SENTIMENT ANALYSIS

(via these docs) | 10-06-19

STEP 1: Import ALL the things

In [1]:
from nltk.classify import NaiveBayesClassifier
from nltk.corpus import subjectivity
from nltk.sentiment import SentimentAnalyzer
from nltk.sentiment.util import *

STEP 2: Borrow subjective and objective sentences from the nltk for practice

In [2]:
n_instances = 100
subj_docs = [(sent, 'subj') for sent in subjectivity.sents(categories='subj')[:n_instances]]
obj_docs = [(sent, 'obj') for sent in subjectivity.sents(categories='obj')[:n_instances]]

STEP 3: Create test and train for both subj and obj

In [3]:
train_subj_docs = subj_docs[:80]
test_subj_docs = subj_docs[80:100]
train_obj_docs = obj_docs[:80]
test_obj_docs = obj_docs[80:100]

STEP 4: Combine the two test and train sets

In [4]:
training_docs = train_subj_docs + train_obj_docs
testing_docs = test_subj_docs + test_obj_docs
# training_docs

STEP 5: Use SentimentAnalyzer to mark negation in training docs

In [5]:
sentim_analyzer = SentimentAnalyzer()
# WTF IS MARK_NEGATION
all_words_neg = sentim_analyzer.all_words([mark_negation(doc) for doc in training_docs])
In [6]:
training_docs
Out[6]:
[(['smart',
   'and',
   'alert',
   ',',
   'thirteen',
   'conversations',
   'about',
   'one',
   'thing',
   'is',
   'a',
   'small',
   'gem',
   '.'],
  'subj'),
 (['color',
   ',',
   'musical',
   'bounce',
   'and',
   'warm',
   'seas',
   'lapping',
   'on',
   'island',
   'shores',
   '.',
   'and',
   'just',
   'enough',
   'science',
   'to',
   'send',
   'you',
   'home',
   'thinking',
   '.'],
  'subj'),
 (['it',
   'is',
   'not',
   'a',
   'mass-market',
   'entertainment',
   'but',
   'an',
   'uncompromising',
   'attempt',
   'by',
   'one',
   'artist',
   'to',
   'think',
   'about',
   'another',
   '.'],
  'subj'),
 (['a',
   'light-hearted',
   'french',
   'film',
   'about',
   'the',
   'spiritual',
   'quest',
   'of',
   'a',
   'fashion',
   'model',
   'seeking',
   'peace',
   'of',
   'mind',
   'while',
   'in',
   'a',
   'love',
   'affair',
   'with',
   'a',
   'veterinarian',
   'who',
   'is',
   'a',
   'non-practicing',
   'jew',
   '.'],
  'subj'),
 (['my',
   'wife',
   'is',
   'an',
   'actress',
   'has',
   'its',
   'moments',
   'in',
   'looking',
   'at',
   'the',
   'comic',
   'effects',
   'of',
   'jealousy',
   '.',
   'in',
   'the',
   'end',
   ',',
   'though',
   ',',
   'it',
   'is',
   'only',
   'mildly',
   'amusing',
   'when',
   'it',
   'could',
   'have',
   'been',
   'so',
   'much',
   'more',
   '.'],
  'subj'),
 (['works',
   'both',
   'as',
   'an',
   'engaging',
   'drama',
   'and',
   'an',
   'incisive',
   'look',
   'at',
   'the',
   'difficulties',
   'facing',
   'native',
   'americans',
   '.'],
  'subj'),
 (['even',
   'a',
   'hardened',
   'voyeur',
   'would',
   'require',
   'the',
   'patience',
   'of',
   'job',
   'to',
   'get',
   'through',
   'this',
   'interminable',
   ',',
   'shapeless',
   'documentary',
   'about',
   'the',
   'swinging',
   'subculture',
   '.'],
  'subj'),
 (['when',
   'perry',
   'fists',
   'a',
   'bull',
   'at',
   'the',
   'moore',
   'farm',
   ',',
   "it's",
   'only',
   'a',
   'matter',
   'of',
   'time',
   'before',
   'he',
   'gets',
   'the',
   'upper',
   'hand',
   'in',
   'matters',
   'of',
   'the',
   'heart',
   '.'],
  'subj'),
 (['the',
   'characters',
   '.',
   '.',
   '.',
   'are',
   'paper-thin',
   ',',
   'and',
   'their',
   'personalities',
   'undergo',
   'radical',
   'changes',
   'when',
   'it',
   'suits',
   'the',
   'script',
   '.'],
  'subj'),
 (['the',
   'script',
   'is',
   'a',
   'tired',
   'one',
   ',',
   'with',
   'few',
   'moments',
   'of',
   'joy',
   'rising',
   'above',
   'the',
   'stale',
   'material',
   '.'],
  'subj'),
 (['the',
   'bland',
   'outweighs',
   'the',
   'nifty',
   ',',
   'and',
   'cletis',
   'tout',
   'never',
   'becomes',
   'the',
   'clever',
   'crime',
   'comedy',
   'it',
   'thinks',
   'it',
   'is',
   '.'],
  'subj'),
 (['directed',
   'by',
   'david',
   'twohy',
   'with',
   'the',
   'same',
   'great',
   'eye',
   'for',
   'eerie',
   'understatement',
   'that',
   'he',
   'brought',
   'to',
   'pitch',
   'black',
   '.'],
  'subj'),
 (["it's",
   'a',
   'very',
   'tasteful',
   'rock',
   'and',
   'roll',
   'movie',
   '.',
   'you',
   'could',
   'put',
   'it',
   'on',
   'a',
   'coffee',
   'table',
   'anywhere',
   '.'],
  'subj'),
 (['provides',
   'the',
   'kind',
   'of',
   "'laugh",
   "therapy'",
   'i',
   'need',
   'from',
   'movie',
   'comedies',
   '--',
   'offbeat',
   'humor',
   ',',
   'amusing',
   'characters',
   ',',
   'and',
   'a',
   'happy',
   'ending',
   '.',
   'after',
   'seeing',
   "'analyze",
   'that',
   ',',
   "'",
   'i',
   'feel',
   'better',
   'already',
   '.'],
  'subj'),
 (['worth',
   'a',
   'look',
   'by',
   'those',
   'on',
   'both',
   'sides',
   'of',
   'the',
   'issues',
   ',',
   'if',
   'only',
   'for',
   'the',
   'perspective',
   'it',
   'offers',
   ',',
   'one',
   'the',
   'public',
   'rarely',
   'sees',
   '.'],
  'subj'),
 (['watching',
   'the',
   'film',
   'is',
   'like',
   'reading',
   'a',
   'times',
   'portrait',
   'of',
   'grief',
   'that',
   'keeps',
   'shifting',
   'focus',
   'to',
   'the',
   'journalist',
   'who',
   'wrote',
   'it',
   '.'],
  'subj'),
 (['despite',
   'these',
   'annoyances',
   ',',
   'the',
   'capable',
   'clayburgh',
   'and',
   'tambor',
   'really',
   'do',
   'a',
   'great',
   'job',
   'of',
   'anchoring',
   'the',
   'characters',
   'in',
   'the',
   'emotional',
   'realities',
   'of',
   'middle',
   'age',
   '.'],
  'subj'),
 (["it's",
   'a',
   'good',
   'thing',
   'that',
   'woolly',
   'mammoths',
   'are',
   'extinct',
   ',',
   'because',
   'this',
   'movie',
   'will',
   'have',
   'every',
   'kid',
   'in',
   'the',
   'schoolyard',
   'wishing',
   'for',
   'their',
   'very',
   'own',
   '.'],
  'subj'),
 (['preposterous',
   'and',
   'tedious',
   ',',
   'sonny',
   'is',
   'spiked',
   'with',
   'unintentional',
   'laughter',
   'that',
   ',',
   'unfortunately',
   ',',
   'occurs',
   'too',
   'infrequently',
   'to',
   'make',
   'the',
   'film',
   'even',
   'a',
   'guilty',
   'pleasure',
   '.'],
  'subj'),
 (['4ever',
   'has',
   'the',
   'same',
   'sledgehammer',
   'appeal',
   'as',
   'pokemon',
   'videos',
   ',',
   'but',
   'it',
   'breathes',
   'more',
   'on',
