sentimetnal 0.0.1

data/data/AFINN-README.txt

@@ -0,0 +1,43 @@
+AFINN is a list of English words rated for valence with an integer
+between minus five (negative) and plus five (positive). The words have
+been manually labeled by Finn Årup Nielsen in 2009-2011. The file
+is tab-separated. There are two versions:
+
+AFINN-111: Newest version with 2477 words and phrases.
+
+AFINN-96: 1468 unique words and phrases on 1480 lines. Note that there
+are 1480 lines, as some words are listed twice. The word list in not
+entirely in alphabetic ordering.  
+
+An evaluation of the word list is available in:
+
+Finn Årup Nielsen, "A new ANEW: Evaluation of a word list for
+sentiment analysis in microblogs", http://arxiv.org/abs/1103.2903
+
+The list was used in: 
+
+Lars Kai Hansen, Adam Arvidsson, Finn Årup Nielsen, Elanor Colleoni,
+Michael Etter, "Good Friends, Bad News - Affect and Virality in
+Twitter", The 2011 International Workshop on Social Computing,
+Network, and Services (SocialComNet 2011).
+
+
+This database of words is copyright protected and distributed under
+"Open Database License (ODbL) v1.0"
+http://www.opendatacommons.org/licenses/odbl/1.0/ or a similar
+copyleft license.
+
+See comments on the word list here:
+http://fnielsen.posterous.com/old-anew-a-sentiment-about-sentiment-analysis
+
+
+In Python the file may be read into a dictionary with:
+
+>>> afinn = dict(map(lambda (k,v): (k,int(v)), 
+                     [ line.split('\t') for line in open("AFINN-111.txt") ]))
+>>> afinn["Good".lower()]
+3
+>>> sum(map(lambda word: afinn.get(word, 0), "Rainy day but still in a good mood".lower().split()))
+2
+
+

data/examples/rapgenius.rb

@@ -0,0 +1,13 @@
+require 'sentimetnal'
+require 'rapgenius'
+
+happy_song = RapGenius::Song.find(139968) # Get Lucky
+sad_song   = RapGenius::Song.find(111264) # Run to the Hills
+
+analyzer = Sentimetnal::Analyzer.new
+
+happy_song_sentiment = analyzer.sentiment(happy_song.lines.map(&:lyric).join("").gsub(/\[.*\]/,""))
+sad_song_sentiment = analyzer.sentiment(sad_song.lines.map(&:lyric).join("").gsub(/\[.*\]/,""))
+
+puts "Get Lucky: #{happy_song_sentiment}"
+puts "Run to the Hills: #{sad_song_sentiment}"

data/examples/tupalo.rb

@@ -0,0 +1,15 @@
+require 'sentimetnal'
+require 'json'
+require 'open-uri'
+
+url = "http://tupalo.com/en/api/v1/reviews.json?public_id=2n5s5m"
+reviews = JSON.parse(open(url).read)
+
+analyzer = Sentimetnal::Analyzer.new
+
+reviews.map do |review|
+  sentiment = analyzer.sentiment(review["review"])
+  puts "#{review["review"][0..100]}..."
+  puts "sentiment: #{sentiment.round(2)} | tupalo_rating: #{review["rating"]} | sentiment_rating: #{sentiment.to_rating} | emoji: #{sentiment.to_emoji}"
+  puts ""
+end

data/lib/sentimetnal.rb

@@ -0,0 +1,31 @@
+require "sentimetnal/core_ext/string"
+require "sentimetnal/core_ext/numeric"
+require "sentimetnal/version"
+
+module Sentimetnal
+  WORD_LIST = File.join(File.dirname(__dir__), "data", "AFINN-111.txt")
+  
+  class Analyzer
+    attr_reader :word_list
+    
+    def initialize(word_list_file=WORD_LIST)
+      @word_list = load_word_list(word_list_file)
+    end
+    
+    def sentiment(string)
+      words = string.tokenize
+      sentiments = words.map { |w| word_list[w] || 0 }
+      
+      sentiments.inject(:+)/Math.sqrt(sentiments.size)
+    end
+    
+    private
+    def load_word_list(word_list_file)
+      word_list_data = IO.readlines(word_list_file, :encoding => "UTF-8")
+      word_list_data.map {|w|
+        t = w.split("\t")
+        [t[0].downcase, t[1].chomp.to_f]
+      }.to_h
+    end
+  end
+end

data/lib/sentimetnal/core_ext/numeric.rb

@@ -0,0 +1,23 @@
+class Numeric
+  def to_emoji
+    case self
+    when -5.0..-1.0 then ":scream:"
+    when -1.0..2.0  then ":expressionless:"
+    when 2.0..5.0   then ":smile:"
+    else
+      self
+    end
+  end
+  
+  def to_rating
+    case self
+    when -5.0..-3.0 then 1
+    when -3.0..-1.0 then 2
+    when -1.0..1.0  then 3
+    when 1.0..3.0   then 4
+    when 3.0..5.0   then 5
+    else
+      self
+    end
+  end
+end

data/lib/sentimetnal/core_ext/string.rb

@@ -0,0 +1,5 @@
+class String
+  def tokenize
+    self.downcase.split(/\W+/)
+  end
+end

