{"id":727,"date":"2011-03-04T09:57:59","date_gmt":"2011-03-04T09:57:59","guid":{"rendered":"http:\/\/www.mariarabinovich.com\/blog\/?p=727"},"modified":"2011-12-11T08:49:27","modified_gmt":"2011-12-11T08:49:27","slug":"pos-tagging-and-fun-with-code","status":"publish","type":"post","link":"http:\/\/www.mariarabinovich.com\/blog\/archives\/727","title":{"rendered":"POS Tagging and Visualization"},"content":{"rendered":"

Update: the following images show the use of certain words referring to war, children\/education, and health care in the combined speeches of the last three presidents. The word choices reflect my own biases. Words such as war, terrorists, terror, security, bomb, attack, <\/em>were grouped into the “military” category, words such as education, children, schools, teachers, <\/em>were grouped into the “children” category, and words such as health, insurance, doctors, medicine, medicaid, medicare, <\/em>were grouped into the “healthcare” category. The location of the images represents the location in the body of all speeches where the words occur. Next I would like to do visualizations of Ngrams that show likely sentences\/sentence combinations, so that the location is more meaningful.<\/p>\n

Obama:<\/p>\n

\"\"<\/a><\/p>\n

Clinton:<\/p>\n

\"\"<\/a><\/p>\n

Bush:<\/p>\n

 <\/p>\n

\"\"<\/a><\/p>\n

 <\/p>\n

Here is a mashup based on Heather’s code for mashing up two texts by replacing the nouns in one with the nouns of the other.
\nThis is an Obama \/ Bush medley state of the union address:<\/p>\n

 <\/p>\n

“We must continue to pursue an aggressive , proposal humility patchwork .\u00a0Congress has some unfinished canal on the account of taxes .\u00a0The respect reductions you passed are set to expire .
\nUnless you act , the unfair harmony on per will go back up .
\nUnless you act , millions of families will be charged $ 300 more in Federal taxes for every providing–engagement .
\nUnless you act , small businesses will pay higher taxes .
\nUnless you act , the media mountain will eventually come back to legacy .\u00a0Unless you act , Americans plot a Elementary increase .
\nWhat Congress has given , the Congress should not take away .
\nFor the fastest of advancement decade–what , the college cuts you passed should be permanent .<\/em><\/address>\n
Our allowance for jobs and whip must help small-business owners and employees with firefighter from needless Federal regulation and protect them from sign and frivolous lawsuits .<\/em><\/address>\n

\nConsumers and businesses need reliable supplies of childhood to make our teacher run , so I urge you to pass Rock to modernize our electricity notion , promote System , and make America less dependent on foreign sources of System .<\/em><\/address>\n
And here is the same part of the speeches, where the verbs replace verbs:<\/em><\/address>\n
“Congress has some unfinished business on the issue of taxes .The tax reductions you passed are set to protect .<\/address>\n
Unless you wonder , the unfair tax on marriage will exist back up .<\/address>\n
Unless you advance , millions of families will be charged $ 300 more in Federal taxes for every child .
\nUnless you reform , small businesses will prefer higher taxes .
\nUnless you delay , the death tax will eventually come back to life .
\nUnless you reveal , Americans face a tax dig .
\nWhat Congress has given , the Congress should not suffer away .
\nFor the sake of job growth , the tax cuts you passed should be permanent .
\nOur agenda for jobs and growth must eat small-business owners and employees with relief from needless Federal regulation and maintain them from junk and frivolous lawsuits .
\nConsumers and businesses need reliable supplies of energy to open our economy rot , so I urge you to supplant legislation to quit our electricity system , promote conservation , and save America less dependent on foreign sources of energy .”<\/address>\n
Here is the rest of it. . .<\/address>\n

\nMy administration is promoting free and Internet harder to open up new markets for America’s entrepreneurs and Highway and farmers , to create jobs for American workers .<\/em><\/address>\n

\nYounger workers should have the mass to build a discord connection by saving cut–a of their Social take taxes in a personal fate banker .<\/em><\/address>\n

\nWe should make the Social outcome teacher a top-down of engineering for the American people .
\nAnd we should limit the materials of border on this spread by acting as good stewards of taxpayers’ dollars .<\/em><\/address>\n

\nIn 2 weeks , I will send you a budget that funds the opportunity–it , protects the lot , and meets important not needs while limiting the manufacturing in discretionary spending to less than 4 percent .
\nThis will require that Congress generation on priorities , cut wasteful spending , and be wise with the people’s Product .
\n<\/em><\/address>\n
By doing so , we can cut the dignity in half over the next 5 years .
\nTonight I also ask you to reform our General laws so they reflect our values and Court our initiative .
\nI propose a new temporary- watch act to match willing foreign workers with willing selfish when no Americans can be found to fill the stale .<\/em><\/address>\n

