Word cloud of Sarah Palin’s speech at the RNC. Text taken from http://elections.nytimes.com/2008/president/conventions/videos/transcripts/20080903_PALIN_SPEECH.html
Created using wordle.net. Process notes: The following changes were made for clarity and to avoid redunancy: United States = UnitedStates; vice president = VicePresident; John McCain = JohnMcCain; John S. McCain = JohnMcCain; McCain (when used without John) = JohnMcCain; candidates = candidate; daughter = daughters; son = sons; Americans = American; small town / small towns / small-town = smalltown; moms = mom; next president = NextPresident; Saudi Arabia = SaudiArabia; challenges = challenge; daughters = daughter; White House = WhiteHouse; pipeline = pipelines; tax = taxes; terrorists = terrorist; opponents = opponent; Al Qaida = AlQaida; businesses = business; produce / produced / producing = production. Not all changes are reflected in the cloud because the frequency was still not high enough.
A space was added before each (noun)’s to ensure that possessives were not listed differently than the nouns that possess.
Many hypens were either deleted or replaced with spaces as appropriate (for example, McCain-Palin = McCain Palin, commander-in-chief remains unchanged, and kind-hearted is changed to kindhearted).
Leave a Reply