   'the',
   'big',
   'screen',
   'and',
   'induces',
   'headaches',
   'more',
   'slowly',
   '.'],
  'subj'),
 (['si',
   'el',
   'siglo',
   'xxi',
   'necesita',
   'de',
   'héroes',
   ',',
   'el',
   'hombre',
   'araña',
   'parece',
   'haber',
   'llegado',
   'para',
   'quedarse',
   '.'],
  'subj'),
 (["it's",
   'hard',
   'to',
   'tell',
   'with',
   'all',
   'the',
   'crashing',
   'and',
   'banging',
   'where',
   'the',
   'salesmanship',
   'ends',
   'and',
   'the',
   'movie',
   'begins',
   '.'],
  'subj'),
 (['it',
   'desperately',
   'wants',
   'to',
   'be',
   'a',
   'wacky',
   ',',
   'screwball',
   'comedy',
   ',',
   'but',
   'the',
   'most',
   'screwy',
   'thing',
   'here',
   'is',
   'how',
   'so',
   'many',
   'talented',
   'people',
   'were',
   'convinced',
   'to',
   'waste',
   'their',
   'time',
   '.'],
  'subj'),
 (['writer/director',
   'walter',
   'hill',
   'is',
   'in',
   'his',
   'hypermasculine',
   'element',
   'here',
   ',',
   'once',
   'again',
   'able',
   'to',
   'inject',
   'some',
   'real',
   'vitality',
   'and',
   'even',
   'art',
   'into',
   'a',
   'pulpy',
   'concept',
   'that',
   ',',
   'in',
   'many',
   'other',
   'hands',
   'would',
   'be',
   'completely',
   'forgettable',
   '.'],
  'subj'),
 (['hill',
   'looks',
   'to',
   'be',
   'going',
   'through',
   'the',
   'motions',
   ',',
   'beginning',
   'with',
   'the',
   'pale',
   'script',
   '.'],
  'subj'),
 (['extremely',
   'well',
   'cast',
   ',',
   'especially',
   'in',
   'the',
   'large',
   'number',
   'of',
   'supporting',
   'roles',
   '.'],
  'subj'),
 (['a',
   'chilling',
   'tale',
   'of',
   'one',
   'of',
   'the',
   'great',
   'crimes',
   'of',
   '20th',
   'century',
   'france',
   ':',
   'the',
   'murder',
   'of',
   'two',
   'rich',
   'women',
   'by',
   'their',
   'servants',
   'in',
   '1933',
   '.'],
  'subj'),
 (['a',
   'dark',
   ',',
   'quirky',
   'road',
   'movie',
   'that',
   'constantly',
   'defies',
   'expectation',
   '.'],
  'subj'),
 (['impostor',
   "doesn't",
   'do',
   'much',
   'with',
   'its',
   'template',
   ',',
   'despite',
   'a',
   'remarkably',
   'strong',
   'cast',
   '.'],
  'subj'),
 (['though',
   'it',
   'lacks',
   'the',
   'utter',
   'authority',
   'of',
   'a',
   'genre',
   'gem',
   ',',
   "there's",
   'a',
   'certain',
   'robustness',
   'to',
   'this',
   'engaging',
   'mix',
   'of',
   'love',
   'and',
   'bloodletting',
   '.'],
  'subj'),
 (['if',
   'you',
   'can',
   'keep',
   'your',
   'eyes',
   'open',
   'amid',
   'all',
   'the',
   'blood',
   'and',
   'gore',
   ',',
   "you'll",
   'see',
   'del',
   'toro',
   'has',
   'brought',
   'unexpected',
   'gravity',
   'to',
   'blade',
   'ii',
   '.'],
  'subj'),
 (["there's",
   'undeniable',
   'enjoyment',
   'to',
   'be',
   'had',
   'from',
   'films',
   'crammed',
   'with',
   'movie',
   'references',
   ',',
   'but',
   'the',
   'fun',
   'wears',
   'thin',
   '--',
   'then',
   'out',
   '--',
   'when',
   "there's",
   'nothing',
   'else',
   'happening',
   '.'],
  'subj'),
 (['a',
   'work',
   'that',
   'lacks',
   'both',
   'a',
   'purpose',
   'and',
   'a',
   'strong',
   'pulse',
   '.'],
  'subj'),
 (['it',
   'helps',
   'that',
   'lil',
   'bow',
   'wow',
   '.',
   '.',
   '.',
   'tones',
   'down',
   'his',
   'pint-sized',
   'gangsta',
   'act',
   'to',
   'play',
   'someone',
   'who',
   'resembles',
   'a',
   'real',
   'kid',
   '.'],
  'subj'),
 (['a',
   'mimetic',
   'approximation',
   'of',
   'better',
   'films',
   'like',
   'contempt',
   'and',
   '8',
   '1/2',
   '.'],
  'subj'),
 (['eastwood',
   'is',
   'an',
   'icon',
   'of',
   'moviemaking',
   ',',
   'one',
   'of',
   'the',
   'best',
   'actors',
   ',',
   'directors',
   'and',
   'producers',
   'around',
   ',',
   'responsible',
   'for',
   'some',
   'excellent',
   'work',
   '.',
   'but',
   'even',
   'a',
   'hero',
   'can',
   'stumble',
   'sometimes',
   '.'],
  'subj'),
 (['nair',
   "doesn't",
   'use',
   '[monsoon',
   'wedding]',
   'to',
   'lament',
   'the',
   'loss',
   'of',
   'culture',
   '.',
   'instead',
   ',',
   'she',
   'sees',
   'it',
   'as',
   'a',
   'chance',
   'to',
   'revitalize',
   'what',
   'is',
   'and',
   'always',
   'has',
   'been',
   'remarkable',
   'about',
   'clung-to',
   'traditions',
   '.'],
  'subj'),
 (['stuffed',
   'to',
   'the',
   'brim',
   'with',
   'ideas',
   ',',
   'american',
   'instigator',
   'michael',
   "moore's",
   'film',
   'is',
   'a',
   'rambling',
   'examination',
   'of',
   'american',
   'gun',
   'culture',
   'that',
   'uses',
   'his',
   'usual',
   'modus',
   'operandi',
   'of',
   'crucifixion',
   'through',
   'juxtaposition',
   '.'],
  'subj'),
 (['.',
   '.',
   '.',
   'a',
   'joke',
   'at',
   'once',
   'flaky',
   'and',
   'resonant',
   ',',
   'lightweight',
   'and',
   'bizarrely',
   'original',
   '.'],
  'subj'),
 (["fontaine's",
   'direction',
   ',',
   'especially',
   'her',
   'agreeably',
   'startling',
   'use',
   'of',
   'close-ups',
   'and',
   'her',
   'grace',
   'with',
   'a',
   'moving',
   'camera',
   ',',
   'creates',
   'sheerly',
   'cinematic',
   'appeal',
   '.'],
  'subj'),
 (['starts',
   'slowly',
   ',',
   'but',
   'adrien',
   'brody',
   'Â\x96',
   'in',
   'the',
   'title',
   'role',
   'Â\x96',
   'helps',
   'make',
   'the',
   "film's",
   'conclusion',
   'powerful',
   'and',
   'satisfying',
   '.'],
  'subj'),
 (['a',
   'refreshing',
   'change',
   'from',
   'the',
   'usual',
   'whoopee-cushion',
   'effort',
   'aimed',
   'at',
   'the',
   'youth',
   'market',
   '.'],
  'subj'),
 (['you',
   'really',
   'have',
   'to',
   'salute',
   'writer-director',
   'haneke',
   '(',
   'he',
   'adapted',
   'elfriede',
   "jelinek's",
   'novel',
   ')',
   'for',
   'making',
   'a',
   'film',
   'that',
   "isn't",
   'nearly',
   'as',
   'graphic',
   'but',
   'much',
   'more',
   'powerful',
   ',',
   'brutally',
   'shocking',
   'and',
   'difficult',
   'to',
   'watch',
   '.'],
  'subj'),
 (['barry',
   'convinces',
   'us',
   "he's",
   'a',
   'dangerous',
   ',',
   'secretly',
   'unhinged',
   'guy',
   'who',
   'could',
   'easily',
   'have',
   'killed',
   'a',
   'president',
   'because',
   'it',
   'made',
   'him',
   'feel',
   'powerful',
   '.'],
  'subj'),
 (['a',
   'distant',
   ',',
   'even',
   'sterile',
   ',',
   'yet',
   'compulsively',
   'watchable',
   'look',
   'at',
   'the',
   'sordid',
   'life',
   'of',
   "hogan's",
   'heroes',
   'star',
   'bob',
   'crane',
   '.'],
  'subj'),
 (["there's",
   'no',
   'disguising',
   'this',
   'as',
   'one',
   'of',
   'the',
   'worst',
   'films',
   'of',
   'the',
   'summer',
   '.',
   'or',
   'for',
   'the',
   'year',
   ',',
   'for',
   'that',
   'matter',
   '.'],
  'subj'),
 (['director',
   'dan',
   'verete',
   'uses',
   'his',
   'camera',
   'as',
   'the',
   'metaphoric',
   'needle',
   ',',
   'and',
   'his',
   'cast',
   'in',
   'each',
   'segment',
   'as',
   'his',
   'thread',
   ',',
   'to',
   'form',
   'a',
   'sweeping',
   'tapestry',
   'of',
   'mis-explanation',
   'and',
   'contention',
   '.'],
  'subj'),
 (['waydowntown',
   'just',
   'like',
   'most',
   'large',
   'cities',
   ',',
   "isn't",
   'somewhere',
   "you'll",
   'want',
   'to',
   'spend',
   'the',
   'rest',
   'of',
   'your',
   'life',
   ',',
   'but',
   'it',
   'sure',
   'is',
   'a',
   'fun',
   'place',
   'to',
   'visit',
   'for',
   'a',
   'while',
   '.'],
  'subj'),
 (['the',
   'acting',
   'in',
   'pauline',
   'and',
   'paulette',
   'is',
   'good',
   'all',
   'round',
   ',',
   'but',
   'what',
   'really',
   'sets',
   'the',
   'film',
   'apart',
   'is',
   "debrauwer's",
   'refusal',
   'to',
   'push',
   'the',
   'easy',
   'emotional',
   'buttons',
   '.'],
  'subj'),
 (['the',
   'only',
   'young',
   'people',
   'who',
   'possibly',
   'will',
   'enjoy',
   'it',
   'are',
   'infants',
   '.',
   '.',
   '.',
   'who',
   'might',
   'be',
   'distracted',
   'by',
   'the',
   "movie's",
   'quick',
   'movements',
   'and',
   'sounds',
   '.'],
  'subj'),
 (["there's",
   'lots',
   'of',
   'cool',
   'stuff',
   'packed',
   'into',
   "espn's",
   'ultimate',
   'x',
   '.'],
  'subj'),
 (['it',
   'gets',
   'old',
   'quickly',
   '.',
   'watch',
   'barbershop',
   'again',
   'if',
   "you're",
   'in',
   'need',
   'of',
   'a',
   'cube',
   'fix--this',
   "isn't",
   'worth',
   'sitting',
   'through',
   '.'],
  'subj'),
 (['harland',
   'williams',
   'is',
   'so',
   'funny',
   'in',
   'drag',
   'he',
   'should',
   'consider',
   'permanent',
   'sex-reassignment',
   '.'],
  'subj'),
 (['the',
   "film's",
   'images',
   'give',
   'a',
   'backbone',
   'to',
   'the',
   'company',
   'and',
   'provide',
   'an',
   'emotional',
   'edge',
   'to',
   'its',
   'ultimate',
   'demise',
   '.'],
  'subj'),
 (["it's",
   'the',
   'kind',
   'of',
   'film',
   'where',
   'the',
   'villain',
   'even',
   'gives',
   'an',
   'evil',
   'look',
   'for',
   'his',
   'passport',
   'photo',
   '.',
   'how',
   'can',
   'you',
   'resist',
   'that',
   '?'],
  'subj'),
 (['plotless',
   'collection',
   'of',
   'moronic',
   'stunts',
   'is',
   'by',
   'far',
   'the',
   'worst',
   'movie',
   'of',
   'the',
   'year',
   '.'],
  'subj'),
 (['a',
   'broad',
   ',',
   'melodramatic',
   'estrogen',
   'opera',
   "that's",
   'pretty',
   'toxic',
   'in',
   'its',
   'own',
   'right',
   '.'],
  'subj'),
 (['just',
   'a',
   'kiss',
   'wants',
   'desperately',
   'to',
   'come',
   'off',
   'as',
   'a',
   'fanciful',
   'film',
   'about',
   'the',
   'typical',
   'problems',
   'of',
   'average',
   'people',
   '.',
   'but',
   'it',
   'is',
   'set',
   'in',
   'a',
   'world',
   'that',
   'is',
   'very',
   ',',
   'very',
   'far',
   'from',
   'the',
   'one',
   'most',
   'of',
   'us',
   'inhabit',
   '.'],
  'subj'),
 (['this',
   'is',
   'a',
   'movie',
   'where',
   'the',
   'most',
   'notable',
   'observation',
   'is',
   'how',
   'long',
   "you've",
   'been',
   'sitting',
   'still',
   '.'],
  'subj'),
 (['with',
   'a',
   'romantic',
   'comedy',
   'plotline',
   'straight',
   'from',
   'the',
   'ages',
   ',',
   'this',
   'cinderella',
   'story',
   "doesn't",
   'have',
   'a',
   'single',
   'surprise',
   'up',
   'its',
   'sleeve',
   '.',
   'but',
   'it',
   'does',
   'somehow',
   'manage',
   'to',
   'get',
   'you',
   'under',
   'its',
   'spell',
   '.'],
  'subj'),
 (['a',
   'charming',
   'trifle',
   '.',
   '.',
   '.',
   'a',
   'welcome',
   'return',
   'to',
   'jocular',
   'form',
   '.'],
  'subj'),
 (["it's",
   'not',
   'difficult',
   'to',
   'spot',
   'the',
   'culprit',
   'early-on',
   'in',
   'this',
   'predictable',
   'thriller',
   '.'],
  'subj'),
 (['without',
   'the',
   'dark',
   'spookiness',
   'of',
   'crystal',
   'lake',
   'camp',
   ',',
   'the',
   'horror',
   'concept',
   'completely',
   'loses',
   'its',
   'creepy',
   'menace',
   '.'],
  'subj'),
 (["there's",
   'suspension',
   'of',
   'disbelief',
   'and',
   'then',
   "there's",
   'bad',
   'screenwriting',
   '.',
   '.',
   '.',
   'this',
   'film',
   'packs',
   'a',
   'wallop',
   'of',
   'the',
   'latter',
   '.'],
  'subj'),
 (['little',
   'more',
   'than',
   'a',
   'stylish',
   'exercise',
   'in',
   'revisionism',
   'whose',
   'point',
   '.',
   '.',
   '.',
   'is',
   'no',
   'doubt',
   'true',
   ',',
   'but',
   'serves',
   'as',
   'a',
   'rather',
   'thin',
   'moral',
   'to',
   'such',
   'a',
   'knowing',
   'fable',
   '.'],
  'subj'),
 (['anyone',
   'who',
   'can',
   'count',
   'to',
   'five',
   '(',
   'the',
   "film's",
   'target',
   'market',
   '?',
   ')',
   'can',
   'see',
   'where',
   'this',
   'dumbed-down',
   'concoction',
   'is',
   'going',
   '.'],
  'subj'),
 (['every',
   'defiantly',
   'over-the-top',
   'action',
   'scene',
   '--',
   'from',
   'high-stakes',
   'car',
   'chases',
   'to',
   'fearsome',
   'drug',
   'busts',
   '--',
   'seizes',
   'your',
   'adrenal',
   'gland',
   'and',
   'milks',
   'it',
   'like',
   'an',
   'epileptic',
   'farmer',
   '.'],
  'subj'),
 (['kosminsky',
   '.',
   '.',
   '.',
   'puts',
   'enough',
   'salt',
   'into',
   'the',
   'wounds',
   'of',
   'the',
   'tortured',
   'and',
   'self-conscious',
   'material',
   'to',
   'make',
   'it',
   'sting',
   '.'],
  'subj'),
 (['a',
   'sobering',
   'and',
   'powerful',
   'documentary',
   'about',
   'the',
   'most',
   'severe',
   'kind',
   'of',
   'personal',
   'loss',
   ':',
   'rejection',
   'by',
   "one's",
   'mother',
   '.'],
  'subj'),
 (['if',
   'the',
   'story',
   'lacks',
   'bite',
   ',',
   'the',
   'performances',
   'are',
   'never',
   'less',
   'than',
   'affectionate',
   '.'],
  'subj'),
 (['a',
   'deftly',
   'entertaining',
   'film',
   ',',
   'smartly',
   'played',
   'and',
   'smartly',
   'directed',
   '.'],
  'subj'),
 (['ice',
   'age',
   'is',
   'the',
   'first',
   'computer-generated',
   'feature',
   'cartoon',
   'to',
   'feel',
   'like',
   'other',
   'movies',
   ',',
   'and',
   'that',
   'makes',
   'for',
   'some',
   'glacial',
   'pacing',
   'early',
   'on',
   '.'],
  'subj'),
 (['i',
   'like',
   'my',
   'christmas',
   'movies',
   'with',
   'more',
   'elves',
   'and',
   'snow',
   'and',
   'less',
   'pimps',
   'and',
   "ho's",
   '.'],
  'subj'),
 (["ferrara's",
   'strongest',
   'and',
   'most',
   'touching',
   'movie',
   'of',
   'recent',
   'years',
   '.'],
  'subj'),
 (['skip',
   'work',
   'to',
   'see',
   'it',
   'at',
   'the',
   'first',
   'opportunity',
   '.'],
  'subj'),
 (['both',
   'the',
   'film',
   'and',
   "nachtwey's",
   'photos',
   'hammer',
   'home',
   'the',
   'grim',
   'reality',
   'of',
   'the',
   "world's",
   'gutters',
   'and',
   'battlefields',
   ',',
   'and',
   'will',
   'make',
   'you',
   'question',
   'what',
   "'news'",
   'really',
   'is',
   '.'],
  'subj'),
 (['so',
   'relentlessly',
   'wholesome',
   'it',
   'made',
   'me',
   'want',
   'to',
   'swipe',
   'something',
   '.'],
  'subj'),
 (['shyamalan',
   'offers',
   'copious',
   'hints',
   'along',
   'the',
   'way',
   '--',
   'myriad',
   'signs',
   ',',
   'if',
   'you',
   'will',
   '--',
   'that',
   'beneath',
   'the',
   'familiar',
   ',',
   'funny',
   'surface',
   'is',
   'a',
   'far',
   'bigger',
   ',',
   'far',
   'more',
   'meaningful',
   'story',
   'than',
   'one',
   'in',
   'which',
   'little',
   'green',
   'men',
   'come',
   'to',
   'earth',
   'for',
   'harvesting',
   'purposes',
   '.'],
  'subj'),
 (['that',
   "'alabama'",
   'manages',
   'to',
   'be',
   'pleasant',
   'in',
   'spite',
   'of',
   'its',
   'predictability',
   'and',
   'occasional',
   'slowness',
   'is',
   'due',
   'primarily',
   'to',
   'the',
   'perkiness',
   'of',
   'witherspoon',
   '(',
   'who',
   'is',
   'always',
   'a',
   'joy',
   'to',
   'watch',
   ',',
   'even',
   'when',
   'her',
   'material',
   'is',
   'not',
   'first-rate',
   ')',
   '.',
   '.',
   '.'],
  'subj'),
 (['against',
   'all',
   'odds',
   'in',
   'heaven',
   'and',
   'hell',
   ',',
   'it',
   'creeped',
   'me',
   'out',
   'just',
   'fine',
   '.'],
  'subj'),
 (['the',
   'movie',
   'begins',
   'in',
   'the',
   'past',
   'where',
   'a',
   'young',
   'boy',
   'named',
   'sam',
   'attempts',
   'to',
   'save',
   'celebi',
   'from',
   'a',
   'hunter',
   '.'],
  'obj'),
 (['emerging',
   'from',
   'the',
   'human',
   'psyche',
   'and',
   'showing',
   'characteristics',
   'of',
   'abstract',
   'expressionism',
   ',',
   'minimalism',
   'and',
   'russian',
   'constructivism',
   ',',
   'graffiti',
   'removal',
   'has',
   'secured',
   'its',
   'place',
   'in',
   'the',
   'history',
   'of',
   'modern',
   'art',
   'while',
   'being',
   'created',
   'by',
   'artists',
   'who',
   'are',
   'unconscious',
   'of',
   'their',
   'artistic',
   'achievements',
   '.'],
  'obj'),
 (['spurning',
   'her',
   "mother's",
   'insistence',
   'that',
   'she',
   'get',
   'on',
   'with',
   'her',
   'life',
   ',',
   'mary',
   'is',
   'thrown',
   'out',
   'of',
   'the',
   'house',
   ',',
   'rejected',
   'by',
   'joe',
   ',',
   'and',
   'expelled',
   'from',
   'school',
   'as',
   'she',
   'grows',
   'larger',
   'with',
   'child',
   '.'],
  'obj'),
 (['amitabh',
   "can't",
   'believe',
   'the',
   'board',
   'of',
   'directors',
   'and',
   'his',
   'mind',
   'is',
   'filled',
   'with',
   'revenge',
   'and',
   'what',
   'better',
   'revenge',
   'than',
   'robbing',
   'the',
   'bank',
   'himself',
   ',',
   'ironic',
   'as',
   'it',
   'may',
   'sound',
   '.'],
  'obj'),
 (['she',
   ',',
   'among',
   'others',
   'excentricities',
   ',',
   'talks',
   'to',
   'a',
   'small',
   'rock',
   ',',
   'gertrude',
   ',',
   'like',
   'if',
   'she',
   'was',
   'alive',
   '.'],
  'obj'),
 (['this',
   'gives',
   'the',
   'girls',
   'a',
   'fair',
   'chance',
   'of',
   'pulling',
   'the',
   'wool',
   'over',
   'their',
   'eyes',
   'using',
   'their',
   'sexiness',
   'to',
   'poach',
   'any',
   'last',
   'vestige',
   'of',
   'common',
   'sense',
   'the',
   'dons',
   'might',
   'have',
   'had',
   '.'],
  'obj'),
 (['styled',
   'after',
   "vh1's",
   '"',
   'behind',
   'the',
   'music',
   ',',
   '"',
   'this',
   'mockumentary',
   'profiles',
   'the',
   'rise',
   'and',
   'fall',
   'of',
   'an',
   'internet',
   'startup',
   ',',
   'called',
   'icevan',
   '.',
   'com',
   '.'],
  'obj'),
 (['being',
   'blue',
   'is',
   'not',
   'his',
   'only',
   'predicament',
   ';',
   'he',
   'also',
   'lacks',
   'the',
   'ability',
   'to',
   'outwardly',
   'express',
   'his',
   'emotions',
   '.'],
  'obj'),
 (['the',
   "killer's",
   'clues',
   'are',
   'a',
   'perversion',
   'of',
   'biblical',
   'punishments',
   'for',
   'sins',
   ':',
   'stoning',
   ',',
   'burning',
   ',',
   'decapitation',
   '.'],
  'obj'),
 (['david',
   'is',
   'a',
   'painter',
   'with',
   "painter's",
   'block',
   'who',
   'takes',
   'a',
   'job',
   'as',
   'a',
   'waiter',
   'to',
   'get',
   'some',
   'inspiration',
   '.'],
  'obj'),
 (['women', 'craved', 'him', 'and', 'men', 'wanted', 'to', 'be', 'him', '.'],
  'obj'),
 (['set',
   'on',
   'an',
   'island',
   'off',
   'the',
   'coast',
   'of',
   'florida',
   ',',
   'a',
   'techno',
   'rave',
   'party',
   'attracts',
   'a',
   'diverse',
   'group',
   'of',
   'college',
   'coeds',
   'and',
   'a',
   'coast',
   'guard',
   'officer',
   '.'],
  'obj'),
 (['lesson',
   'to',
   'be',
   'learned',
   ':',
   'never',
   ',',
   'never',
   'mess',
   'with',
   '"',
   'the',
   'gay',
   'mafia',
   '!',
   '"'],
  'obj'),
 (['the',
   'theme',
   'of',
   'the',
   'film',
   'simultaneously',
   'addresses',
   'the',
   'similarities',
   'between',
   'the',
   'two',
   'factions',
   'of',
   'law',
   'and',
   'crime',
   'while',
   'revealing',
   'the',
   'similarities',
   'between',
   'the',
   'two',
   'brothers',
   '.'],
  'obj'),
 (["they're",
   'jewish',
   ',',
   "they're",
   'grandmothers',
   ',',
   'and',
   "they're",
   'lesbians',
   '.'],
  'obj'),
 (['but',
   "he's",
   'neglecting',
   'his',
   'work',
   ',',
   'carping',
   'at',
   'his',
   'mom',
   ',',
   'and',
   'behaving',
   'badly',
   'toward',
   'his',
   'loyal',
   'friend',
   'bobbi',
   '.'],
  'obj'),
 (['with',
   'all',
   'this',
   'going',
   'on',
   ',',
   "gerry's",
   'estranged',
   'wife',
   'margaret',
   'is',
   'worried',
   'for',
   'her',
   "daughter's",
   'safety',
   'and',
   'finds',
   'herself',
   'another',
   'target',
   'in',
   'the',
   'race',
   'to',
   'find',
   'the',
   'code',
   '.'],
  'obj'),
 (['valento',
   'feels',
   'the',
   'heat',
   'and',
   'turns',
   'the',
   'table',
   ':',
   'he',
   'makes',
   'the',
   'dupe',
   'into',
   'one',
   'of',
   'his',
   'own',
   'and',
   'rubs',
   'the',
   "da's",
   'nose',
   'in',
   'it',
   '.'],
  'obj'),
 (['saigon',
   ',',
   '1952',
   ',',
   'a',
   'beautiful',
   ',',
   'exotic',
   ',',
   'and',
   'mysterious',
   'city',
   'caught',
   'in',
   'the',
   'grips',
   'of',
   'the',
   'vietnamese',
   'war',
   'of',
   'liberation',
   'from',
   'the',
   'french',
   'colonial',
   'powers',
   '.'],
  'obj'),
 (['deep',
   'in',
   'the',
   'northwest',
   ',',
   'there',
   'is',
   'a',
   'lone',
   'ranch',
   'tucked',
   'away',
   'so',
   'purposefully',
   ',',
   'the',
   'only',
   'way',
   'to',
   'find',
   'it',
   'is',
   'by',
   'not',
   'looking',
   '.'],
  'obj'),
 (['as',
   'a',
   'young',
   'teenager',
   ',',
   'he',
   'finds',
   'out',
   'who',
   'his',
   'father',
   'is',
   '.'],
  'obj'),
 (['in',
   'life',
   ',',
   "there's",
   'silver',
   ',',
   'and',
   "there's",
   'lead',
   ',',
   'says',
   'rikki',
   'ortega',
   ',',
   'as',
   'he',
   'moves',
   'to',
   'be',
   'king',
   'of',
   'the',
   'street',
   'in',
   '"',
   '&#193',
   ';',
   'nglio',
   ',',
   '"',
   'l',
   '.',
   'a',
   '.',
   "'s",
   'east',
   'side',
   '.'],
  'obj'),
 (['all',
   'these',
   'games',
   'of',
   'chasing',
   ',',
   'rejecting',
   'and',
   'seducing',
   'are',
   'played',
   'out',
   'in',
   'an',
   'economically',
   'and',
   'spiritually',
   'depressed',
   'hong',
   'kong',
   ',',
   'without',
   'much',
   'gusto',
   '.'],
  'obj'),
 (['television',
   'made',
   'him',
   'famous',
   ',',
   'but',
   'his',
   'biggest',
   'hits',
   'happened',
   'off',
   'screen',
   '.'],
  'obj'),
 (['jordan',
   'is',
   'a',
   'mom',
   'who',
   'is',
   'on',
   'a',
   'life',
   'long',
   'search',
   'for',
   'true',
   'faith',
   'as',
   'she',
   'tries',
   'to',
   'protect',
   'her',
   'only',
   'child',
   'from',
   'what',
   'she',
   'believes',
   'is',
   'injustice',
   '.'],
  'obj'),
 (["'bloody",
   "magic'",
   'is',
   'the',
   'story',
   'of',
   'zack',
   ',',
   'an',
   'eleven',
   'year',
   'old',
   'school',
   'boy',
   ',',
   "who's",
   'family',
   'is',
   'visited',
   'by',
   'three',
   'debt',
   'collectors',
   '.'],
  'obj'),
 (['however',
   ',',
   'jane',
   ',',
   "wendy's",
   '12-year-old',
   'daughter',
   ',',
   'sees',
   'it',
   'all',
   'as',
   'make',
   'believe',
   'and',
   'refuses',
   'to',
   'believe',
   'in',
   'the',
   'tales',
   '.'],
  'obj'),
 (['called',
   '"',
   'an',
   'elegant',
   'documentary',
   '"',
   'by',
   'sundance',
   'and',
   '"',
   'eloquent',
   'and',
   'deeply',
   'moving',
   '"',
   'by',
   'the',
   'la',
   'times',
   ',',
   'toyo',
   'miyatake',
   ':',
   'infinite',
   'shades',
   'of',
   'gray',
   'is',
   'a',
   'penetrating',
   'portrait',
   'of',
   'this',
   "photographer's",
   'search',
   'for',
   'truth',
   'and',
   'beauty',
   'in',
   'a',
   'world',
   'of',
   'impermanence',
   '.'],
  'obj'),
 (['straight',
   'up',
   ':',
   'helicopters',
   'in',
   'action',
   'will',
   'take',
   'audiences',
   'on',
   'a',
   'series',
   'of',
   'aerial',
   'adventures',
   '.'],
  'obj'),
 (['a',
   'lapp',
   'woman',
   'anni',
   'gives',
   'a',
   'shelter',
   'to',
   'both',
   'of',
   'them',
   'at',
   'her',
   'farm',
   '.'],
  'obj'),
 (['it',
   'also',
   'touches',
   'on',
   'the',
   'encroachment',
   'of',
   'christianity',
   'brought',
   'by',
   'the',
   'missionaries',
   ',',
   'which',
   'is',
   'at',
   'odds',
   'with',
   "mepe's",
   'tribal',
   'and',
   'traditional',
   'roots',
   '.'],
  'obj'),
 (['a',
   'set',
   'of',
   'grisly',
   'murders',
   'brings',
   'fbi',
   'agent',
   'will',
   'graham',
   '(',
   'norton',
   ')',
   'out',
   'of',
   'retirement',
   'and',
   'puts',
   'him',
   'in',
   'search',
   'of',
   'an',
   'atrocious',
   'killer',
   '(',
   'fiennes',
   ')',
   "who's",
   'driven',
   'by',
   'the',
   'image',
   'of',
   'a',
   'painting',
   '.'],
  'obj'),
 (['soon',
   ',',
   'the',
   'team',
   'begins',
   'to',
   'suspect',
   'that',
   "knowles'",
   'main',
   'objective',
   'is',
   'actually',
   'to',
   'recover',
   'the',
   'prototype',
   'of',
   'a',
   'dna',
   'testing',
   'machine',
   'called',
   'the',
   'huxley',
   'project',
   ',',
   'which',
   'his',
   'company',
   'has',
   'spent',
   'years',
   'and',
   'millions',
   'of',
   'dollars',
   'developing',
   '.'],
  'obj'),
 (['his',
   'mother',
   'persuades',
   'a',
   'renowned',
   'entomologist',
   'to',
   'take',
   'them',
   'on',
   'a',
   'trip',
   'to',
   'the',
   'jungle',
   'to',
   'search',
   'for',
   'the',
   'butterfly',
   ',',
   'leading',
   'to',
   'an',
   'adventure',
   'that',
   'will',
   'transform',
   'their',
   'lives',
   '.'],
  'obj'),
 (['with',
   'a',
   'rare',
   'gift',
   'for',
   'melding',
   'subjectivity',
   'with',
   'biographical',
   'facts',
   ',',
   'm&#225',
   ';',
   'rton',
   'brings',
   'sabina',
   'spielrein',
   'back',
   'to',
   'life',
   ',',
   'body',
   'and',
   'soul',
   '.'],
  'obj'),
 (['seeking',
   'a',
   'mental',
   'escape',
   ',',
   'simone',
   'begins',
   'to',
   'tune',
   'into',
   "what's",
   'happening',
   'with',
   'the',
   'other',
   'couples',
   'around',
   'her',
   '.'],
  'obj'),
 (['the',
   'beatle',
   'fan',
   'is',
   'a',
   'drama',
   'about',
   'albert',
   ',',
   'a',
   'psychotic',
   'prisoner',
   'who',
   'is',
   'a',
   'devoted',
   'fan',
   'of',
   'john',
   'lennon',
   'and',
   'the',
   'beatles',
   '.'],
  'obj'),
 (['then',
   ',',
   'in',
   '1974',
   ',',
   'something',
   'incredible',
   'happened',
   '-',
   'they',
   'fell',
   'in',
   'love',
   '.'],
  'obj'),
 (['on',
   'her',
   'deathbed',
   ',',
   'candice',
   'klein',
   'accidentally',
   'asks',
   'the',
   'question',
   ',',
   '"',
   'what',
   'did',
   'i',
   'ever',
   'do',
   'to',
   'deserve',
   'this',
   '?',
   '"'],
  'obj'),
 (['shot',
   'as',
   'a',
   '"',
   'behind-the-scenes',
   '"',
   'look',
   'at',
   'how',
   'a',
   'fictional',
   'kung-fu',
   'movie',
   'is',
   'made',
   ',',
   'the',
   'film',
   'is',
   'basically',
   'a',
   'movie',
   'about',
   'the',
   'making',
   'of',
   'a',
   'movie',
   '.'],
  'obj'),
 (['before',
   'the',
   'investigation',
   'ends',
   ',',
   "we've",
   'met',
   'boyfriends',
   ',',
   'a',
   'drug',
   'dealer',
   ',',
   "alicia's",
   'mom',
   ',',
   "hadley's",
   'dad',
   ',',
   'nurses',
   ',',
   'doctors',
   ',',
   'and',
   'an',
   'orderly',
   '.'],
  'obj'),
 (['but',
   'what',
   'exactly',
   'is',
   'good',
   '&#38',
   ';',
   'what',
   'exactly',
   'is',
   'evil',
   '?'],
  'obj'),
 (['the',
   'movie',
   'takes',
   'place',
   'in',
   'mexico',
   ',',
   '2002',
   '(',
   'based',
   'on',
   'a',
   'story',
   'from',
   'the',
   "1800's",
   ')',
   '.'],
  'obj'),
 (["rainone's",
   'love',
   'affair',
   'with',
   'singing',
   'sensation',
   'kelly',
   'mcguire',
   'whom',
   'he',
   'discovered',
   'and',
   'his',
   'near',
   'demise',
   'by',
   'the',
   'hands',
   'of',
   'his',
   'own',
   'prot&#233',
   ';',
   'g&#233',
   ';',
   'vincent',
   'riccola',
   'is',
   'the',
   'juice',
   'that',
   'fuels',
   'this',
   'roller',
   'coaster',
   'ride',
   'through',
   'two',
   'debauchery-filled',
   'decades',
   'of',
   'greed',
   ',',
   'sex',
   ',',
   'drugs',
   'and',
   'rock',
   'and',
   'roll',
   '.'],
  'obj'),
 (['trapped',
   'in',
   'a',
   'lovers',
   'triangle',
   'and',
   'ruthless',
   'game',
   'of',
   'lust',
   ',',
   'greed',
   ',',
   'and',
   'betrayal',
   'we',
   'follow',
   'one',
   "woman's",
   'hypnotic',
   'journey',
   'to',
   'discover',
   'her',
   'true',
   'self',
   '.',
   '.',
   '.'],
  'obj'),
 (['decent-but-dull',
   'dek',
   'loves',
   'shirley',
   ',',
   'so',
   'much',
   'so',
   'that',
   'he',
   'humiliates',
   'her',
   'by',
   'proposing',
   'without',
   'warning',
   'on',
   'national',
   'television',
   '.'],
  'obj'),
 (['since',
   'all',
   'her',
   'architects',
   'are',
   'either',
   'busy',
   'otherwise',
   'or',
   'too',
   'conservative',
   'in',
   'style',
   ',',
   'this',
   'ambivalent',
   'honour',
   'falls',
   'to',
   'numerobis',
   '.'],
  'obj'),
 (["there's",
   'a',
   'story',
   'that',
   'goes',
   'around',
   'the',
   'town',
   'of',
   'darkness',
   'falls',
   'about',
   'her',
   ',',
   'and',
   "she's",
   'called',
   'the',
   'tooth',
   'fairy',
   '.'],
  'obj'),
 (['a',
   'strange',
   'film',
   'employing',
   'old',
   'home',
   'movies',
   'and',
   'newly',
   'shot',
   'footage',
   'in',
   'an',
   'effort',
   'to',
   'expose',
   'one',
   'hungarian',
   'family',
   'and',
   'their',
   'mutiple',
   'problems',
   'from',
   'the',
   '1940s',
   'to',
   'current',
   '.'],
  'obj'),
 (['matsumoto',
   'and',
   'sawako',
   'were',
   'a',
   'happy',
   'couple',
   ',',
   'but',
   'meddling',
   'parents',
   'and',
   'chase',
   'for',
   'success',
   'push',
   'the',
   'boy',
   'to',
   'a',
   'tragic',
   'choice',
   '.'],
  'obj'),
 (['elvis',
   'teams',
   'up',
   'with',
   'jack',
   '(',
   'ossie',
   'davis',
   ')',
   ',',
   'a',
   'fellow',
   'nursing',
   'home',
   'resident',
   'who',
   'thinks',
   'that',
   'he',
   'is',
   'actually',
   'president',
   'john',
   'f',
   '.',
   'kennedy',
   ',',
   'and',
   'the',
   'two',
   'valiant',
   'old',
   'codgers',
   'sally',
   'forth',
   'to',
   'battle',
   'an',
   'evil',
   'egyptian',
   'entity',
   'who',
   'has',
   'chosen',
   'their',
   'long-term',
   'care',
   'facility',
   'as',
   'his',
   'happy',
   'hunting',
   'grounds',
   '.'],
  'obj'),
 (['everywhere',
   'he',
   'goes',
   'he',
   'is',
   'plagued',
   'by',
   'cats',
   'and',
   'when',
   'by',
   'chance',
   'he',
   'meets',
   'carol',
   'on',
   'a',
   'lonely',
   'highway',
   'they',
   'must',
   'begin',
   'a',
   'journey',
   ',',
   'avoiding',
   'the',
   'mysterious',
   'private',
   'detective',
   'mr',
   'barlow',
   'and',
   'the',
   'terrifying',
   'inhuman',
   'creature',
   'jack',
   ',',
   'to',
   'uncover',
   'the',
   'dark',
   'truth',
   'to',
   "charlie's",
   'life',
   '.'],
  'obj'),
 (['used',
   'to',
   'living',
   'in',
   'poverty',
   ',',
   'it',
   'seemed',
   'impossible',
   'for',
   'cass',
   'and',
   'cary',
   'to',
   'have',
   'a',
   'comfortable',
   'and',
   'bountiful',
   'life',
   'until',
   'doqa',
   'gracia',
   'comes',
   'to',
   'bring',
   'them',
   'into',
   'her',
   'home',
   '.'],
  'obj'),
 (['the',
   'story',
   'of',
   'a',
   'normal',
   'family',
   'in',
   'which',
   'come',
   'out',
   'the',
   'dreams',
   'of',
   'those',
   'who',
   'have',
   'lost',
   'their',
   'possibilities',
   'and',
   'of',
   'those',
   'who',
   'want',
   'to',
   'realize',
   'them',
   '.'],
  'obj'),
 (['with',
   'grit',
   'and',
   'determination',
   'molly',
   'guides',
   'the',
   'girls',
   'on',
   'an',
   'epic',
   'journey',
   ',',
   'one',
   'step',
   'ahead',
   'of',
   'the',
   'authorities',
   ',',
   'over',
   '1',
   ',',
   '500',
   'miles',
   'of',
   "australia's",
   'outback',
   'in',
   'search',
   'of',
   'the',
   'rabbit-proof',
   'fence',
   'that',
   'bisects',
   'the',
   'continent',
   'and',
   'will',
   'lead',
   'them',
   'home',
   '.'],
  'obj'),
 (['they',
   'nevertherless',
   'feel',
   'responsible',
   'to',
   'protect',
   'the',
   'flag',
   'until',
   "monday's",
   'ceremony',
   '.'],
  'obj'),
 (['the',
   'doctor',
   'realizes',
   "it''s",
   'a',
   'love',
   'virus',
   'so',
   'he',
   'advises',
   'him',
   'to',
   'woo',
   'the',
   'girl',
   'somehow',
   ',',
   'not',
   'realizing',
   'that',
   'munnabhai',
   'has',
   'fallen',
   'for',
   'none',
   'other',
   'than',
   'his',
   'own',
   'younger',
   'sister',
   'komal',
   '.'],
  'obj'),
 (['however',
   ',',
   'he',
   'can',
   'only',
   'inhabit',
   'the',
   'body',
   'of',
   'a',
   'child',
   'for',
   'a',
   'short',
   'time',
   '.'],
  'obj'),
 (['years',
   'later',
   ',',
   'on',
   'a',
   'hunting',
   'trip',
   'in',
   'the',
   'maine',
   'woods',
   ',',
   'they',
   'are',
   'overtaken',
   'by',
   'a',
   'blizzard',
   ',',
   'a',
   'vicious',
   'storm',
   'in',
   'which',
   'something',
   'much',
   'more',
   'ominous',
   'moves',
   '.'],
  'obj'),
 (['consequently',
   ',',
   'what',
   'begins',
   'as',
   'an',
   'enthusiastic',
   'road',
   'trip',
   'is',
   'soon',
   'plagued',
   'with',
   'mysterious',
   'roadside',
   'obstacles',
   'that',
   'threaten',
   'to',
   'prevent',
   'the',
   'boys',
   'from',
   'ever',
   'making',
   'it',
   'to',
   'the',
   'competition',
   '.'],
  'obj'),
 (['when',
   'she',
   'gets',
   'into',
   'trouble',
   'with',
   'the',
   'police',
   'simon',
   'represses',
   'his',
   'death',
   'wish',
   'and',
   'decides',
   'to',
   'help',
   'her',
   'out',
   '.'],
  'obj'),
 (['chon',
   'then',
   'travels',
   'to',
   'new',
   'york',
   'for',
   'roy',
   "o'bannon",
   '(',
   'owen',
   'wilson',
   ')',
   '.'],
  'obj'),
 (['not',
   'only',
   'must',
   'they',
   'overcome',
   'an',
   'enemy',
   'adept',
   'at',
   'technological',
   'witchery',
   ',',
   'they',
   'must',
   'overcome',
   'the',
   'curse',
   'that',
   'marks',
   'their',
   'destiny',
   '.'],
  'obj'),
 (['their',
   'life',
   'becomes',
   'less',
   'ordinary',
   'when',
   'they',
   'encounter',
   'herb',
   ',',
   'a',
   'mischievous',
   'and',
   'malevolent',
   'geek',
   '.'],
  'obj'),
 (['they', 'call', 'themselves', 'd', '.', 'e', '.', 'b', '.', 's', '.'],
  'obj'),
 (['the',
   'story',
   'starts',
   'with',
   'hakimi',
   ',',
   'a',
   'freelance',
   'scriptwriter',
   'who',
   'is',
   'on',
   'his',
   'way',
   'to',
   'send',
   'his',
   '7-year-old',
   'daughter',
   ',',
   'imelda',
   ',',
   'to',
   'his',
   "ex-wife's",
   'house',
   'on',
   'one',
   'stormy',
   'night',
   '.'],
  'obj'),
 (['they',
   'follow',
   'leads',
   ',',
   'informants',
   'turn',
   'up',
   'dead',
   ',',
   "nick's",
   'wife',
   'is',
   'unhappy',
   "he's",
   'back',
   'on',
   'the',
   'street',
   ',',
   "henry's",
   'protective',
   'of',
   'the',
   'dead',
   "cop's",
   'wife',
   '.'],
  'obj'),
 (['the',
   'second',
   'part',
   'of',
   'aki',
   'kaurism&#228',
   ';',
   "ki's",
   '"',
   'finland',
   '"',
   'trilogy',
   ',',
   'the',
   'film',
   'follows',
   'a',
   'man',
   'who',
   'arrives',
   'in',
   'helsinki',
   'and',
   'gets',
   'beaten',
   'up',
   'so',
   'severely',
   'he',
   'develops',
   'amnesia',
   '.'],
  'obj'),
 (['soon',
   'after',
   'the',
   'accident',
   ',',
   'the',
   'survivors',
   'of',
   'the',
   'accident',
   'start',
   'dropping',
   'like',
   'flies',
   '.'],
  'obj'),
 (['edgar',
   'becomes',
   'intent',
   'on',
   'laying',
   'down',
   'some',
   'new',
   'rules',
   'and',
   'turning',
   'his',
   'coddled',
   'son',
   'into',
   'someone',
   'who',
   'can',
   'take',
   'on',
   'the',
   'family',
   'farm',
   '.'],
  'obj'),
 (['bound',
   'by',
   'a',
   'long',
   'red',
   'cord',
   ',',
   'a',
   'young',
   'couple',
   'wanders',
   'in',
   'search',
   'of',
   'something',
   'they',
   'have',
   'forgotten',
   '.'],
  'obj'),
 (['sudden',
   'fame',
   'does',
   'not',
   'seem',
   'to',
   'solve',
   'everything',
   ',',
   'however',
   '.'],
  'obj'),
 (['with',
   'no',
   'option',
   ',',
   'joe',
   'and',
   'katsuragi',
   'must',
   'use',
   'their',
   'martial',
   'arts',
   'skills',
   'to',
   'fight',
   'in',
   'the',
   'muscle',
   'dome',
   '.'],
  'obj'),
 (['drawing',
   'from',
   'his',
   'time',
   'with',
   'the',
   'kids',
   ',',
   'he',
   'writes',
   'a',
   'story',
   'about',
   'children',
   'who',
   "don't",
   'want',
   'to',
   'grow',
   'up',
   '.'],
  'obj'),
 (["she's",
   'an',
   'artist',
   ',',
   'but',
   "hasn't",
   'picked',
   'up',
   'a',
   'brush',
   'in',
   'a',
   'year',
   '.'],
  'obj'),
 (['when',
   'his',
   'daughter',
   'is',
   'kidnapped',
   'and',
   'held',
   'in',
   'exchange',
   'for',
   'priceless',
   'diamonds',
   ',',
   'the',
   'leader',
   'of',
   'a',
   'crew',
   'of',
   'highly',
   'skilled',
   'urban',
   'thieves',
   '(',
   'dmx',
   ')',
   'forges',
   'an',
   'unlikely',
   'alliance',
   'with',
   'a',
   'taiwanese',
   'intelligence',
   'officer',
   '(',
   'jet',
   'li',
   ')',
   'to',
   'rescue',
   'her',
   '.'],
  'obj'),
 (['"',
   'garmento',
   '"',
   'tells',
   'the',
   'other',
   'side',
   'of',
   'the',
   'story',
   ',',
   'with',
   'a',
   'dark',
   'and',
   'satirical',
   'look',
   'at',
   'new',
   "york's",
   'wholesale',
   'garment',
   'industry',
   ',',
   'where',
   'shady',
   'deals',
   'are',
   'made',
   'for',
   'a',
   'buck',
   'and',
   'ruthlessness',
   'is',
   'a',
   'prerequisite',
   'for',
   'career',
   'success',
   '.'],
  'obj'),
 (['rudy',
   'yellowshirt',
   'is',
   'an',
   'investigator',
   'with',
   'the',
   'police',
   'department',
   'and',
   'witnesses',
   'firsthand',
   'the',
   'painful',
   'legacy',
   'of',
   'indian',
   'existence',
   '.'],
  'obj'),
 (['journeying',
   'from',
   'the',
   'vietnam',
   'war',
   'to',
   'pulaski',
   ',',
   'tennessee',
   'and',
   'back',
   'to',
   'vietnam',
   ',',
   'daughter',
   'from',
   'danang',
   'tensely',
   'unfolds',
   'as',
   'cultural',
   'differences',
   'and',
   'the',
   'years',
   'of',
   'separation',
   'take',
   'their',
   'toll',
   'in',
   'a',
   'riveting',
   'film',
   'about',
   'longing',
   'and',
   'the',
   'personal',
   'legacy',
   'of',
   'war',
   '.'],
  'obj'),
 (['each',
   'weekend',
   'they',
   'come',
   'back',
   'with',
   'nothing',
   'but',
   'a',
   'hangover',
   '.'],
  'obj')]
In [7]:
all_words_neg[25:45]
Out[7]:
['.',
 'and',
 'just',
 'enough',
 'science',
 'to',
 'send',
 'you',
 'home',
 'thinking',
 '.',
 'it',
 'is',
 'not',
 'a_NEG',
 'mass-market_NEG',
 'entertainment_NEG',
 'but_NEG',
 'an_NEG',
 'uncompromising_NEG']

Note how this sentiment analyzer is marking everything after a negation word with '_NEG'

This is one of many ways we can determine sentiment

STEP 6: Use unigram_word_feats to get unigrams features

In [8]:
unigram_feats = sentim_analyzer.unigram_word_feats(all_words_neg, min_freq=4)
len(unigram_feats)
Out[8]:
83

STEP 7: Use add_feat_extractor to get a feature-value representation of our data

Apply to both training_set and testing_set

In [62]:
sentim_analyzer.add_feat_extractor(extract_unigram_feats, unigrams=unigram_feats)
In [63]:
training_set = sentim_analyzer.apply_features(training_docs)
training_set[:1]
Out[63]:
[({'contains(.)': True, 'contains(the)': False, 'contains(,)': True, 'contains(a)': True, 'contains(and)': True, 'contains(of)': False, 'contains(to)': False, 'contains(is)': True, 'contains(in)': False, 'contains(with)': False, 'contains(it)': False, 'contains(that)': False, 'contains(his)': False, 'contains(on)': False, 'contains(for)': False, 'contains(an)': False, 'contains(who)': False, 'contains(by)': False, 'contains(he)': False, 'contains(from)': False, 'contains(her)': False, 'contains(")': False, 'contains(film)': False, 'contains(as)': False, 'contains(this)': False, 'contains(movie)': False, 'contains(their)': False, 'contains(but)': False, 'contains(one)': True, 'contains(at)': False, 'contains(about)': True, 'contains(the_NEG)': False, 'contains(a_NEG)': False, 'contains(to_NEG)': False, 'contains(are)': False, "contains(there's)": False, 'contains(()': False, 'contains(story)': False, 'contains(when)': False, 'contains(so)': False, 'contains(be)': False, 'contains(,_NEG)': False, 'contains())': False, 'contains(they)': False, 'contains(you)': False, 'contains(not)': False, 'contains(have)': False, 'contains(like)': False, 'contains(will)': False, 'contains(all)': False, 'contains(into)': False, 'contains(out)': False, 'contains(she)': False, 'contains(what)': False, 'contains(life)': False, 'contains(has)': False, 'contains(its)': False, 'contains(only)': False, 'contains(more)': False, 'contains(even)': False, 'contains(--)': False, 'contains(:)': False, 'contains(can)': False, 'contains(;)': False, 'contains(home)': False, 'contains(look)': False, "contains(it's)": False, 'contains(if)': False, 'contains(where)': False, 'contains(most)': False, 'contains(him)': False, 'contains(search)': False, 'contains(but_NEG)': False, 'contains(love)': False, 'contains(both)': False, 'contains(make)': False, 'contains(begins)': False, 'contains(some)': False, 'contains(two)': False, 'contains(of_NEG)': False, 'contains(made)': False, 'contains(which)': False, 'contains(them)': False}, 'subj')]
In [64]:
test_set = sentim_analyzer.apply_features(testing_docs)
test_set[:1]
Out[64]:
[({'contains(.)': True, 'contains(the)': True, 'contains(,)': False, 'contains(a)': True, 'contains(and)': False, 'contains(of)': True, 'contains(to)': False, 'contains(is)': False, 'contains(in)': False, 'contains(with)': True, 'contains(it)': False, 'contains(that)': False, 'contains(his)': False, 'contains(on)': False, 'contains(for)': True, 'contains(an)': False, 'contains(who)': False, 'contains(by)': False, 'contains(he)': False, 'contains(from)': False, 'contains(her)': False, 'contains(")': False, 'contains(film)': False, 'contains(as)': False, 'contains(this)': False, 'contains(movie)': False, 'contains(their)': False, 'contains(but)': False, 'contains(one)': False, 'contains(at)': False, 'contains(about)': False, 'contains(the_NEG)': False, 'contains(a_NEG)': False, 'contains(to_NEG)': False, 'contains(are)': False, "contains(there's)": False, 'contains(()': False, 'contains(story)': False, 'contains(when)': False, 'contains(so)': False, 'contains(be)': False, 'contains(,_NEG)': False, 'contains())': False, 'contains(they)': False, 'contains(you)': False, 'contains(not)': False, 'contains(have)': False, 'contains(like)': False, 'contains(will)': False, 'contains(all)': False, 'contains(into)': False, 'contains(out)': False, 'contains(she)': False, 'contains(what)': False, 'contains(life)': False, 'contains(has)': False, 'contains(its)': False, 'contains(only)': False, 'contains(more)': False, 'contains(even)': False, 'contains(--)': False, 'contains(:)': False, 'contains(can)': False, 'contains(;)': False, 'contains(home)': False, 'contains(look)': False, "contains(it's)": False, 'contains(if)': False, 'contains(where)': False, 'contains(most)': False, 'contains(him)': False, 'contains(search)': False, 'contains(but_NEG)': False, 'contains(love)': False, 'contains(both)': False, 'contains(make)': False, 'contains(begins)': False, 'contains(some)': False, 'contains(two)': False, 'contains(of_NEG)': False, 'contains(made)': False, 'contains(which)': False, 'contains(them)': False}, 'subj')]

STEP 8: FINAL STEP!! We use Naive Bayes to create a trainer and FINALLY classify our data!

In [65]:
trainer = NaiveBayesClassifier.train
classifier = sentim_analyzer.train(trainer, training_set)
Training classifier
In [66]:
for key,value in sorted(sentim_analyzer.evaluate(test_set).items()):
    print('{0}: {1}'.format(key,value))
Evaluating NaiveBayesClassifier results...
Accuracy: 0.8
F-measure [obj]: 0.8
F-measure [subj]: 0.8
Precision [obj]: 0.8
Precision [subj]: 0.8
Recall [obj]: 0.8
Recall [subj]: 0.8