data/lib/sentimetnal/version.rb

@@ -0,0 +1,3 @@
+module Sentimetnal
+  VERSION = "0.0.1"
+end

data/sentimetnal.gemspec

@@ -0,0 +1,26 @@
+# coding: utf-8
+
+lib = File.expand_path('../lib', __FILE__)
+$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
+require 'sentimetnal/version'
+
+Gem::Specification.new do |spec|
+  spec.name          = "sentimetnal"
+  spec.version       = Sentimetnal::VERSION
+  spec.authors       = ["johdax"]
+  spec.email         = ["johdax@gmail.com"]
+  spec.summary       = %q{Sentiment analyzer}
+  spec.description   = %q{Simple Ruby sentiment analyzer based on the AFINN word list. Returns a float value for the sentiment strength of an input text}
+  spec.homepage      = "http://github.com/johdax/sentimetnal"
+  spec.license       = "MIT"
+
+  spec.files         = `git ls-files -z`.split("\x0")
+  spec.test_files    = spec.files.grep(%r{^(spec)/})
+  spec.require_paths = ["lib"]
+
+  spec.add_development_dependency "bundler", "~> 1.6"
+  spec.add_development_dependency "rake", "~> 10.0"
+  spec.add_development_dependency "rspec", "~> 3"
+  spec.add_development_dependency "guard", "~> 2.6"
+  spec.add_development_dependency "guard-rspec", "~> 4.3"
+end

data/spec/sentimetnal_spec.rb

@@ -0,0 +1,58 @@
+require 'sentimetnal'
+
+describe "String tokenizer" do
+  let(:text) { "This is a sentence to tokenize. Another sentence; to split into words!" }
+  let(:tokenized_text) { text.tokenize }
+  
+  it "returns an array of correct size" do
+    expect(tokenized_text).to       be_a(Array)
+    expect(tokenized_text.count).to eq(12)
+  end
+  
+  it "the array contains only words" do
+    expect(tokenized_text).not_to include(".", ";", "!")
+    expect(tokenized_text).to     include("this", "sentence", "tokenize", "words")
+  end
+end
+
+describe "Sentiment Analyzer" do
+  let(:analyzer) { Sentimetnal::Analyzer.new }
+   
+  describe "Sentiment Analyzer" do
+    context "AFINN sentiment word list" do
+      let(:word_list) { analyzer.word_list }
+      
+      it "loads the word list into a hash" do
+        expect(word_list).to be_a(Hash)
+      end
+  
+      it "returns a numeric value for a specific word" do
+        expect(word_list[word_list.keys.sample]).to be_a(Float)
+      end
+    end 
+  end
+  
+  context "sentiment analysis" do
+    it "returns a float for sentiment strength" do
+      expect(analyzer.sentiment("Not sure if this is good or bad?")).to be_a(Float)
+    end
+    
+    it "returns a positive value for positive valence" do
+      expect(analyzer.sentiment("The best & most delicious beef and friendly staff!")).to be > 0
+    end
+    
+    it "returns a negative value for negative valence" do
+      expect(analyzer.sentiment("WTF? Those horrible dishes gave me sleepless nights and stomach ache!")).to be < 0
+    end
+  end
+  
+  context "sentiment strength converter" do
+    it "convert into a 5 star rating" do
+      expect(analyzer.sentiment("The best & most delicious beef and friendly staff!").to_rating).to eq(4)
+    end
+    
+    it "convert into a emoji" do
+      expect(analyzer.sentiment("WTF? Those horrible dishes gave me sleepless nights and stomach ache!").to_emoji).to eq(":scream:")
+    end
+  end
+end

metadata

@@ -0,0 +1,134 @@
+--- !ruby/object:Gem::Specification
+name: sentimetnal
+version: !ruby/object:Gem::Version
+  version: 0.0.1
+platform: ruby
+authors:
+- johdax
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2014-08-02 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: bundler
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.6'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.6'
+- !ruby/object:Gem::Dependency
+  name: rake
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '10.0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '10.0'
+- !ruby/object:Gem::Dependency
+  name: rspec
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3'
+- !ruby/object:Gem::Dependency
+  name: guard
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '2.6'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '2.6'
+- !ruby/object:Gem::Dependency
+  name: guard-rspec
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '4.3'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '4.3'
+description: Simple Ruby sentiment analyzer based on the AFINN word list. Returns
+  a float value for the sentiment strength of an input text
+email:
+- johdax@gmail.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- ".gitignore"
+- ".travis.yml"
+- Gemfile
+- Guardfile
+- LICENSE.txt
+- README.md
+- Rakefile
+- data/AFINN-111.txt
+- data/AFINN-96.txt
+- data/AFINN-README.txt
+- examples/rapgenius.rb
+- examples/tupalo.rb
+- lib/sentimetnal.rb
+- lib/sentimetnal/core_ext/numeric.rb
+- lib/sentimetnal/core_ext/string.rb
+- lib/sentimetnal/version.rb
+- sentimetnal.gemspec
+- spec/sentimetnal_spec.rb
+homepage: http://github.com/johdax/sentimetnal
+licenses:
+- MIT
+metadata: {}
+post_install_message: 
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubyforge_project: 
+rubygems_version: 2.4.1
+signing_key: 
+specification_version: 4
+summary: Sentiment analyzer
+test_files:
+- spec/sentimetnal_spec.rb