Skip to content

Instantly share code, notes, and snippets.

@driki
Last active December 15, 2015 08:38
Show Gist options
  • Star 0 You must be signed in to star a gist
  • Fork 0 You must be signed in to fork a gist
  • Save driki/5232070 to your computer and use it in GitHub Desktop.
Save driki/5232070 to your computer and use it in GitHub Desktop.
30 topics and themes automatically extracted from Knight News Challenge entries.

#Knight News Challenge - Open Government ###Hi, there.

NearbyFYI submitted a proposal to the Knight Foundation News Challenge, we're making it easier for small and mid-sized cities to share information online. It's a website like Yelp, but for cities and towns instead of restaurants.

Small cities and towns lack tools and incentive to publish structured data, so we collect what they already publish, unstructured text and analyze it to create structured data. We wanted to use the same tools and techniques that we use everyday to learn more about the themes and topics in the Open Government News Challenge. It was also a pretty neat way to browse the more than 800 amazing entries.

We've used a technique called latent Dirichlet allocation to automatically cluster and group the challenge entries. What themes emerge, what clusters of entries show up and how are they grouping? The groupings can be found below, this is a quick hack - a few hours of time - but we thought it'd be a fun way to view the entries while promoting our submission.

Enjoy, Matt & Jason

#Themes and Groupings

###Topic: 1 ["better", "change", "decisions", "making", "way", "world", "need", "problem", "game", "decision", "challenge", "real", "want", "good", "power", "even", "stories", "problems", "society", "well"]

###Topic: 2 ["news", "journalists", "journalism", "reporting", "investigative", "stories", "access", "reporters", "carolina", "press", "north", "coverage", "reports", "training", "organizations", "journalist", "⊓", "available", "team", "working"]

###Topic: 3 ["mobile", "access", "using", "services", "india", "internet", "service", "technology", "text", "areas", "sms", "communication", "population", "via", "over", "based", "way", "voice", "phones", "phone"]

###Topic: 4 ["policy", "process", "solutions", "citizen", "decision", "ideas", "debate", "political", "face", "making", "participation", "dialogue", "proposals", "policies", "issue", "way", "petition", "think", "discussion", "based"]

###Topic: 5 ["source", "software", "development", "projects", "support", "standards", "code", "working", "organizations", "management", "team", "governments", "experience", "build", "based", "need", "foundation", "solution", "drupal", "already"]

###Topic: 6 ["app", "mobile", "application", "user", "apps", "location", "citizen", "using", "create", "smartphone", "different", "cities", "via", "based", "phone", "take", "real", "reports", "reporting", "share"]

###Topic: 7 ["performance", "states", "⊝", "tool", "federal", "analysis", "phase", "accessibility", "provide", "process", "transparency", "agencies", "used", "national", "software", "available", "⊔", "united", "organizations", "both"]

###Topic: 8 ["source", "available", "search", "access", "applications", "datasets", "portal", "sets", "user", "tool", "provide", "websites", "find", "build", "create", "using", "easy", "repository", "developers", "resources"]

###Topic: 9 ["health", "justice", "court", "women", "philadelphia", "legal", "human", "care", "rights", "violence", "access", "healthcare", "law", "courts", "well", "cases", "safety", "gun", "criminal", "industry"]

###Topic: 10 ["officials", "elected", "congress", "political", "legislation", "legislative", "constituents", "representatives", "vote", "bill", "bills", "direct", "democracy", "legislators", "members", "votes", "federal", "house", "user", "representative"]

###Topic: 11 ["citizen", "transparency", "participation", "society", "authorities", "european", "institutions", "between", "initiatives", "political", "accountability", "parliament", "countries", "corruption", "parliamentary", "process", "openness", "order", "reports", "knowledge"]

###Topic: 12 ["school", "water", "chicago", "schools", "students", "children", "parents", "education", "teachers", "california", "learning", "child", "kids", "families", "paul", "building", "buildings", "nonprofit", "district", "create"]

