{"id":22800,"date":"2020-11-15T21:10:38","date_gmt":"2020-11-15T21:10:38","guid":{"rendered":"https:\/\/www.lifeandnews.com\/articles\/?p=22800"},"modified":"2020-11-16T04:35:54","modified_gmt":"2020-11-16T04:35:54","slug":"fox-news-viewers-write-about-blm-the-same-way-cnn-viewers-write-about-kkk","status":"publish","type":"post","link":"https:\/\/www.lifeandnews.com\/articles\/fox-news-viewers-write-about-blm-the-same-way-cnn-viewers-write-about-kkk\/","title":{"rendered":"Fox News viewers write about ‘BLM’ the same way CNN viewers write about ‘KKK’"},"content":{"rendered":"

Mark Kamlet<\/a>, Carnegie Mellon University<\/a><\/em>; Ashique KhudaBukhsh<\/a>, Carnegie Mellon University<\/a><\/em>, and Tom Mitchell<\/a>, Carnegie Mellon University<\/a><\/em><\/p>\n

It\u2019s no secret that U.S. politics has become highly polarized<\/a>.<\/p>\n

Even so, there are probably few living Americans who ever witnessed anything that quite compares with this fall\u2019s first presidential debate<\/a>.<\/p>\n

Was it really the case that the nation could do no better than a verbal food fight, with two candidates hurling fourth-grade insults and talking past each other?<\/p>\n

To us, the discordant debate was just one more symptom of the nation\u2019s fraying civic discourse, which, in a recent study, we were able to show extends to the words we use to talk about politics.<\/p>\n

Earlier this year, we started constructing a data set that consists of all of the viewer comments on YouTube videos posted by four television networks \u2013 MSNBC, CNN, Fox News and One America News Network<\/a> \u2013 that target slices of the political spectrum<\/a>. Together, the data set contains over 85 million comments on over 200,000 videos from 6.5 million viewers since 2014.<\/p>\n

We studied whether there are distinct variants of English written in the comments sections, akin to the distinction between British English<\/a> and American English<\/a>.<\/p>\n

Using machine learning methods, we found these permutations do exist. Moreover, we can rank them in terms of the \u201cleft-ness\u201d and the \u201cright-ness.\u201d To the best of our knowledge, this is the first empirical demonstration of quantifiable linguistic differences in news audiences.<\/p>\n

Our second finding, however, was even more unexpected.<\/p>\n

Our machine learning translation system found that words with vastly different meanings, like \u201cKKK\u201d and \u201cBLM,\u201d were used in the exact same contexts depending on the YouTube channel being analyzed.<\/p>\n

The company a word keeps<\/h2>\n

When translating two different languages \u2013 say, Spanish and English \u2013 automated translation systems like Google Translate begin with a large training set of texts in both languages. The system then applies machine learning methods to become better at translating.<\/p>\n

Over the years, this technology has become increasingly accurate<\/a>, thanks to two key insights.<\/p>\n

The first dates back to the 1950s, when linguist John Rupert Firth<\/a> came up with the aphorism \u201cYou shall know a word by the company it keeps.\u201d<\/p>\n

To modern machine translation systems, the \u201ccompany\u201d a word keeps is its \u201ccontext,\u201d or the words surrounding it. For example, the English word \u201cgrape\u201d occurs in contexts such as \u201cgrape juice\u201d and \u201cgrape vine,\u201d while the equivalent word in Spanish, uva<\/em>, occurs in the same contexts \u2013 jugo de uva<\/em>, vid de uva<\/em> \u2013 in Spanish sentences.<\/p>\n

The second important discovery came rather recently. A 2013 study<\/a> found a way to identify \u2013 and thereby link \u2013 a word\u2019s context in one language to its context in another. Modern machine translation depends heavily on this process.<\/p>\n

What we have done is to use this type of translation in an entirely new way<\/a>: to translate English to English.<\/p>\n

When \u2018Trumptards\u2019 become \u2018snowflakes\u2019<\/h2>\n

That may sound bizarre. Why translate English to English?<\/p>\n

Well, consider American English and British English. Many words are the same in both languages. Yet there can be subtle differences. For instance, \u201capartment\u201d in American English may translate into \u201cflat\u201d in British English.<\/p>\n

For the purposes of our study, we labeled the language used in each network\u2019s comment section \u201cMSNBC-English,\u201d \u201cCNN-English,\u201d \u201cFox-English\u201d and \u201cOneAmerica-English.\u201d After analyzing the comments, our translation algorithms uncovered two different patterns of \u201cmisaligned words\u201d \u2013 terms that aren\u2019t identical across the comment sections but are used in the same contexts.<\/p>\n

One type was similar to \u201cflat\u201d and \u201capartment,\u201d in the sense that both are describing ostensibly the same thing. However, the word pairs we uncovered have different intonations. For example, we found that what one community calls \u201cPelosi,\u201d the other one calls \u201cPelousy\u201d; and \u201cTrump\u201d in one news-language translates into \u201cDrumpf\u201d in another.<\/p>\n

