sentimetnal 0.0.1
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +7 -0
- data/.gitignore +14 -0
- data/.travis.yml +7 -0
- data/Gemfile +4 -0
- data/Guardfile +11 -0
- data/LICENSE.txt +22 -0
- data/README.md +53 -0
- data/Rakefile +33 -0
- data/data/AFINN-111.txt +2477 -0
- data/data/AFINN-96.txt +1480 -0
- data/data/AFINN-README.txt +43 -0
- data/examples/rapgenius.rb +13 -0
- data/examples/tupalo.rb +15 -0
- data/lib/sentimetnal.rb +31 -0
- data/lib/sentimetnal/core_ext/numeric.rb +23 -0
- data/lib/sentimetnal/core_ext/string.rb +5 -0
- data/lib/sentimetnal/version.rb +3 -0
- data/sentimetnal.gemspec +26 -0
- data/spec/sentimetnal_spec.rb +58 -0
- metadata +134 -0
@@ -0,0 +1,43 @@
|
|
1
|
+
AFINN is a list of English words rated for valence with an integer
|
2
|
+
between minus five (negative) and plus five (positive). The words have
|
3
|
+
been manually labeled by Finn Årup Nielsen in 2009-2011. The file
|
4
|
+
is tab-separated. There are two versions:
|
5
|
+
|
6
|
+
AFINN-111: Newest version with 2477 words and phrases.
|
7
|
+
|
8
|
+
AFINN-96: 1468 unique words and phrases on 1480 lines. Note that there
|
9
|
+
are 1480 lines, as some words are listed twice. The word list in not
|
10
|
+
entirely in alphabetic ordering.
|
11
|
+
|
12
|
+
An evaluation of the word list is available in:
|
13
|
+
|
14
|
+
Finn Årup Nielsen, "A new ANEW: Evaluation of a word list for
|
15
|
+
sentiment analysis in microblogs", http://arxiv.org/abs/1103.2903
|
16
|
+
|
17
|
+
The list was used in:
|
18
|
+
|
19
|
+
Lars Kai Hansen, Adam Arvidsson, Finn Årup Nielsen, Elanor Colleoni,
|
20
|
+
Michael Etter, "Good Friends, Bad News - Affect and Virality in
|
21
|
+
Twitter", The 2011 International Workshop on Social Computing,
|
22
|
+
Network, and Services (SocialComNet 2011).
|
23
|
+
|
24
|
+
|
25
|
+
This database of words is copyright protected and distributed under
|
26
|
+
"Open Database License (ODbL) v1.0"
|
27
|
+
http://www.opendatacommons.org/licenses/odbl/1.0/ or a similar
|
28
|
+
copyleft license.
|
29
|
+
|
30
|
+
See comments on the word list here:
|
31
|
+
http://fnielsen.posterous.com/old-anew-a-sentiment-about-sentiment-analysis
|
32
|
+
|
33
|
+
|
34
|
+
In Python the file may be read into a dictionary with:
|
35
|
+
|
36
|
+
>>> afinn = dict(map(lambda (k,v): (k,int(v)),
|
37
|
+
[ line.split('\t') for line in open("AFINN-111.txt") ]))
|
38
|
+
>>> afinn["Good".lower()]
|
39
|
+
3
|
40
|
+
>>> sum(map(lambda word: afinn.get(word, 0), "Rainy day but still in a good mood".lower().split()))
|
41
|
+
2
|
42
|
+
|
43
|
+
|
@@ -0,0 +1,13 @@
|
|
1
|
+
require 'sentimetnal'
|
2
|
+
require 'rapgenius'
|
3
|
+
|
4
|
+
happy_song = RapGenius::Song.find(139968) # Get Lucky
|
5
|
+
sad_song = RapGenius::Song.find(111264) # Run to the Hills
|
6
|
+
|
7
|
+
analyzer = Sentimetnal::Analyzer.new
|
8
|
+
|
9
|
+
happy_song_sentiment = analyzer.sentiment(happy_song.lines.map(&:lyric).join("").gsub(/\[.*\]/,""))
|
10
|
+
sad_song_sentiment = analyzer.sentiment(sad_song.lines.map(&:lyric).join("").gsub(/\[.*\]/,""))
|
11
|
+
|
12
|
+
puts "Get Lucky: #{happy_song_sentiment}"
|
13
|
+
puts "Run to the Hills: #{sad_song_sentiment}"
|
data/examples/tupalo.rb
ADDED
@@ -0,0 +1,15 @@
|
|
1
|
+
require 'sentimetnal'
|
2
|
+
require 'json'
|
3
|
+
require 'open-uri'
|
4
|
+
|
5
|
+
url = "http://tupalo.com/en/api/v1/reviews.json?public_id=2n5s5m"
|
6
|
+
reviews = JSON.parse(open(url).read)
|
7
|
+
|
8
|
+
analyzer = Sentimetnal::Analyzer.new
|
9
|
+
|
10
|
+
reviews.map do |review|
|
11
|
+
sentiment = analyzer.sentiment(review["review"])
|
12
|
+
puts "#{review["review"][0..100]}..."
