). Words from each row language are then translated into each column language and intersected with each other corpora."
So, how much are the results a reflection of the experimenter's biases and skills in translation to the 2nd language. I'm suspicious of this type of comparison. From the article (not the paper), "For example, on a scale of 1 to 9 with nine being the happiest, Germans rate the word “gift” as 3.54. That’s slightly negative. By contrast, English speakers rate “gift” as strongly positive at 7.72." As a somewhat fluent German speaker, I know that the German word "gift" means poison, and I would consider it not just slightly negative but extremely negative. If the experimenters actually presented the German speakers with the German translation of the English word "gift", e.g., something like "Geschenk", then I imagine the German response would have been very positive.
the team paid native speakers to rate how they felt about each word on a scale ranging from the most negative or sad to the most positive or happy
So all the research was based on the native language speakers interpretation of how happy or sad the words were - and then their relative frequency in the texts. If the speakers of each language had a natural disposition to happiness or sadness, that would skew the whole result. And since there's no objective measure of a word's "happiness", the whole thing comes down to interpretation, rather than science.
politicians are like babies' nappies: they should both be changed regularly and for the same reasons
she can find the cloud behind every silver lining
Remember kids, if you're not paying for the service, YOU ARE THE PRODUCT THAT IS BEING SOLD.
These top two languages share a written form in which "novels in various languages" are written.
We are talking about something that is not simple and clear cut to begin with. Welcome to the the edge of science, the "soft" sciences where the boundaries of science are routinely explored and often exceeded. Hey, at least they can be serious, educated and somewhat formal in their attempts rather than just guessing the result like some cable newscaster.
Democracy Now! - uncensored, anti-establishment news
why don't you explain it then?
you don't have to type a thesis, just hit the high points, and be sure to throw in some links
Thank you Dave Raggett