A second \u2013 and deeper \u2013 kind of misalignment occurred when the two words refer to two fundamentally different things.<\/p>\n

For example, we found that in CNN-English, \u201cKKK\u201d \u2013 the abbreviation for the Ku Klux Klan \u2013 is translated by our algorithm to \u201cBLM\u201d \u2013 shorthand for Black Lives Matter \u2013 in Fox-English. The algorithm is basically finding that the comments made by one community about KKK are very much like the comments made by the other about BLM. While the belief systems of the KKK and BLM are about as different as can be, depending on the comment section, they seem to each represent something similarly ominous and threatening.<\/p>\n

CNN-English and Fox-English are not the only two languages displaying these types of misalignments. The conservative end of the spectrum itself breaks into two languages. For example, \u201cmask\u201d in Fox-English translates to \u201cmuzzle\u201d in OneAmerica-English, reflecting the differing attitudes across these subcommunities.<\/p>\n

There seems to be a mirrorlike duality at play. \u201cConservatism\u201d becomes \u201cliberalism,\u201d \u201cred\u201d is translated to \u201cblue,\u201d while \u201cCooper\u201d is converted into \u201cHannity.\u201d<\/p>\n

There\u2019s also no lack of what can only be called childish name-calling.<\/p>\n

\u201cTrumptards\u201d in CNN-English translates to \u201csnowflakes<\/a>\u201d in Fox-English; \u201cTrumpty\u201d in CNN-English translates to \u201cObummer\u201d in Fox-English; and \u201crepublicunts\u201d in CNN-English translates to \u201cdemocraps\u201d in Fox-English.<\/p>\n

Uncharted territory<\/h2>\n

Linguists have long emphasized how effective communication among people with different beliefs requires common ground<\/a>. Our findings show that the way we talk about political issues is becoming more divergent; depending on who\u2019s writing, a common word can be imbued with an entirely different meaning.<\/p>\n

[Deep knowledge, daily.<\/em> Sign up for The Conversation\u2019s newsletter<\/a>.]<\/p>\n

We wonder: How far are we from the point of no return when these linguistic differences begin to erode the common ground needed for productive communication?<\/p>\n

Have echo chambers on social media<\/a> exacerbated political polarization to the point where these linguistic misalignments have become ingrained in political discourse?<\/p>\n

When will \u201cdemocracy\u201d in one language variant stop translating into \u201cdemocracy\u201d in the other?\"The<\/p>\n

Mark Kamlet<\/a>, University Professor of Economics and Public Policy, Carnegie Mellon University<\/a><\/em>; Ashique KhudaBukhsh<\/a>, Project Scientist at the School of Computer Science, Carnegie Mellon University<\/a><\/em>, and Tom Mitchell<\/a>, Founders University Professor of Machine Learning, Carnegie Mellon University<\/a><\/em><\/p>\n

This article is republished from The Conversation<\/a> under a Creative Commons license. Read the original article<\/a>.<\/p>\n","protected":false},"excerpt":{"rendered":"

Mark Kamlet, Carnegie Mellon University; Ashique KhudaBukhsh, Carnegie Mellon University, and Tom Mitchell, Carnegie Mellon University It\u2019s no secret that U.S. politics has become highly polarized. Even so, there are probably few living Americans who ever witnessed anything that quite compares with this fall\u2019s first presidential debate. Was it really the case that the nation […]<\/p>\n","protected":false},"author":44,"featured_media":22801,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":[],"categories":[4],"tags":[1261,8410,149,326,1277,868,6351,3171,1791],"_links":{"self":[{"href":"https:\/\/www.lifeandnews.com\/articles\/wp-json\/wp\/v2\/posts\/22800"}],"collection":[{"href":"https:\/\/www.lifeandnews.com\/articles\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.lifeandnews.com\/articles\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.lifeandnews.com\/articles\/wp-json\/wp\/v2\/users\/44"}],"replies":[{"embeddable":true,"href":"https:\/\/www.lifeandnews.com\/articles\/wp-json\/wp\/v2\/comments?post=22800"}],"version-history":[{"count":2,"href":"https:\/\/www.lifeandnews.com\/articles\/wp-json\/wp\/v2\/posts\/22800\/revisions"}],"predecessor-version":[{"id":22813,"href":"https:\/\/www.lifeandnews.com\/articles\/wp-json\/wp\/v2\/posts\/22800\/revisions\/22813"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.lifeandnews.com\/articles\/wp-json\/wp\/v2\/media\/22801"}],"wp:attachment":[{"href":"https:\/\/www.lifeandnews.com\/articles\/wp-json\/wp\/v2\/media?parent=22800"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.lifeandnews.com\/articles\/wp-json\/wp\/v2\/categories?post=22800"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.lifeandnews.com\/articles\/wp-json\/wp\/v2\/tags?post=22800"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}