|
13
|
+
puts "sentiment: #{sentiment.round(2)} | tupalo_rating: #{review["rating"]} | sentiment_rating: #{sentiment.to_rating} | emoji: #{sentiment.to_emoji}"
|
14
|
+
puts ""
|
15
|
+
end
|
data/lib/sentimetnal.rb
ADDED
@@ -0,0 +1,31 @@
|
|
1
|
+
require "sentimetnal/core_ext/string"
|
2
|
+
require "sentimetnal/core_ext/numeric"
|
3
|
+
require "sentimetnal/version"
|
4
|
+
|
5
|
+
module Sentimetnal
|
6
|
+
WORD_LIST = File.join(File.dirname(__dir__), "data", "AFINN-111.txt")
|
7
|
+
|
8
|
+
class Analyzer
|
9
|
+
attr_reader :word_list
|
10
|
+
|
11
|
+
def initialize(word_list_file=WORD_LIST)
|
12
|
+
@word_list = load_word_list(word_list_file)
|
13
|
+
end
|
14
|
+
|
15
|
+
def sentiment(string)
|
16
|
+
words = string.tokenize
|
17
|
+
sentiments = words.map { |w| word_list[w] || 0 }
|
18
|
+
|
19
|
+
sentiments.inject(:+)/Math.sqrt(sentiments.size)
|
20
|
+
end
|
21
|
+
|
22
|
+
private
|
23
|
+
def load_word_list(word_list_file)
|
24
|
+
word_list_data = IO.readlines(word_list_file, :encoding => "UTF-8")
|
25
|
+
word_list_data.map {|w|
|
26
|
+
t = w.split("\t")
|
27
|
+
[t[0].downcase, t[1].chomp.to_f]
|
28
|
+
}.to_h
|
29
|
+
end
|
30
|
+
end
|
31
|
+
end
|
@@ -0,0 +1,23 @@
|
|
1
|
+
class Numeric
|
2
|
+
def to_emoji
|
3
|
+
case self
|
4
|
+
when -5.0..-1.0 then ":scream:"
|
5
|
+
when -1.0..2.0 then ":expressionless:"
|
6
|
+
when 2.0..5.0 then ":smile:"
|
7
|
+
else
|
8
|
+
self
|
9
|
+
end
|
10
|
+
end
|
11
|
+
|
12
|
+
def to_rating
|
13
|
+
case self
|
14
|
+
when -5.0..-3.0 then 1
|
15
|
+
when -3.0..-1.0 then 2
|
16
|
+
when -1.0..1.0 then 3
|
17
|
+
when 1.0..3.0 then 4
|
18
|
+
when 3.0..5.0 then 5
|
19
|
+
else
|
20
|
+
self
|
21
|
+
end
|
22
|
+
end
|
23
|
+
end
|
data/sentimetnal.gemspec
ADDED
@@ -0,0 +1,26 @@
|
|
1
|
+
# coding: utf-8
|
2
|
+
|
3
|
+
lib = File.expand_path('../lib', __FILE__)
|
4
|
+
$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
|
5
|
+
require 'sentimetnal/version'
|
6
|
+
|
7
|
+
Gem::Specification.new do |spec|
|
8
|
+
spec.name = "sentimetnal"
|
9
|
+
spec.version = Sentimetnal::VERSION
|
10
|
+
spec.authors = ["johdax"]
|
11
|
+
spec.email = ["johdax@gmail.com"]
|
12
|
+
spec.summary = %q{Sentiment analyzer}
|
13
|
+
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}
|
14
|
+
spec.homepage = "http://github.com/johdax/sentimetnal"
|
15
|
+
spec.license = "MIT"
|
16
|
+
|
17
|
+
spec.files = `git ls-files -z`.split("\x0")
|
18
|
+
spec.test_files = spec.files.grep(%r{^(spec)/})
|
19
|
+
spec.require_paths = ["lib"]
|
20
|
+
|
21
|
+
spec.add_development_dependency "bundler", "~> 1.6"
|
22
|
+
spec.add_development_dependency "rake", "~> 10.0"
|
23
|
+
spec.add_development_dependency "rspec", "~> 3"
|
24
|
+
spec.add_development_dependency "guard", "~> 2.6"
|
25
|
+
spec.add_development_dependency "guard-rspec", "~> 4.3"
|
26
|
+
end
|
@@ -0,0 +1,58 @@
|
|
1
|
+
require 'sentimetnal'
|
2
|
+
|
3
|
+
describe "String tokenizer" do
|
4
|
+
let(:text) { "This is a sentence to tokenize. Another sentence; to split into words!" }
|
5
|
+
let(:tokenized_text) { text.tokenize }
|
6
|
+
|
7
|
+
it "returns an array of correct size" do
|
8
|
+
expect(tokenized_text).to be_a(Array)
|
9
|
+
expect(tokenized_text.count).to eq(12)
|
10
|
+
end
|
11
|
+
|
12
|
+
it "the array contains only words" do
|
13
|
+
expect(tokenized_text).not_to include(".", ";", "!")
