chime 0.1.0
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +15 -0
- data/.document +5 -0
- data/Gemfile +14 -0
- data/Gemfile.lock +74 -0
- data/LICENSE.txt +20 -0
- data/README.md +4 -0
- data/README.rdoc +19 -0
- data/Rakefile +53 -0
- data/VERSION +1 -0
- data/chime.gemspec +70 -0
- data/lib/chime/emotions/emotion_bank.rb +265 -0
- data/lib/chime/emotions/emotions.csv +1542 -0
- data/lib/chime/emotions/stopwords.rb +42 -0
- data/lib/chime/emotions/subjectivity.csv +1 -0
- data/lib/chime/emotions/term_polarities.rb +1467 -0
- data/lib/chime/version.rb +3 -0
- data/lib/chime.rb +175 -0
- data/test/helper.rb +18 -0
- data/test/test_chime.rb +7 -0
- metadata +134 -0
data/lib/chime.rb
ADDED
@@ -0,0 +1,175 @@
|
|
1
|
+
require_relative "./chime/version"
|
2
|
+
require_relative './chime/emotions/emotion_bank.rb'
|
3
|
+
require_relative './chime/emotions/term_polarities.rb'
|
4
|
+
require_relative './chime/emotions/stopwords.rb'
|
5
|
+
require 'lingua/stemmer'
|
6
|
+
|
7
|
+
module Chime
|
8
|
+
|
9
|
+
# this method returns the best-fit emotion for the status message
|
10
|
+
def self.emotion(message)
|
11
|
+
# get the emotion for which the emotion score value is highest
|
12
|
+
Chime.get_emotion_score(message, EmotionBank.get_term_emotions, build_term_frequencies(message))
|
13
|
+
end
|
14
|
+
|
15
|
+
# this method returns the polarity value for the status message
|
16
|
+
# (normalized by the number of 'polar' words that the status
|
17
|
+
# message contains)
|
18
|
+
def self.polarity(message)
|
19
|
+
# get the polarity for which the polarity score value is highest
|
20
|
+
Chime.get_polarity_score(message, TermPolarities.get_term_polarities, Chime.build_term_frequencies(message))
|
21
|
+
end
|
22
|
+
|
23
|
+
|
24
|
+
private
|
25
|
+
|
26
|
+
# this method reads the text of the status message
|
27
|
+
# inputed by the user, removes common english words,
|
28
|
+
# strips punctuation and capitalized letters, isolates
|
29
|
+
# the stem of the word, and ultimately produces a hash
|
30
|
+
# where the keys are the stems of the remaining words,
|
31
|
+
# and the values are their respective frequencies within
|
32
|
+
# the status message
|
33
|
+
def self.build_term_frequencies(message, term_frequencies = {})
|
34
|
+
# clean the text of the status message
|
35
|
+
happy_emoticon = happy_emoticon(message)
|
36
|
+
sad_emoticon = sad_emoticon(message)
|
37
|
+
words = words_from_message_text(message)
|
38
|
+
#filter for english stopwords
|
39
|
+
stopwords = Stopwords.stopwords
|
40
|
+
words = words - stopwords
|
41
|
+
#get word stems
|
42
|
+
word_stems = Chime.get_word_stems words
|
43
|
+
#create term_frequencies
|
44
|
+
#return term frequency hash
|
45
|
+
create_term_frequencies(word_stems, term_frequencies)
|
46
|
+
end
|
47
|
+
|
48
|
+
# this method takes an array of words an returns an array of word stems
|
49
|
+
def self.get_word_stems(words, output=[])
|
50
|
+
stemmer = Lingua::Stemmer.new(:language => "en")
|
51
|
+
words.each do |word|
|
52
|
+
output << stemmer.stem(word)
|
53
|
+
end
|
54
|
+
output
|
55
|
+
end
|
56
|
+
|
57
|
+
# this method takes an emotion-words hash and a hash containing word
|
58
|
+
# frequencies for the status message, calculates a numerical score
|
59
|
+
# for each possble emotion, and returns the emotion with the highest
|
60
|
+
# "score"
|
61
|
+
def self.get_emotion_score(message, emotions, term_frequencies, emotion_score = {})
|
62
|
+
term_frequencies.each do |key,value|
|
63
|
+
set_emotions(emotions, emotion_score, key, value)
|
64
|
+
end
|
65
|
+
# return an emotion_score_hash to be processed by emotion
|
66
|
+
# get clue from any emoticons present
|
67
|
+
check_emoticon_for_emotion(emotion_score, message)
|
68
|
+
end
|
69
|
+
|
70
|
+
# this method gives the status method a normalized polarity
|
71
|
+
# value based on the words it contains
|
72
|
+
def self.get_polarity_score (message, polarity_hash, term_frequencies, polarity_scores = [])
|
73
|
+
term_frequencies.each do |key, value|
|
74
|
+
set_polarities(key, value, polarity_hash, polarity_scores)
|
75
|
+
end
|
76
|
+
|
77
|
+
# return an polarity_score_hash to be processed by polarity method
|
78
|
+
# return an emotion_score_hash to be processed by emotion
|
79
|
+
# get clue from any emoticons present
|
80
|
+
check_emoticon_for_polarity(polarity_scores, message)
|
81
|
+
end
|
82
|
+
|
83
|
+
def self.happy_emoticon(message)
|
84
|
+
(message.include?(":)") || message.include?(":-)") || message.include?(":]") || message.include?(":-]"))
|
85
|
+
end
|
86
|
+
|
87
|
+
def self.sad_emoticon(message)
|
88
|
+
(message.include?(":(") || message.include?(":-(") || message.include?(":[") || message.include?(":-["))
|
89
|
+
end
|
90
|
+
|
91
|
+
def self.words_from_message_text(message)
|
92
|
+
message.gsub!(/[^a-z ]/i, '')
|
93
|
+
message.downcase!
|
94
|
+
message.gsub!(/((([A-Za-z]{3,9}:(?:\/\/)?)(?:[-;:&=\+\$,\w]+@)?[A-Za-z0-9.-]+|(?:www.|[-;:&=\+\$,\w]+@)[A-Za-z0-9.-]+)((?:\/[\+~%\/.\w-_]*)?\??(?:[-\+=&;%@.\w_]*)#?(?:[\w]*))?)/, '')
|
95
|
+
message.gsub!(/(?=\w*h)(?=\w*t)(?=\w*t)(?=\w*p)\w*/, '')
|
96
|
+
message.gsub!(/\s\s+/,' ')
|
97
|
+
message.split(" ")
|
98
|
+
end
|
99
|
+
|
100
|
+
def self.set_emotions(emotions, emotion_score, term, frequency)
|
101
|
+
emotions.keys.each do |k|
|
102
|
+
store_emotions(emotions, emotion_score, k, term, frequency)
|
103
|
+
end
|
104
|
+
end
|
105
|
+
|
106
|
+
def self.set_polarities(term, frequency, polarity_hash, polarity_scores)
|
107
|
+
polarity_hash.keys.each do |k|
|
108
|
+
store_polarities(term, k, polarity_hash, polarity_scores)
|
109
|
+
end
|
110
|
+
end
|
111
|
+
|
112
|
+
def self.store_emotions(emotions, emotion_score, emotion, term, frequency)
|
113
|
+
if emotions[emotion].include?(term)
|
114
|
+
emotion_score[emotion] ||= 0
|
115
|
+
emotion_score[emotion] += frequency
|
116
|
+
end
|
117
|
+
end
|
118
|
+
|
119
|
+
def self.store_polarities(term, word, polarity_hash, polarity_scores)
|
120
|
+
if term == word
|
121
|
+
polarity_scores << (polarity_hash[word].to_f)
|
122
|
+
end
|
123
|
+
end
|
124
|
+
|
125
|
+
def self.check_emoticon_for_emotion(emotion_score, message)
|
126
|
+
if (happy_emoticon(message) && sad_emoticon(message))
|
127
|
+
"ambiguous"
|
128
|
+
elsif happy_emoticon(message)
|
129
|
+
"joy"
|
130
|
+
elsif sad_emoticon(message)
|
131
|
+
"sadness"
|
132
|
+
else
|
133
|
+
return_emotion_score(emotion_score)
|
134
|
+
end
|
135
|
+
end
|
136
|
+
|
137
|
+
def self.return_emotion_score(emotion_score)
|
138
|
+
## 0 if unable to detect emotion
|
139
|
+
if emotion_score == {}
|
140
|
+
"ambiguous"
|
141
|
+
else
|
142
|
+
emotion_score.max_by{|k, v| v}[0]
|
143
|
+
end
|
144
|
+
end
|
145
|
+
|
146
|
+
def self.check_emoticon_for_polarity(polarity_scores, message)
|
147
|
+
if (happy_emoticon(message) && sad_emoticon(message))
|
148
|
+
score = 5
|
149
|
+
elsif happy_emoticon(message)
|
150
|
+
score = 8
|
151
|
+
elsif sad_emoticon(message)
|
152
|
+
score = 2
|
153
|
+
else
|
154
|
+
return_polarity_scores(polarity_scores)
|
155
|
+
end
|
156
|
+
end
|
157
|
+
|
158
|
+
def self.return_polarity_scores(polarity_scores)
|
159
|
+
if polarity_scores == []
|
160
|
+
# polarity unreadable; return a neutral score of 5
|
161
|
+
5
|
162
|
+
else
|
163
|
+
polarity_scores.inject(0.0){ |sum, el| sum + el}/polarity_scores.length
|
164
|
+
end
|
165
|
+
end
|
166
|
+
|
167
|
+
def self.create_term_frequencies(word_stems, term_frequencies)
|
168
|
+
word_stems.each do |stem|
|
169
|
+
term_frequencies[stem] = word_stems.count(stem)
|
170
|
+
end
|
171
|
+
term_frequencies
|
172
|
+
end
|
173
|
+
|
174
|
+
|
175
|
+
end
|
data/test/helper.rb
ADDED
@@ -0,0 +1,18 @@
|
|
1
|
+
require 'rubygems'
|
2
|
+
require 'bundler'
|
3
|
+
begin
|
4
|
+
Bundler.setup(:default, :development)
|
5
|
+
rescue Bundler::BundlerError => e
|
6
|
+
$stderr.puts e.message
|
7
|
+
$stderr.puts "Run `bundle install` to install missing gems"
|
8
|
+
exit e.status_code
|
9
|
+
end
|
10
|
+
require 'test/unit'
|
11
|
+
require 'shoulda'
|
12
|
+
|
13
|
+
$LOAD_PATH.unshift(File.join(File.dirname(__FILE__), '..', 'lib'))
|
14
|
+
$LOAD_PATH.unshift(File.dirname(__FILE__))
|
15
|
+
require 'chime'
|
16
|
+
|
17
|
+
class Test::Unit::TestCase
|
18
|
+
end
|
data/test/test_chime.rb
ADDED
metadata
ADDED
@@ -0,0 +1,134 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: chime
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.1.0
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- jonathanamccann
|
8
|
+
autorequire:
|
9
|
+
bindir: bin
|
10
|
+
cert_chain: []
|
11
|
+
date: 2013-10-15 00:00:00.000000000 Z
|
12
|
+
dependencies:
|
13
|
+
- !ruby/object:Gem::Dependency
|
14
|
+
name: shoulda
|
15
|
+
requirement: !ruby/object:Gem::Requirement
|
16
|
+
requirements:
|
17
|
+
- - ! '>='
|
18
|
+
- !ruby/object:Gem::Version
|
19
|
+
version: '0'
|
20
|
+
type: :development
|
21
|
+
prerelease: false
|
22
|
+
version_requirements: !ruby/object:Gem::Requirement
|
23
|
+
requirements:
|
24
|
+
- - ! '>='
|
25
|
+
- !ruby/object:Gem::Version
|
26
|
+
version: '0'
|
27
|
+
- !ruby/object:Gem::Dependency
|
28
|
+
name: rdoc
|
29
|
+
requirement: !ruby/object:Gem::Requirement
|
30
|
+
requirements:
|
31
|
+
- - ~>
|
32
|
+
- !ruby/object:Gem::Version
|
33
|
+
version: '3.12'
|
34
|
+
type: :development
|
35
|
+
prerelease: false
|
36
|
+
version_requirements: !ruby/object:Gem::Requirement
|
37
|
+
requirements:
|
38
|
+
- - ~>
|
39
|
+
- !ruby/object:Gem::Version
|
40
|
+
version: '3.12'
|
41
|
+
- !ruby/object:Gem::Dependency
|
42
|
+
name: bundler
|
43
|
+
requirement: !ruby/object:Gem::Requirement
|
44
|
+
requirements:
|
45
|
+
- - ~>
|
46
|
+
- !ruby/object:Gem::Version
|
47
|
+
version: '1.0'
|
48
|
+
type: :development
|
49
|
+
prerelease: false
|
50
|
+
version_requirements: !ruby/object:Gem::Requirement
|
51
|
+
requirements:
|
52
|
+
- - ~>
|
53
|
+
- !ruby/object:Gem::Version
|
54
|
+
version: '1.0'
|
55
|
+
- !ruby/object:Gem::Dependency
|
56
|
+
name: jeweler
|
57
|
+
requirement: !ruby/object:Gem::Requirement
|
58
|
+
requirements:
|
59
|
+
- - ~>
|
60
|
+
- !ruby/object:Gem::Version
|
61
|
+
version: 1.8.7
|
62
|
+
type: :development
|
63
|
+
prerelease: false
|
64
|
+
version_requirements: !ruby/object:Gem::Requirement
|
65
|
+
requirements:
|
66
|
+
- - ~>
|
67
|
+
- !ruby/object:Gem::Version
|
68
|
+
version: 1.8.7
|
69
|
+
- !ruby/object:Gem::Dependency
|
70
|
+
name: rcov
|
71
|
+
requirement: !ruby/object:Gem::Requirement
|
72
|
+
requirements:
|
73
|
+
- - '='
|
74
|
+
- !ruby/object:Gem::Version
|
75
|
+
version: 0.9.11
|
76
|
+
type: :development
|
77
|
+
prerelease: false
|
78
|
+
version_requirements: !ruby/object:Gem::Requirement
|
79
|
+
requirements:
|
80
|
+
- - '='
|
81
|
+
- !ruby/object:Gem::Version
|
82
|
+
version: 0.9.11
|
83
|
+
description: Text Analysis for Member Based Organizations
|
84
|
+
email: jonathanamccann@gmail.com
|
85
|
+
executables: []
|
86
|
+
extensions: []
|
87
|
+
extra_rdoc_files:
|
88
|
+
- LICENSE.txt
|
89
|
+
- README.md
|
90
|
+
- README.rdoc
|
91
|
+
files:
|
92
|
+
- .document
|
93
|
+
- Gemfile
|
94
|
+
- Gemfile.lock
|
95
|
+
- LICENSE.txt
|
96
|
+
- README.md
|
97
|
+
- README.rdoc
|
98
|
+
- Rakefile
|
99
|
+
- VERSION
|
100
|
+
- chime.gemspec
|
101
|
+
- lib/chime.rb
|
102
|
+
- lib/chime/emotions/emotion_bank.rb
|
103
|
+
- lib/chime/emotions/emotions.csv
|
104
|
+
- lib/chime/emotions/stopwords.rb
|
105
|
+
- lib/chime/emotions/subjectivity.csv
|
106
|
+
- lib/chime/emotions/term_polarities.rb
|
107
|
+
- lib/chime/version.rb
|
108
|
+
- test/helper.rb
|
109
|
+
- test/test_chime.rb
|
110
|
+
homepage: http://github.com/jonathanamccann/chime
|
111
|
+
licenses:
|
112
|
+
- MIT
|
113
|
+
metadata: {}
|
114
|
+
post_install_message:
|
115
|
+
rdoc_options: []
|
116
|
+
require_paths:
|
117
|
+
- lib
|
118
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
119
|
+
requirements:
|
120
|
+
- - ! '>='
|
121
|
+
- !ruby/object:Gem::Version
|
122
|
+
version: '0'
|
123
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
124
|
+
requirements:
|
125
|
+
- - ! '>='
|
126
|
+
- !ruby/object:Gem::Version
|
127
|
+
version: '0'
|
128
|
+
requirements: []
|
129
|
+
rubyforge_project:
|
130
|
+
rubygems_version: 2.0.5
|
131
|
+
signing_key:
|
132
|
+
specification_version: 4
|
133
|
+
summary: Text Analysis for Member Based Organizations
|
134
|
+
test_files: []
|