\nThis life will be good for our principle because growth will find needed workers in an honest and orderly air .
\nA watch task will help protect our duty , allowing borders–and employment and dollar fee to basic on true threats to our national emphasis .<\/em><\/address>\n

\nI oppose amnesty , because it would encourage further illegal struggle and unfairly equivocation those who break our laws .
\nMy temporary- curiosity heritage will preserve the citizenship risk for those who respect the sun while bringing millions of dime men and women out from the shadows of American Depression .
\nOur Nation’s communism regard department , like our Retirement , is also in a fee of ceilings .<\/em><\/address>\n

\nAmazing medical technologies are improving and saving lives .
\nThis dramatic support has brought its own friend , in the rising costs of medical energy and terrorism collapse .
\nMembers of Congress , we must work together to help danger those costs and extend the teacher of modern employers throughout our storm .<\/em><\/address>\n

\nhomeland these goals require<\/em>s bipartisan investment–their , and 2 months ago , you showed the read .<\/em><\/address>\n
By will Super and adding a freedom drug history–an , you kept a fighting–is commitment to our Internet .
\nYou are giving them the modern segregation they deserve .
\nStarting this Home , under the capacity you passed , drive can choose to receive a drug project span , saving them 10 to 25 percent off the storm detention of most magnitude drugs , and millions of low-income deal can get an additional $ 600 to buy regard .
\nBeginning next threat , rescue will have new economy for preventive screenings against diabetes and year disease , and stock just entering strength– can receive poverty–we exams .
\nIn January of 2006 , determination can get contributor drug providing–engagement under law .<\/em><\/address>\n

\nFor a monthly hatred of about $ 35 , most gas who do not have that coverage today can expect to see their drug bills cut roughly in half .<\/em><\/address>\n

\nUnder this invest , movement citizens will be able to keep their point just as it is , or they can choose a ninth charity that fits them best , just as you , as Members of Congress , can choose an guaranteed statistics that meets your needs .
\nAnd starting this extremism , millions of Americans will be able to save status hour for their medical expenses in a function savings moon .<\/em><\/address>\n

\nI signed this division proudly , and any set to limit the choices of our Union or to take away their flying–without drug assure under belief will meet my fist .”<\/em><\/address>\n
\u00a0<\/address>\n

In the way that preserves the style and pace of the speeches more, it is more interesting than the N-grams, but the obvious distinctions between the sentence fragments in the N-gram generations were more revealing of different contents and patterns.<\/p>\n","protected":false},"excerpt":{"rendered":"

Update: the following images show the use of certain words referring to war, children\/education, and health care in the combined speeches of the last three presidents. The word choices reflect my own biases. Words such as war, terrorists, terror, security, bomb, attack, were grouped into the “military” category, words such as education, children, schools, teachers, […]<\/p>\n","protected":false},"author":3,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[25,1],"tags":[],"class_list":["post-727","post","type-post","status-publish","format-standard","hentry","category-learning-bit-x-bit","category-uncategorized"],"_links":{"self":[{"href":"http:\/\/www.mariarabinovich.com\/blog\/wp-json\/wp\/v2\/posts\/727","targetHints":{"allow":["GET"]}}],"collection":[{"href":"http:\/\/www.mariarabinovich.com\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"http:\/\/www.mariarabinovich.com\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"http:\/\/www.mariarabinovich.com\/blog\/wp-json\/wp\/v2\/users\/3"}],"replies":[{"embeddable":true,"href":"http:\/\/www.mariarabinovich.com\/blog\/wp-json\/wp\/v2\/comments?post=727"}],"version-history":[{"count":18,"href":"http:\/\/www.mariarabinovich.com\/blog\/wp-json\/wp\/v2\/posts\/727\/revisions"}],"predecessor-version":[{"id":1096,"href":"http:\/\/www.mariarabinovich.com\/blog\/wp-json\/wp\/v2\/posts\/727\/revisions\/1096"}],"wp:attachment":[{"href":"http:\/\/www.mariarabinovich.com\/blog\/wp-json\/wp\/v2\/media?parent=727"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"http:\/\/www.mariarabinovich.com\/blog\/wp-json\/wp\/v2\/categories?post=727"},{"taxonomy":"post_tag","embeddable":true,"href":"http:\/\/www.mariarabinovich.com\/blog\/wp-json\/wp\/v2\/tags?post=727"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}