|
14
|
+
expect(tokenized_text).to include("this", "sentence", "tokenize", "words")
|
15
|
+
end
|
16
|
+
end
|
17
|
+
|
18
|
+
describe "Sentiment Analyzer" do
|
19
|
+
let(:analyzer) { Sentimetnal::Analyzer.new }
|
20
|
+
|
21
|
+
describe "Sentiment Analyzer" do
|
22
|
+
context "AFINN sentiment word list" do
|
23
|
+
let(:word_list) { analyzer.word_list }
|
24
|
+
|
25
|
+
it "loads the word list into a hash" do
|
26
|
+
expect(word_list).to be_a(Hash)
|
27
|
+
end
|
28
|
+
|
29
|
+
it "returns a numeric value for a specific word" do
|
30
|
+
expect(word_list[word_list.keys.sample]).to be_a(Float)
|
31
|
+
end
|
32
|
+
end
|
33
|
+
end
|
34
|
+
|
35
|
+
context "sentiment analysis" do
|
36
|
+
it "returns a float for sentiment strength" do
|
37
|
+
expect(analyzer.sentiment("Not sure if this is good or bad?")).to be_a(Float)
|
38
|
+
end
|
39
|
+
|
40
|
+
it "returns a positive value for positive valence" do
|
41
|
+
expect(analyzer.sentiment("The best & most delicious beef and friendly staff!")).to be > 0
|
42
|
+
end
|
43
|
+
|
44
|
+
it "returns a negative value for negative valence" do
|
45
|
+
expect(analyzer.sentiment("WTF? Those horrible dishes gave me sleepless nights and stomach ache!")).to be < 0
|
46
|
+
end
|
47
|
+
end
|
48
|
+
|
49
|
+
context "sentiment strength converter" do
|
50
|
+
it "convert into a 5 star rating" do
|
51
|
+
expect(analyzer.sentiment("The best & most delicious beef and friendly staff!").to_rating).to eq(4)
|
52
|
+
end
|
53
|
+
|
54
|
+
it "convert into a emoji" do
|
55
|
+
expect(analyzer.sentiment("WTF? Those horrible dishes gave me sleepless nights and stomach ache!").to_emoji).to eq(":scream:")
|
56
|
+
end
|
57
|
+
end
|
58
|
+
end
|
metadata
ADDED
@@ -0,0 +1,134 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: sentimetnal
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.0.1
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- johdax
|
8
|
+
autorequire:
|
9
|
+
bindir: bin
|
10
|
+
cert_chain: []
|
11
|
+
date: 2014-08-02 00:00:00.000000000 Z
|
12
|
+
dependencies:
|
13
|
+
- !ruby/object:Gem::Dependency
|
14
|
+
name: bundler
|
15
|
+
requirement: !ruby/object:Gem::Requirement
|
16
|
+
requirements:
|
17
|
+
- - "~>"
|
18
|
+
- !ruby/object:Gem::Version
|
19
|
+
version: '1.6'
|
20
|
+
type: :development
|
21
|
+
prerelease: false
|
22
|
+
version_requirements: !ruby/object:Gem::Requirement
|
23
|
+
requirements:
|
24
|
+
- - "~>"
|
25
|
+
- !ruby/object:Gem::Version
|
26
|
+
version: '1.6'
|
27
|
+
- !ruby/object:Gem::Dependency
|
28
|
+
name: rake
|
29
|
+
requirement: !ruby/object:Gem::Requirement
|
30
|
+
requirements:
|
31
|
+
- - "~>"
|
32
|
+
- !ruby/object:Gem::Version
|
33
|
+
version: '10.0'
|
34
|
+
type: :development
|
35
|
+
prerelease: false
|
36
|
+
version_requirements: !ruby/object:Gem::Requirement
|
37
|
+
requirements:
|
38
|
+
- - "~>"
|
39
|
+
- !ruby/object:Gem::Version
|
40
|
+
version: '10.0'
|
41
|
+
- !ruby/object:Gem::Dependency
|
42
|
+
name: rspec
|
43
|
+
requirement: !ruby/object:Gem::Requirement
|
44
|
+
requirements:
|
45
|
+
- - "~>"
|
46
|
+
- !ruby/object:Gem::Version
|
47
|
+
version: '3'
|
48
|
+
type: :development
|
49
|
+
prerelease: false
|
50
|
+
version_requirements: !ruby/object:Gem::Requirement
|
51
|
+
requirements:
|
52
|
+
- - "~>"
|
53
|
+
- !ruby/object:Gem::Version
|
54
|
+
version: '3'
|
55
|
+
- !ruby/object:Gem::Dependency
|
56
|
+
name: guard
|
57
|
+
requirement: !ruby/object:Gem::Requirement
|
58
|
+
requirements:
|
59
|
+
- - "~>"
|
60
|
+
- !ruby/object:Gem::Version
|
61
|
+
version: '2.6'
|
62
|
+
type: :development
|
63
|
+
prerelease: false
|
64
|
+
version_requirements: !ruby/object:Gem::Requirement
|
65
|
+
requirements:
|
66
|
+
- - "~>"
|
67
|
+
- !ruby/object:Gem::Version
|
68
|
+
version: '2.6'
|
69
|
+
- !ruby/object:Gem::Dependency
|
70
|
+
name: guard-rspec
|
71
|
+
requirement: !ruby/object:Gem::Requirement
|
72
|
+
requirements:
|
73
|
+
- - "~>"
|
74
|
+
- !ruby/object:Gem::Version
|
75
|
+
version: '4.3'
|
76
|
+
type: :development
|
77
|
+
prerelease: false
|
78
|
+
version_requirements: !ruby/object:Gem::Requirement
|
79
|
+
requirements:
|
80
|
+
- - "~>"
|
81
|
+
- !ruby/object:Gem::Version
|
82
|
+
version: '4.3'
|
83
|
+
description: Simple Ruby sentiment analyzer based on the AFINN word list. Returns
|
84
|
+
a float value for the sentiment strength of an input text
|
85
|
+
email:
|
86
|
+
- johdax@gmail.com
|
87
|
+
executables: []
|
88
|
+
extensions: []
|
89
|
+
extra_rdoc_files: []
|
90
|
+
files:
|
91
|
+
- ".gitignore"
|
92
|
+
- ".travis.yml"
|
93
|
+
- Gemfile
|
94
|
+
- Guardfile
|
95
|
+
- LICENSE.txt
|
96
|
+
- README.md
|
97
|
+
- Rakefile
|
98
|
+
- data/AFINN-111.txt
|
99
|
+
- data/AFINN-96.txt
|
100
|
+
- data/AFINN-README.txt
|
101
|
+
- examples/rapgenius.rb
|
102
|
+
- examples/tupalo.rb
|
103
|
+
- lib/sentimetnal.rb
|
104
|
+
- lib/sentimetnal/core_ext/numeric.rb
|
105
|
+
- lib/sentimetnal/core_ext/string.rb
|
106
|
+
- lib/sentimetnal/version.rb
|
107
|
+
- sentimetnal.gemspec
|
108
|
+
- spec/sentimetnal_spec.rb
|
109
|
+
homepage: http://github.com/johdax/sentimetnal
|
110
|
+
licenses:
|
111
|
+
- MIT
|
112
|
+
metadata: {}
|
113
|
+
post_install_message:
|
114
|
+
rdoc_options: []
|
115
|
+
require_paths:
|
116
|
+
- lib
|
117
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
118
|
+
requirements:
|
119
|
+
- - ">="
|
120
|
+
- !ruby/object:Gem::Version
|
121
|
+
version: '0'
|
122
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
123
|
+
requirements:
|
124
|
+
- - ">="
|
125
|
+
- !ruby/object:Gem::Version
|
126
|
+
version: '0'
|
127
|
+
requirements: []
|
128
|
+
rubyforge_project:
|
129
|
+
rubygems_version: 2.4.1
|
130
|
+
signing_key:
|
131
|
+
specification_version: 4
|
132
|
+
summary: Sentiment analyzer
|
133
|
+
test_files:
|
134
|
+
- spec/sentimetnal_spec.rb
|