###Topic: 13 ["organization", "groups", "regulations", "change", "members", "activities", "democracy", "laws", "legal", "law", "protest", "group", "rights", "permit", "model", "organizational", "issue", "activists", "common", "held"]

###Topic: 14 ["comment", "idea", "great", "february", "see", "think", "very", "love", "much", "good", "really", "way", "need", "know", "want", "here", "hope", "something", "well", "thank"]

###Topic: 15 ["engagement", "communities", "technology", "network", "engage", "members", "participation", "organizations", "citizen", "leaders", "outreach", "digital", "democracy", "well", "officials", "sharing", "person", "create", "residents", "knowledge"]

###Topic: 16 ["news", "content", "stories", "action", "video", "story", "digital", "videos", "ón", "radio", "show", "blog", "point", "los", "events", "interactive", "want", "engage", "good", "change"]

###Topic: 17 ["video", "meetings", "meeting", "agenda", "agendas", "specific", "topics", "council", "island", "audio", "items", "record", "available", "text", "being", "documents", "well", "officials", "solution", "important"]

###Topic: 18 ["services", "service", "county", "business", "governments", "small", "cost", "companies", "program", "businesses", "vendors", "provide", "insurance", "job", "costs", "need", "towns", "access", "quality", "company"]

###Topic: 19 ["youth", "service", "national", "education", "⊝", "programs", "parks", "program", "young", "park", "activities", "training", "cultural", "educational", "resources", "communities", "process", "mission", "based", "support"]

###Topic: 20 ["university", "technology", "research", "development", "policy", "center", "team", "science", "school", "design", "developing", "developed", "access", "director", "including", "systems", "founder", "computer", "department", "over"]

###Topic: 21 ["map", "environmental", "climate", "maps", "mapping", "disaster", "toolkit", "natural", "flood", "organizations", "change", "documents", "modules", "communities", "module", "based", "weather", "satellite", "additional", "user"]

###Topic: 22 ["planning", "transit", "transportation", "infrastructure", "traffic", "bike", "feedback", "models", "urban", "application", "transport", "source", "area", "planners", "tweets", "street", "using", "food", "projects", "safety"]

###Topic: 23 ["cities", "communities", "projects", "neighborhood", "neighborhoods", "ideas", "urban", "design", "residents", "engagement", "development", "action", "create", "planning", "innovation", "build", "solutions", "program", "together", "around"]

###Topic: 24 ["budget", "federal", "spending", "money", "contracts", "financial", "florida", "database", "states", "contract", "tax", "level", "dollars", "finance", "understand", "funding", "transparency", "budgets", "million", "much"]

###Topic: 25 ["voters", "voter", "elections", "election", "ballot", "candidates", "⊢", "voting", "candidate", "vote", "polling", "results", "process", "ballots", "guide", "initiative", "test", "initiatives", "level", "democracy"]

###Topic: 26 ["matt", "town", "documents", "governments", "cities", "michigan", "service", "municipal", "hall", "great", "jerry", "access", "municipalities", "support", "detroit", "database", "news", "level", "focus", "idea"]

###Topic: 27 ["political", "vote", "campaign", "candidates", "voting", "politicians", "election", "candidate", "smart", "elections", "campaigns", "background", "contributions", "politics", "issue", "elected", "interest", "special", "promises", "provide"]

###Topic: 28 ["think", "⊙t", "⊓", "zach", "feedback", "⊝", "don", "someone", "want", "something", "way", "find", "⊙re", "know", "call", "phone", "going", "edwards", "even", "great"]

###Topic: 29 ["requests", "records", "foia", "request", "freedom", "agencies", "process", "act", "documents", "transparency", "law", "federal", "database", "foi", "access", "right", "corporate", "released", "allow", "journalists"]

###Topic: 30 ["land", "kenya", "countries", "world", "projects", "africa", "society", "african", "governments", "international", "well", "global", "initiative", "aid", "sector", "around", "country", "provide", "organisations", "improve"]

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment