{ "cells": [ { "cell_type": "markdown", "metadata": {}, "source": [ "# SENTIMENT ANALYSIS" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "(via [these docs](http://www.nltk.org/howto/sentiment.html)) | 10-06-19" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### STEP 1: Import ALL the things" ] }, { "cell_type": "code", "execution_count": 1, "metadata": {}, "outputs": [], "source": [ "from nltk.classify import NaiveBayesClassifier\n", "from nltk.corpus import subjectivity\n", "from nltk.sentiment import SentimentAnalyzer\n", "from nltk.sentiment.util import *" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### STEP 2: Borrow `subjective` and `objective` sentences from the nltk for practice" ] }, { "cell_type": "code", "execution_count": 2, "metadata": {}, "outputs": [], "source": [ "n_instances = 100\n", "subj_docs = [(sent, 'subj') for sent in subjectivity.sents(categories='subj')[:n_instances]]\n", "obj_docs = [(sent, 'obj') for sent in subjectivity.sents(categories='obj')[:n_instances]]" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### STEP 3: Create `test` and `train` for both `subj` and `obj`" ] }, { "cell_type": "code", "execution_count": 3, "metadata": {}, "outputs": [], "source": [ "train_subj_docs = subj_docs[:80]\n", "test_subj_docs = subj_docs[80:100]\n", "train_obj_docs = obj_docs[:80]\n", "test_obj_docs = obj_docs[80:100]" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### STEP 4: Combine the two `test` and `train` sets " ] }, { "cell_type": "code", "execution_count": 4, "metadata": {}, "outputs": [], "source": [ "training_docs = train_subj_docs + train_obj_docs\n", "testing_docs = test_subj_docs + test_obj_docs\n", "# training_docs" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### STEP 5: Use `SentimentAnalyzer` to mark negation in training docs" ] }, { "cell_type": "code", "execution_count": 5, "metadata": {}, "outputs": [], "source": [ "sentim_analyzer = SentimentAnalyzer()\n", "# WTF IS MARK_NEGATION\n", "all_words_neg = sentim_analyzer.all_words([mark_negation(doc) for doc in training_docs])" ] }, { "cell_type": "code", "execution_count": 6, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "[(['smart',\n", " 'and',\n", " 'alert',\n", " ',',\n", " 'thirteen',\n", " 'conversations',\n", " 'about',\n", " 'one',\n", " 'thing',\n", " 'is',\n", " 'a',\n", " 'small',\n", " 'gem',\n", " '.'],\n", " 'subj'),\n", " (['color',\n", " ',',\n", " 'musical',\n", " 'bounce',\n", " 'and',\n", " 'warm',\n", " 'seas',\n", " 'lapping',\n", " 'on',\n", " 'island',\n", " 'shores',\n", " '.',\n", " 'and',\n", " 'just',\n", " 'enough',\n", " 'science',\n", " 'to',\n", " 'send',\n", " 'you',\n", " 'home',\n", " 'thinking',\n", " '.'],\n", " 'subj'),\n", " (['it',\n", " 'is',\n", " 'not',\n", " 'a',\n", " 'mass-market',\n", " 'entertainment',\n", " 'but',\n", " 'an',\n", " 'uncompromising',\n", " 'attempt',\n", " 'by',\n", " 'one',\n", " 'artist',\n", " 'to',\n", " 'think',\n", " 'about',\n", " 'another',\n", " '.'],\n", " 'subj'),\n", " (['a',\n", " 'light-hearted',\n", " 'french',\n", " 'film',\n", " 'about',\n", " 'the',\n", " 'spiritual',\n", " 'quest',\n", " 'of',\n", " 'a',\n", " 'fashion',\n", " 'model',\n", " 'seeking',\n", " 'peace',\n", " 'of',\n", " 'mind',\n", " 'while',\n", " 'in',\n", " 'a',\n", " 'love',\n", " 'affair',\n", " 'with',\n", " 'a',\n", " 'veterinarian',\n", " 'who',\n", " 'is',\n", " 'a',\n", " 'non-practicing',\n", " 'jew',\n", " '.'],\n", " 'subj'),\n", " (['my',\n", " 'wife',\n", " 'is',\n", " 'an',\n", " 'actress',\n", " 'has',\n", " 'its',\n", " 'moments',\n", " 'in',\n", " 'looking',\n", " 'at',\n", " 'the',\n", " 'comic',\n", " 'effects',\n", " 'of',\n", " 'jealousy',\n", " '.',\n", " 'in',\n", " 'the',\n", " 'end',\n", " ',',\n", " 'though',\n", " ',',\n", " 'it',\n", " 'is',\n", " 'only',\n", " 'mildly',\n", " 'amusing',\n", " 'when',\n", " 'it',\n", " 'could',\n", " 'have',\n", " 'been',\n", " 'so',\n", " 'much',\n", " 'more',\n", " '.'],\n", " 'subj'),\n", " (['works',\n", " 'both',\n", " 'as',\n", " 'an',\n", " 'engaging',\n", " 'drama',\n", " 'and',\n", " 'an',\n", " 'incisive',\n", " 'look',\n", " 'at',\n", " 'the',\n", " 'difficulties',\n", " 'facing',\n", " 'native',\n", " 'americans',\n", " '.'],\n", " 'subj'),\n", " (['even',\n", " 'a',\n", " 'hardened',\n", " 'voyeur',\n", " 'would',\n", " 'require',\n", " 'the',\n", " 'patience',\n", " 'of',\n", " 'job',\n", " 'to',\n", " 'get',\n", " 'through',\n", " 'this',\n", " 'interminable',\n", " ',',\n", " 'shapeless',\n", " 'documentary',\n", " 'about',\n", " 'the',\n", " 'swinging',\n", " 'subculture',\n", " '.'],\n", " 'subj'),\n", " (['when',\n", " 'perry',\n", " 'fists',\n", " 'a',\n", " 'bull',\n", " 'at',\n", " 'the',\n", " 'moore',\n", " 'farm',\n", " ',',\n", " \"it's\",\n", " 'only',\n", " 'a',\n", " 'matter',\n", " 'of',\n", " 'time',\n", " 'before',\n", " 'he',\n", " 'gets',\n", " 'the',\n", " 'upper',\n", " 'hand',\n", " 'in',\n", " 'matters',\n", " 'of',\n", " 'the',\n", " 'heart',\n", " '.'],\n", " 'subj'),\n", " (['the',\n", " 'characters',\n", " '.',\n", " '.',\n", " '.',\n", " 'are',\n", " 'paper-thin',\n", " ',',\n", " 'and',\n", " 'their',\n", " 'personalities',\n", " 'undergo',\n", " 'radical',\n", " 'changes',\n", " 'when',\n", " 'it',\n", " 'suits',\n", " 'the',\n", " 'script',\n", " '.'],\n", " 'subj'),\n", " (['the',\n", " 'script',\n", " 'is',\n", " 'a',\n", " 'tired',\n", " 'one',\n", " ',',\n", " 'with',\n", " 'few',\n", " 'moments',\n", " 'of',\n", " 'joy',\n", " 'rising',\n", " 'above',\n", " 'the',\n", " 'stale',\n", " 'material',\n", " '.'],\n", " 'subj'),\n", " (['the',\n", " 'bland',\n", " 'outweighs',\n", " 'the',\n", " 'nifty',\n", " ',',\n", " 'and',\n", " 'cletis',\n", " 'tout',\n", " 'never',\n", " 'becomes',\n", " 'the',\n", " 'clever',\n", " 'crime',\n", " 'comedy',\n", " 'it',\n", " 'thinks',\n", " 'it',\n", " 'is',\n", " '.'],\n", " 'subj'),\n", " (['directed',\n", " 'by',\n", " 'david',\n", " 'twohy',\n", " 'with',\n", " 'the',\n", " 'same',\n", " 'great',\n", " 'eye',\n", " 'for',\n", " 'eerie',\n", " 'understatement',\n", " 'that',\n", " 'he',\n", " 'brought',\n", " 'to',\n", " 'pitch',\n", " 'black',\n", " '.'],\n", " 'subj'),\n", " ([\"it's\",\n", " 'a',\n", " 'very',\n", " 'tasteful',\n", " 'rock',\n", " 'and',\n", " 'roll',\n", " 'movie',\n", " '.',\n", " 'you',\n", " 'could',\n", " 'put',\n", " 'it',\n", " 'on',\n", " 'a',\n", " 'coffee',\n", " 'table',\n", " 'anywhere',\n", " '.'],\n", " 'subj'),\n", " (['provides',\n", " 'the',\n", " 'kind',\n", " 'of',\n", " \"'laugh\",\n", " \"therapy'\",\n", " 'i',\n", " 'need',\n", " 'from',\n", " 'movie',\n", " 'comedies',\n", " '--',\n", " 'offbeat',\n", " 'humor',\n", " ',',\n", " 'amusing',\n", " 'characters',\n", " ',',\n", " 'and',\n", " 'a',\n", " 'happy',\n", " 'ending',\n", " '.',\n", " 'after',\n", " 'seeing',\n", " \"'analyze\",\n", " 'that',\n", " ',',\n", " \"'\",\n", " 'i',\n", " 'feel',\n", " 'better',\n", " 'already',\n", " '.'],\n", " 'subj'),\n", " (['worth',\n", " 'a',\n", " 'look',\n", " 'by',\n", " 'those',\n", " 'on',\n", " 'both',\n", " 'sides',\n", " 'of',\n", " 'the',\n", " 'issues',\n", " ',',\n", " 'if',\n", " 'only',\n", " 'for',\n", " 'the',\n", " 'perspective',\n", " 'it',\n", " 'offers',\n", " ',',\n", " 'one',\n", " 'the',\n", " 'public',\n", " 'rarely',\n", " 'sees',\n", " '.'],\n", " 'subj'),\n", " (['watching',\n", " 'the',\n", " 'film',\n", " 'is',\n", " 'like',\n", " 'reading',\n", " 'a',\n", " 'times',\n", " 'portrait',\n", " 'of',\n", " 'grief',\n", " 'that',\n", " 'keeps',\n", " 'shifting',\n", " 'focus',\n", " 'to',\n", " 'the',\n", " 'journalist',\n", " 'who',\n", " 'wrote',\n", " 'it',\n", " '.'],\n", " 'subj'),\n", " (['despite',\n", " 'these',\n", " 'annoyances',\n", " ',',\n", " 'the',\n", " 'capable',\n", " 'clayburgh',\n", " 'and',\n", " 'tambor',\n", " 'really',\n", " 'do',\n", " 'a',\n", " 'great',\n", " 'job',\n", " 'of',\n", " 'anchoring',\n", " 'the',\n", " 'characters',\n", " 'in',\n", " 'the',\n", " 'emotional',\n", " 'realities',\n", " 'of',\n", " 'middle',\n", " 'age',\n", " '.'],\n", " 'subj'),\n", " ([\"it's\",\n", " 'a',\n", " 'good',\n", " 'thing',\n", " 'that',\n", " 'woolly',\n", " 'mammoths',\n", " 'are',\n", " 'extinct',\n", " ',',\n", " 'because',\n", " 'this',\n", " 'movie',\n", " 'will',\n", " 'have',\n", " 'every',\n", " 'kid',\n", " 'in',\n", " 'the',\n", " 'schoolyard',\n", " 'wishing',\n", " 'for',\n", " 'their',\n", " 'very',\n", " 'own',\n", " '.'],\n", " 'subj'),\n", " (['preposterous',\n", " 'and',\n", " 'tedious',\n", " ',',\n", " 'sonny',\n", " 'is',\n", " 'spiked',\n", " 'with',\n", " 'unintentional',\n", " 'laughter',\n", " 'that',\n", " ',',\n", " 'unfortunately',\n", " ',',\n", " 'occurs',\n", " 'too',\n", " 'infrequently',\n", " 'to',\n", " 'make',\n", " 'the',\n", " 'film',\n", " 'even',\n", " 'a',\n", " 'guilty',\n", " 'pleasure',\n", " '.'],\n", " 'subj'),\n", " (['4ever',\n", " 'has',\n", " 'the',\n", " 'same',\n", " 'sledgehammer',\n", " 'appeal',\n", " 'as',\n", " 'pokemon',\n", " 'videos',\n", " ',',\n", " 'but',\n", " 'it',\n", " 'breathes',\n", " 'more',\n", " 'on',\n", " 'the',\n", " 'big',\n", " 'screen',\n", " 'and',\n", " 'induces',\n", " 'headaches',\n", " 'more',\n", " 'slowly',\n", " '.'],\n", " 'subj'),\n", " (['si',\n", " 'el',\n", " 'siglo',\n", " 'xxi',\n", " 'necesita',\n", " 'de',\n", " 'héroes',\n", " ',',\n", " 'el',\n", " 'hombre',\n", " 'araña',\n", " 'parece',\n", " 'haber',\n", " 'llegado',\n", " 'para',\n", " 'quedarse',\n", " '.'],\n", " 'subj'),\n", " ([\"it's\",\n", " 'hard',\n", " 'to',\n", " 'tell',\n", " 'with',\n", " 'all',\n", " 'the',\n", " 'crashing',\n", " 'and',\n", " 'banging',\n", " 'where',\n", " 'the',\n", " 'salesmanship',\n", " 'ends',\n", " 'and',\n", " 'the',\n", " 'movie',\n", " 'begins',\n", " '.'],\n", " 'subj'),\n", " (['it',\n", " 'desperately',\n", " 'wants',\n", " 'to',\n", " 'be',\n", " 'a',\n", " 'wacky',\n", " ',',\n", " 'screwball',\n", " 'comedy',\n", " ',',\n", " 'but',\n", " 'the',\n", " 'most',\n", " 'screwy',\n", " 'thing',\n", " 'here',\n", " 'is',\n", " 'how',\n", " 'so',\n", " 'many',\n", " 'talented',\n", " 'people',\n", " 'were',\n", " 'convinced',\n", " 'to',\n", " 'waste',\n", " 'their',\n", " 'time',\n", " '.'],\n", " 'subj'),\n", " (['writer/director',\n", " 'walter',\n", " 'hill',\n", " 'is',\n", " 'in',\n", " 'his',\n", " 'hypermasculine',\n", " 'element',\n", " 'here',\n", " ',',\n", " 'once',\n", " 'again',\n", " 'able',\n", " 'to',\n", " 'inject',\n", " 'some',\n", " 'real',\n", " 'vitality',\n", " 'and',\n", " 'even',\n", " 'art',\n", " 'into',\n", " 'a',\n", " 'pulpy',\n", " 'concept',\n", " 'that',\n", " ',',\n", " 'in',\n", " 'many',\n", " 'other',\n", " 'hands',\n", " 'would',\n", " 'be',\n", " 'completely',\n", " 'forgettable',\n", " '.'],\n", " 'subj'),\n", " (['hill',\n", " 'looks',\n", " 'to',\n", " 'be',\n", " 'going',\n", " 'through',\n", " 'the',\n", " 'motions',\n", " ',',\n", " 'beginning',\n", " 'with',\n", " 'the',\n", " 'pale',\n", " 'script',\n", " '.'],\n", " 'subj'),\n", " (['extremely',\n", " 'well',\n", " 'cast',\n", " ',',\n", " 'especially',\n", " 'in',\n", " 'the',\n", " 'large',\n", " 'number',\n", " 'of',\n", " 'supporting',\n", " 'roles',\n", " '.'],\n", " 'subj'),\n", " (['a',\n", " 'chilling',\n", " 'tale',\n", " 'of',\n", " 'one',\n", " 'of',\n", " 'the',\n", " 'great',\n", " 'crimes',\n", " 'of',\n", " '20th',\n", " 'century',\n", " 'france',\n", " ':',\n", " 'the',\n", " 'murder',\n", " 'of',\n", " 'two',\n", " 'rich',\n", " 'women',\n", " 'by',\n", " 'their',\n", " 'servants',\n", " 'in',\n", " '1933',\n", " '.'],\n", " 'subj'),\n", " (['a',\n", " 'dark',\n", " ',',\n", " 'quirky',\n", " 'road',\n", " 'movie',\n", " 'that',\n", " 'constantly',\n", " 'defies',\n", " 'expectation',\n", " '.'],\n", " 'subj'),\n", " (['impostor',\n", " \"doesn't\",\n", " 'do',\n", " 'much',\n", " 'with',\n", " 'its',\n", " 'template',\n", " ',',\n", " 'despite',\n", " 'a',\n", " 'remarkably',\n", " 'strong',\n", " 'cast',\n", " '.'],\n", " 'subj'),\n", " (['though',\n", " 'it',\n", " 'lacks',\n", " 'the',\n", " 'utter',\n", " 'authority',\n", " 'of',\n", " 'a',\n", " 'genre',\n", " 'gem',\n", " ',',\n", " \"there's\",\n", " 'a',\n", " 'certain',\n", " 'robustness',\n", " 'to',\n", " 'this',\n", " 'engaging',\n", " 'mix',\n", " 'of',\n", " 'love',\n", " 'and',\n", " 'bloodletting',\n", " '.'],\n", " 'subj'),\n", " (['if',\n", " 'you',\n", " 'can',\n", " 'keep',\n", " 'your',\n", " 'eyes',\n", " 'open',\n", " 'amid',\n", " 'all',\n", " 'the',\n", " 'blood',\n", " 'and',\n", " 'gore',\n", " ',',\n", " \"you'll\",\n", " 'see',\n", " 'del',\n", " 'toro',\n", " 'has',\n", " 'brought',\n", " 'unexpected',\n", " 'gravity',\n", " 'to',\n", " 'blade',\n", " 'ii',\n", " '.'],\n", " 'subj'),\n", " ([\"there's\",\n", " 'undeniable',\n", " 'enjoyment',\n", " 'to',\n", " 'be',\n", " 'had',\n", " 'from',\n", " 'films',\n", " 'crammed',\n", " 'with',\n", " 'movie',\n", " 'references',\n", " ',',\n", " 'but',\n", " 'the',\n", " 'fun',\n", " 'wears',\n", " 'thin',\n", " '--',\n", " 'then',\n", " 'out',\n", " '--',\n", " 'when',\n", " \"there's\",\n", " 'nothing',\n", " 'else',\n", " 'happening',\n", " '.'],\n", " 'subj'),\n", " (['a',\n", " 'work',\n", " 'that',\n", " 'lacks',\n", " 'both',\n", " 'a',\n", " 'purpose',\n", " 'and',\n", " 'a',\n", " 'strong',\n", " 'pulse',\n", " '.'],\n", " 'subj'),\n", " (['it',\n", " 'helps',\n", " 'that',\n", " 'lil',\n", " 'bow',\n", " 'wow',\n", " '.',\n", " '.',\n", " '.',\n", " 'tones',\n", " 'down',\n", " 'his',\n", " 'pint-sized',\n", " 'gangsta',\n", " 'act',\n", " 'to',\n", " 'play',\n", " 'someone',\n", " 'who',\n", " 'resembles',\n", " 'a',\n", " 'real',\n", " 'kid',\n", " '.'],\n", " 'subj'),\n", " (['a',\n", " 'mimetic',\n", " 'approximation',\n", " 'of',\n", " 'better',\n", " 'films',\n", " 'like',\n", " 'contempt',\n", " 'and',\n", " '8',\n", " '1/2',\n", " '.'],\n", " 'subj'),\n", " (['eastwood',\n", " 'is',\n", " 'an',\n", " 'icon',\n", " 'of',\n", " 'moviemaking',\n", " ',',\n", " 'one',\n", " 'of',\n", " 'the',\n", " 'best',\n", " 'actors',\n", " ',',\n", " 'directors',\n", " 'and',\n", " 'producers',\n", " 'around',\n", " ',',\n", " 'responsible',\n", " 'for',\n", " 'some',\n", " 'excellent',\n", " 'work',\n", " '.',\n", " 'but',\n", " 'even',\n", " 'a',\n", " 'hero',\n", " 'can',\n", " 'stumble',\n", " 'sometimes',\n", " '.'],\n", " 'subj'),\n", " (['nair',\n", " \"doesn't\",\n", " 'use',\n", " '[monsoon',\n", " 'wedding]',\n", " 'to',\n", " 'lament',\n", " 'the',\n", " 'loss',\n", " 'of',\n", " 'culture',\n", " '.',\n", " 'instead',\n", " ',',\n", " 'she',\n", " 'sees',\n", " 'it',\n", " 'as',\n", " 'a',\n", " 'chance',\n", " 'to',\n", " 'revitalize',\n", " 'what',\n", " 'is',\n", " 'and',\n", " 'always',\n", " 'has',\n", " 'been',\n", " 'remarkable',\n", " 'about',\n", " 'clung-to',\n", " 'traditions',\n", " '.'],\n", " 'subj'),\n", " (['stuffed',\n", " 'to',\n", " 'the',\n", " 'brim',\n", " 'with',\n", " 'ideas',\n", " ',',\n", " 'american',\n", " 'instigator',\n", " 'michael',\n", " \"moore's\",\n", " 'film',\n", " 'is',\n", " 'a',\n", " 'rambling',\n", " 'examination',\n", " 'of',\n", " 'american',\n", " 'gun',\n", " 'culture',\n", " 'that',\n", " 'uses',\n", " 'his',\n", " 'usual',\n", " 'modus',\n", " 'operandi',\n", " 'of',\n", " 'crucifixion',\n", " 'through',\n", " 'juxtaposition',\n", " '.'],\n", " 'subj'),\n", " (['.',\n", " '.',\n", " '.',\n", " 'a',\n", " 'joke',\n", " 'at',\n", " 'once',\n", " 'flaky',\n", " 'and',\n", " 'resonant',\n", " ',',\n", " 'lightweight',\n", " 'and',\n", " 'bizarrely',\n", " 'original',\n", " '.'],\n", " 'subj'),\n", " ([\"fontaine's\",\n", " 'direction',\n", " ',',\n", " 'especially',\n", " 'her',\n", " 'agreeably',\n", " 'startling',\n", " 'use',\n", " 'of',\n", " 'close-ups',\n", " 'and',\n", " 'her',\n", " 'grace',\n", " 'with',\n", " 'a',\n", " 'moving',\n", " 'camera',\n", " ',',\n", " 'creates',\n", " 'sheerly',\n", " 'cinematic',\n", " 'appeal',\n", " '.'],\n", " 'subj'),\n", " (['starts',\n", " 'slowly',\n", " ',',\n", " 'but',\n", " 'adrien',\n", " 'brody',\n", " 'Â\\x96',\n", " 'in',\n", " 'the',\n", " 'title',\n", " 'role',\n", " 'Â\\x96',\n", " 'helps',\n", " 'make',\n", " 'the',\n", " \"film's\",\n", " 'conclusion',\n", " 'powerful',\n", " 'and',\n", " 'satisfying',\n", " '.'],\n", " 'subj'),\n", " (['a',\n", " 'refreshing',\n", " 'change',\n", " 'from',\n", " 'the',\n", " 'usual',\n", " 'whoopee-cushion',\n", " 'effort',\n", " 'aimed',\n", " 'at',\n", " 'the',\n", " 'youth',\n", " 'market',\n", " '.'],\n", " 'subj'),\n", " (['you',\n", " 'really',\n", " 'have',\n", " 'to',\n", " 'salute',\n", " 'writer-director',\n", " 'haneke',\n", " '(',\n", " 'he',\n", " 'adapted',\n", " 'elfriede',\n", " \"jelinek's\",\n", " 'novel',\n", " ')',\n", " 'for',\n", " 'making',\n", " 'a',\n", " 'film',\n", " 'that',\n", " \"isn't\",\n", " 'nearly',\n", " 'as',\n", " 'graphic',\n", " 'but',\n", " 'much',\n", " 'more',\n", " 'powerful',\n", " ',',\n", " 'brutally',\n", " 'shocking',\n", " 'and',\n", " 'difficult',\n", " 'to',\n", " 'watch',\n", " '.'],\n", " 'subj'),\n", " (['barry',\n", " 'convinces',\n", " 'us',\n", " \"he's\",\n", " 'a',\n", " 'dangerous',\n", " ',',\n", " 'secretly',\n", " 'unhinged',\n", " 'guy',\n", " 'who',\n", " 'could',\n", " 'easily',\n", " 'have',\n", " 'killed',\n", " 'a',\n", " 'president',\n", " 'because',\n", " 'it',\n", " 'made',\n", " 'him',\n", " 'feel',\n", " 'powerful',\n", " '.'],\n", " 'subj'),\n", " (['a',\n", " 'distant',\n", " ',',\n", " 'even',\n", " 'sterile',\n", " ',',\n", " 'yet',\n", " 'compulsively',\n", " 'watchable',\n", " 'look',\n", " 'at',\n", " 'the',\n", " 'sordid',\n", " 'life',\n", " 'of',\n", " \"hogan's\",\n", " 'heroes',\n", " 'star',\n", " 'bob',\n", " 'crane',\n", " '.'],\n", " 'subj'),\n", " ([\"there's\",\n", " 'no',\n", " 'disguising',\n", " 'this',\n", " 'as',\n", " 'one',\n", " 'of',\n", " 'the',\n", " 'worst',\n", " 'films',\n", " 'of',\n", " 'the',\n", " 'summer',\n", " '.',\n", " 'or',\n", " 'for',\n", " 'the',\n", " 'year',\n", " ',',\n", " 'for',\n", " 'that',\n", " 'matter',\n", " '.'],\n", " 'subj'),\n", " (['director',\n", " 'dan',\n", " 'verete',\n", " 'uses',\n", " 'his',\n", " 'camera',\n", " 'as',\n", " 'the',\n", " 'metaphoric',\n", " 'needle',\n", " ',',\n", " 'and',\n", " 'his',\n", " 'cast',\n", " 'in',\n", " 'each',\n", " 'segment',\n", " 'as',\n", " 'his',\n", " 'thread',\n", " ',',\n", " 'to',\n", " 'form',\n", " 'a',\n", " 'sweeping',\n", " 'tapestry',\n", " 'of',\n", " 'mis-explanation',\n", " 'and',\n", " 'contention',\n", " '.'],\n", " 'subj'),\n", " (['waydowntown',\n", " 'just',\n", " 'like',\n", " 'most',\n", " 'large',\n", " 'cities',\n", " ',',\n", " \"isn't\",\n", " 'somewhere',\n", " \"you'll\",\n", " 'want',\n", " 'to',\n", " 'spend',\n", " 'the',\n", " 'rest',\n", " 'of',\n", " 'your',\n", " 'life',\n", " ',',\n", " 'but',\n", " 'it',\n", " 'sure',\n", " 'is',\n", " 'a',\n", " 'fun',\n", " 'place',\n", " 'to',\n", " 'visit',\n", " 'for',\n", " 'a',\n", " 'while',\n", " '.'],\n", " 'subj'),\n", " (['the',\n", " 'acting',\n", " 'in',\n", " 'pauline',\n", " 'and',\n", " 'paulette',\n", " 'is',\n", " 'good',\n", " 'all',\n", " 'round',\n", " ',',\n", " 'but',\n", " 'what',\n", " 'really',\n", " 'sets',\n", " 'the',\n", " 'film',\n", " 'apart',\n", " 'is',\n", " \"debrauwer's\",\n", " 'refusal',\n", " 'to',\n", " 'push',\n", " 'the',\n", " 'easy',\n", " 'emotional',\n", " 'buttons',\n", " '.'],\n", " 'subj'),\n", " (['the',\n", " 'only',\n", " 'young',\n", " 'people',\n", " 'who',\n", " 'possibly',\n", " 'will',\n", " 'enjoy',\n", " 'it',\n", " 'are',\n", " 'infants',\n", " '.',\n", " '.',\n", " '.',\n", " 'who',\n", " 'might',\n", " 'be',\n", " 'distracted',\n", " 'by',\n", " 'the',\n", " \"movie's\",\n", " 'quick',\n", " 'movements',\n", " 'and',\n", " 'sounds',\n", " '.'],\n", " 'subj'),\n", " ([\"there's\",\n", " 'lots',\n", " 'of',\n", " 'cool',\n", " 'stuff',\n", " 'packed',\n", " 'into',\n", " \"espn's\",\n", " 'ultimate',\n", " 'x',\n", " '.'],\n", " 'subj'),\n", " (['it',\n", " 'gets',\n", " 'old',\n", " 'quickly',\n", " '.',\n", " 'watch',\n", " 'barbershop',\n", " 'again',\n", " 'if',\n", " \"you're\",\n", " 'in',\n", " 'need',\n", " 'of',\n", " 'a',\n", " 'cube',\n", " 'fix--this',\n", " \"isn't\",\n", " 'worth',\n", " 'sitting',\n", " 'through',\n", " '.'],\n", " 'subj'),\n", " (['harland',\n", " 'williams',\n", " 'is',\n", " 'so',\n", " 'funny',\n", " 'in',\n", " 'drag',\n", " 'he',\n", " 'should',\n", " 'consider',\n", " 'permanent',\n", " 'sex-reassignment',\n", " '.'],\n", " 'subj'),\n", " (['the',\n", " \"film's\",\n", " 'images',\n", " 'give',\n", " 'a',\n", " 'backbone',\n", " 'to',\n", " 'the',\n", " 'company',\n", " 'and',\n", " 'provide',\n", " 'an',\n", " 'emotional',\n", " 'edge',\n", " 'to',\n", " 'its',\n", " 'ultimate',\n", " 'demise',\n", " '.'],\n", " 'subj'),\n", " ([\"it's\",\n", " 'the',\n", " 'kind',\n", " 'of',\n", " 'film',\n", " 'where',\n", " 'the',\n", " 'villain',\n", " 'even',\n", " 'gives',\n", " 'an',\n", " 'evil',\n", " 'look',\n", " 'for',\n", " 'his',\n", " 'passport',\n", " 'photo',\n", " '.',\n", " 'how',\n", " 'can',\n", " 'you',\n", " 'resist',\n", " 'that',\n", " '?'],\n", " 'subj'),\n", " (['plotless',\n", " 'collection',\n", " 'of',\n", " 'moronic',\n", " 'stunts',\n", " 'is',\n", " 'by',\n", " 'far',\n", " 'the',\n", " 'worst',\n", " 'movie',\n", " 'of',\n", " 'the',\n", " 'year',\n", " '.'],\n", " 'subj'),\n", " (['a',\n", " 'broad',\n", " ',',\n", " 'melodramatic',\n", " 'estrogen',\n", " 'opera',\n", " \"that's\",\n", " 'pretty',\n", " 'toxic',\n", " 'in',\n", " 'its',\n", " 'own',\n", " 'right',\n", " '.'],\n", " 'subj'),\n", " (['just',\n", " 'a',\n", " 'kiss',\n", " 'wants',\n", " 'desperately',\n", " 'to',\n", " 'come',\n", " 'off',\n", " 'as',\n", " 'a',\n", " 'fanciful',\n", " 'film',\n", " 'about',\n", " 'the',\n", " 'typical',\n", " 'problems',\n", " 'of',\n", " 'average',\n", " 'people',\n", " '.',\n", " 'but',\n", " 'it',\n", " 'is',\n", " 'set',\n", " 'in',\n", " 'a',\n", " 'world',\n", " 'that',\n", " 'is',\n", " 'very',\n", " ',',\n", " 'very',\n", " 'far',\n", " 'from',\n", " 'the',\n", " 'one',\n", " 'most',\n", " 'of',\n", " 'us',\n", " 'inhabit',\n", " '.'],\n", " 'subj'),\n", " (['this',\n", " 'is',\n", " 'a',\n", " 'movie',\n", " 'where',\n", " 'the',\n", " 'most',\n", " 'notable',\n", " 'observation',\n", " 'is',\n", " 'how',\n", " 'long',\n", " \"you've\",\n", " 'been',\n", " 'sitting',\n", " 'still',\n", " '.'],\n", " 'subj'),\n", " (['with',\n", " 'a',\n", " 'romantic',\n", " 'comedy',\n", " 'plotline',\n", " 'straight',\n", " 'from',\n", " 'the',\n", " 'ages',\n", " ',',\n", " 'this',\n", " 'cinderella',\n", " 'story',\n", " \"doesn't\",\n", " 'have',\n", " 'a',\n", " 'single',\n", " 'surprise',\n", " 'up',\n", " 'its',\n", " 'sleeve',\n", " '.',\n", " 'but',\n", " 'it',\n", " 'does',\n", " 'somehow',\n", " 'manage',\n", " 'to',\n", " 'get',\n", " 'you',\n", " 'under',\n", " 'its',\n", " 'spell',\n", " '.'],\n", " 'subj'),\n", " (['a',\n", " 'charming',\n", " 'trifle',\n", " '.',\n", " '.',\n", " '.',\n", " 'a',\n", " 'welcome',\n", " 'return',\n", " 'to',\n", " 'jocular',\n", " 'form',\n", " '.'],\n", " 'subj'),\n", " ([\"it's\",\n", " 'not',\n", " 'difficult',\n", " 'to',\n", " 'spot',\n", " 'the',\n", " 'culprit',\n", " 'early-on',\n", " 'in',\n", " 'this',\n", " 'predictable',\n", " 'thriller',\n", " '.'],\n", " 'subj'),\n", " (['without',\n", " 'the',\n", " 'dark',\n", " 'spookiness',\n", " 'of',\n", " 'crystal',\n", " 'lake',\n", " 'camp',\n", " ',',\n", " 'the',\n", " 'horror',\n", " 'concept',\n", " 'completely',\n", " 'loses',\n", " 'its',\n", " 'creepy',\n", " 'menace',\n", " '.'],\n", " 'subj'),\n", " ([\"there's\",\n", " 'suspension',\n", " 'of',\n", " 'disbelief',\n", " 'and',\n", " 'then',\n", " \"there's\",\n", " 'bad',\n", " 'screenwriting',\n", " '.',\n", " '.',\n", " '.',\n", " 'this',\n", " 'film',\n", " 'packs',\n", " 'a',\n", " 'wallop',\n", " 'of',\n", " 'the',\n", " 'latter',\n", " '.'],\n", " 'subj'),\n", " (['little',\n", " 'more',\n", " 'than',\n", " 'a',\n", " 'stylish',\n", " 'exercise',\n", " 'in',\n", " 'revisionism',\n", " 'whose',\n", " 'point',\n", " '.',\n", " '.',\n", " '.',\n", " 'is',\n", " 'no',\n", " 'doubt',\n", " 'true',\n", " ',',\n", " 'but',\n", " 'serves',\n", " 'as',\n", " 'a',\n", " 'rather',\n", " 'thin',\n", " 'moral',\n", " 'to',\n", " 'such',\n", " 'a',\n", " 'knowing',\n", " 'fable',\n", " '.'],\n", " 'subj'),\n", " (['anyone',\n", " 'who',\n", " 'can',\n", " 'count',\n", " 'to',\n", " 'five',\n", " '(',\n", " 'the',\n", " \"film's\",\n", " 'target',\n", " 'market',\n", " '?',\n", " ')',\n", " 'can',\n", " 'see',\n", " 'where',\n", " 'this',\n", " 'dumbed-down',\n", " 'concoction',\n", " 'is',\n", " 'going',\n", " '.'],\n", " 'subj'),\n", " (['every',\n", " 'defiantly',\n", " 'over-the-top',\n", " 'action',\n", " 'scene',\n", " '--',\n", " 'from',\n", " 'high-stakes',\n", " 'car',\n", " 'chases',\n", " 'to',\n", " 'fearsome',\n", " 'drug',\n", " 'busts',\n", " '--',\n", " 'seizes',\n", " 'your',\n", " 'adrenal',\n", " 'gland',\n", " 'and',\n", " 'milks',\n", " 'it',\n", " 'like',\n", " 'an',\n", " 'epileptic',\n", " 'farmer',\n", " '.'],\n", " 'subj'),\n", " (['kosminsky',\n", " '.',\n", " '.',\n", " '.',\n", " 'puts',\n", " 'enough',\n", " 'salt',\n", " 'into',\n", " 'the',\n", " 'wounds',\n", " 'of',\n", " 'the',\n", " 'tortured',\n", " 'and',\n", " 'self-conscious',\n", " 'material',\n", " 'to',\n", " 'make',\n", " 'it',\n", " 'sting',\n", " '.'],\n", " 'subj'),\n", " (['a',\n", " 'sobering',\n", " 'and',\n", " 'powerful',\n", " 'documentary',\n", " 'about',\n", " 'the',\n", " 'most',\n", " 'severe',\n", " 'kind',\n", " 'of',\n", " 'personal',\n", " 'loss',\n", " ':',\n", " 'rejection',\n", " 'by',\n", " \"one's\",\n", " 'mother',\n", " '.'],\n", " 'subj'),\n", " (['if',\n", " 'the',\n", " 'story',\n", " 'lacks',\n", " 'bite',\n", " ',',\n", " 'the',\n", " 'performances',\n", " 'are',\n", " 'never',\n", " 'less',\n", " 'than',\n", " 'affectionate',\n", " '.'],\n", " 'subj'),\n", " (['a',\n", " 'deftly',\n", " 'entertaining',\n", " 'film',\n", " ',',\n", " 'smartly',\n", " 'played',\n", " 'and',\n", " 'smartly',\n", " 'directed',\n", " '.'],\n", " 'subj'),\n", " (['ice',\n", " 'age',\n", " 'is',\n", " 'the',\n", " 'first',\n", " 'computer-generated',\n", " 'feature',\n", " 'cartoon',\n", " 'to',\n", " 'feel',\n", " 'like',\n", " 'other',\n", " 'movies',\n", " ',',\n", " 'and',\n", " 'that',\n", " 'makes',\n", " 'for',\n", " 'some',\n", " 'glacial',\n", " 'pacing',\n", " 'early',\n", " 'on',\n", " '.'],\n", " 'subj'),\n", " (['i',\n", " 'like',\n", " 'my',\n", " 'christmas',\n", " 'movies',\n", " 'with',\n", " 'more',\n", " 'elves',\n", " 'and',\n", " 'snow',\n", " 'and',\n", " 'less',\n", " 'pimps',\n", " 'and',\n", " \"ho's\",\n", " '.'],\n", " 'subj'),\n", " ([\"ferrara's\",\n", " 'strongest',\n", " 'and',\n", " 'most',\n", " 'touching',\n", " 'movie',\n", " 'of',\n", " 'recent',\n", " 'years',\n", " '.'],\n", " 'subj'),\n", " (['skip',\n", " 'work',\n", " 'to',\n", " 'see',\n", " 'it',\n", " 'at',\n", " 'the',\n", " 'first',\n", " 'opportunity',\n", " '.'],\n", " 'subj'),\n", " (['both',\n", " 'the',\n", " 'film',\n", " 'and',\n", " \"nachtwey's\",\n", " 'photos',\n", " 'hammer',\n", " 'home',\n", " 'the',\n", " 'grim',\n", " 'reality',\n", " 'of',\n", " 'the',\n", " \"world's\",\n", " 'gutters',\n", " 'and',\n", " 'battlefields',\n", " ',',\n", " 'and',\n", " 'will',\n", " 'make',\n", " 'you',\n", " 'question',\n", " 'what',\n", " \"'news'\",\n", " 'really',\n", " 'is',\n", " '.'],\n", " 'subj'),\n", " (['so',\n", " 'relentlessly',\n", " 'wholesome',\n", " 'it',\n", " 'made',\n", " 'me',\n", " 'want',\n", " 'to',\n", " 'swipe',\n", " 'something',\n", " '.'],\n", " 'subj'),\n", " (['shyamalan',\n", " 'offers',\n", " 'copious',\n", " 'hints',\n", " 'along',\n", " 'the',\n", " 'way',\n", " '--',\n", " 'myriad',\n", " 'signs',\n", " ',',\n", " 'if',\n", " 'you',\n", " 'will',\n", " '--',\n", " 'that',\n", " 'beneath',\n", " 'the',\n", " 'familiar',\n", " ',',\n", " 'funny',\n", " 'surface',\n", " 'is',\n", " 'a',\n", " 'far',\n", " 'bigger',\n", " ',',\n", " 'far',\n", " 'more',\n", " 'meaningful',\n", " 'story',\n", " 'than',\n", " 'one',\n", " 'in',\n", " 'which',\n", " 'little',\n", " 'green',\n", " 'men',\n", " 'come',\n", " 'to',\n", " 'earth',\n", " 'for',\n", " 'harvesting',\n", " 'purposes',\n", " '.'],\n", " 'subj'),\n", " (['that',\n", " \"'alabama'\",\n", " 'manages',\n", " 'to',\n", " 'be',\n", " 'pleasant',\n", " 'in',\n", " 'spite',\n", " 'of',\n", " 'its',\n", " 'predictability',\n", " 'and',\n", " 'occasional',\n", " 'slowness',\n", " 'is',\n", " 'due',\n", " 'primarily',\n", " 'to',\n", " 'the',\n", " 'perkiness',\n", " 'of',\n", " 'witherspoon',\n", " '(',\n", " 'who',\n", " 'is',\n", " 'always',\n", " 'a',\n", " 'joy',\n", " 'to',\n", " 'watch',\n", " ',',\n", " 'even',\n", " 'when',\n", " 'her',\n", " 'material',\n", " 'is',\n", " 'not',\n", " 'first-rate',\n", " ')',\n", " '.',\n", " '.',\n", " '.'],\n", " 'subj'),\n", " (['against',\n", " 'all',\n", " 'odds',\n", " 'in',\n", " 'heaven',\n", " 'and',\n", " 'hell',\n", " ',',\n", " 'it',\n", " 'creeped',\n", " 'me',\n", " 'out',\n", " 'just',\n", " 'fine',\n", " '.'],\n", " 'subj'),\n", " (['the',\n", " 'movie',\n", " 'begins',\n", " 'in',\n", " 'the',\n", " 'past',\n", " 'where',\n", " 'a',\n", " 'young',\n", " 'boy',\n", " 'named',\n", " 'sam',\n", " 'attempts',\n", " 'to',\n", " 'save',\n", " 'celebi',\n", " 'from',\n", " 'a',\n", " 'hunter',\n", " '.'],\n", " 'obj'),\n", " (['emerging',\n", " 'from',\n", " 'the',\n", " 'human',\n", " 'psyche',\n", " 'and',\n", " 'showing',\n", " 'characteristics',\n", " 'of',\n", " 'abstract',\n", " 'expressionism',\n", " ',',\n", " 'minimalism',\n", " 'and',\n", " 'russian',\n", " 'constructivism',\n", " ',',\n", " 'graffiti',\n", " 'removal',\n", " 'has',\n", " 'secured',\n", " 'its',\n", " 'place',\n", " 'in',\n", " 'the',\n", " 'history',\n", " 'of',\n", " 'modern',\n", " 'art',\n", " 'while',\n", " 'being',\n", " 'created',\n", " 'by',\n", " 'artists',\n", " 'who',\n", " 'are',\n", " 'unconscious',\n", " 'of',\n", " 'their',\n", " 'artistic',\n", " 'achievements',\n", " '.'],\n", " 'obj'),\n", " (['spurning',\n", " 'her',\n", " \"mother's\",\n", " 'insistence',\n", " 'that',\n", " 'she',\n", " 'get',\n", " 'on',\n", " 'with',\n", " 'her',\n", " 'life',\n", " ',',\n", " 'mary',\n", " 'is',\n", " 'thrown',\n", " 'out',\n", " 'of',\n", " 'the',\n", " 'house',\n", " ',',\n", " 'rejected',\n", " 'by',\n", " 'joe',\n", " ',',\n", " 'and',\n", " 'expelled',\n", " 'from',\n", " 'school',\n", " 'as',\n", " 'she',\n", " 'grows',\n", " 'larger',\n", " 'with',\n", " 'child',\n", " '.'],\n", " 'obj'),\n", " (['amitabh',\n", " \"can't\",\n", " 'believe',\n", " 'the',\n", " 'board',\n", " 'of',\n", " 'directors',\n", " 'and',\n", " 'his',\n", " 'mind',\n", " 'is',\n", " 'filled',\n", " 'with',\n", " 'revenge',\n", " 'and',\n", " 'what',\n", " 'better',\n", " 'revenge',\n", " 'than',\n", " 'robbing',\n", " 'the',\n", " 'bank',\n", " 'himself',\n", " ',',\n", " 'ironic',\n", " 'as',\n", " 'it',\n", " 'may',\n", " 'sound',\n", " '.'],\n", " 'obj'),\n", " (['she',\n", " ',',\n", " 'among',\n", " 'others',\n", " 'excentricities',\n", " ',',\n", " 'talks',\n", " 'to',\n", " 'a',\n", " 'small',\n", " 'rock',\n", " ',',\n", " 'gertrude',\n", " ',',\n", " 'like',\n", " 'if',\n", " 'she',\n", " 'was',\n", " 'alive',\n", " '.'],\n", " 'obj'),\n", " (['this',\n", " 'gives',\n", " 'the',\n", " 'girls',\n", " 'a',\n", " 'fair',\n", " 'chance',\n", " 'of',\n", " 'pulling',\n", " 'the',\n", " 'wool',\n", " 'over',\n", " 'their',\n", " 'eyes',\n", " 'using',\n", " 'their',\n", " 'sexiness',\n", " 'to',\n", " 'poach',\n", " 'any',\n", " 'last',\n", " 'vestige',\n", " 'of',\n", " 'common',\n", " 'sense',\n", " 'the',\n", " 'dons',\n", " 'might',\n", " 'have',\n", " 'had',\n", " '.'],\n", " 'obj'),\n", " (['styled',\n", " 'after',\n", " \"vh1's\",\n", " '\"',\n", " 'behind',\n", " 'the',\n", " 'music',\n", " ',',\n", " '\"',\n", " 'this',\n", " 'mockumentary',\n", " 'profiles',\n", " 'the',\n", " 'rise',\n", " 'and',\n", " 'fall',\n", " 'of',\n", " 'an',\n", " 'internet',\n", " 'startup',\n", " ',',\n", " 'called',\n", " 'icevan',\n", " '.',\n", " 'com',\n", " '.'],\n", " 'obj'),\n", " (['being',\n", " 'blue',\n", " 'is',\n", " 'not',\n", " 'his',\n", " 'only',\n", " 'predicament',\n", " ';',\n", " 'he',\n", " 'also',\n", " 'lacks',\n", " 'the',\n", " 'ability',\n", " 'to',\n", " 'outwardly',\n", " 'express',\n", " 'his',\n", " 'emotions',\n", " '.'],\n", " 'obj'),\n", " (['the',\n", " \"killer's\",\n", " 'clues',\n", " 'are',\n", " 'a',\n", " 'perversion',\n", " 'of',\n", " 'biblical',\n", " 'punishments',\n", " 'for',\n", " 'sins',\n", " ':',\n", " 'stoning',\n", " ',',\n", " 'burning',\n", " ',',\n", " 'decapitation',\n", " '.'],\n", " 'obj'),\n", " (['david',\n", " 'is',\n", " 'a',\n", " 'painter',\n", " 'with',\n", " \"painter's\",\n", " 'block',\n", " 'who',\n", " 'takes',\n", " 'a',\n", " 'job',\n", " 'as',\n", " 'a',\n", " 'waiter',\n", " 'to',\n", " 'get',\n", " 'some',\n", " 'inspiration',\n", " '.'],\n", " 'obj'),\n", " (['women', 'craved', 'him', 'and', 'men', 'wanted', 'to', 'be', 'him', '.'],\n", " 'obj'),\n", " (['set',\n", " 'on',\n", " 'an',\n", " 'island',\n", " 'off',\n", " 'the',\n", " 'coast',\n", " 'of',\n", " 'florida',\n", " ',',\n", " 'a',\n", " 'techno',\n", " 'rave',\n", " 'party',\n", " 'attracts',\n", " 'a',\n", " 'diverse',\n", " 'group',\n", " 'of',\n", " 'college',\n", " 'coeds',\n", " 'and',\n", " 'a',\n", " 'coast',\n", " 'guard',\n", " 'officer',\n", " '.'],\n", " 'obj'),\n", " (['lesson',\n", " 'to',\n", " 'be',\n", " 'learned',\n", " ':',\n", " 'never',\n", " ',',\n", " 'never',\n", " 'mess',\n", " 'with',\n", " '\"',\n", " 'the',\n", " 'gay',\n", " 'mafia',\n", " '!',\n", " '\"'],\n", " 'obj'),\n", " (['the',\n", " 'theme',\n", " 'of',\n", " 'the',\n", " 'film',\n", " 'simultaneously',\n", " 'addresses',\n", " 'the',\n", " 'similarities',\n", " 'between',\n", " 'the',\n", " 'two',\n", " 'factions',\n", " 'of',\n", " 'law',\n", " 'and',\n", " 'crime',\n", " 'while',\n", " 'revealing',\n", " 'the',\n", " 'similarities',\n", " 'between',\n", " 'the',\n", " 'two',\n", " 'brothers',\n", " '.'],\n", " 'obj'),\n", " ([\"they're\",\n", " 'jewish',\n", " ',',\n", " \"they're\",\n", " 'grandmothers',\n", " ',',\n", " 'and',\n", " \"they're\",\n", " 'lesbians',\n", " '.'],\n", " 'obj'),\n", " (['but',\n", " \"he's\",\n", " 'neglecting',\n", " 'his',\n", " 'work',\n", " ',',\n", " 'carping',\n", " 'at',\n", " 'his',\n", " 'mom',\n", " ',',\n", " 'and',\n", " 'behaving',\n", " 'badly',\n", " 'toward',\n", " 'his',\n", " 'loyal',\n", " 'friend',\n", " 'bobbi',\n", " '.'],\n", " 'obj'),\n", " (['with',\n", " 'all',\n", " 'this',\n", " 'going',\n", " 'on',\n", " ',',\n", " \"gerry's\",\n", " 'estranged',\n", " 'wife',\n", " 'margaret',\n", " 'is',\n", " 'worried',\n", " 'for',\n", " 'her',\n", " \"daughter's\",\n", " 'safety',\n", " 'and',\n", " 'finds',\n", " 'herself',\n", " 'another',\n", " 'target',\n", " 'in',\n", " 'the',\n", " 'race',\n", " 'to',\n", " 'find',\n", " 'the',\n", " 'code',\n", " '.'],\n", " 'obj'),\n", " (['valento',\n", " 'feels',\n", " 'the',\n", " 'heat',\n", " 'and',\n", " 'turns',\n", " 'the',\n", " 'table',\n", " ':',\n", " 'he',\n", " 'makes',\n", " 'the',\n", " 'dupe',\n", " 'into',\n", " 'one',\n", " 'of',\n", " 'his',\n", " 'own',\n", " 'and',\n", " 'rubs',\n", " 'the',\n", " \"da's\",\n", " 'nose',\n", " 'in',\n", " 'it',\n", " '.'],\n", " 'obj'),\n", " (['saigon',\n", " ',',\n", " '1952',\n", " ',',\n", " 'a',\n", " 'beautiful',\n", " ',',\n", " 'exotic',\n", " ',',\n", " 'and',\n", " 'mysterious',\n", " 'city',\n", " 'caught',\n", " 'in',\n", " 'the',\n", " 'grips',\n", " 'of',\n", " 'the',\n", " 'vietnamese',\n", " 'war',\n", " 'of',\n", " 'liberation',\n", " 'from',\n", " 'the',\n", " 'french',\n", " 'colonial',\n", " 'powers',\n", " '.'],\n", " 'obj'),\n", " (['deep',\n", " 'in',\n", " 'the',\n", " 'northwest',\n", " ',',\n", " 'there',\n", " 'is',\n", " 'a',\n", " 'lone',\n", " 'ranch',\n", " 'tucked',\n", " 'away',\n", " 'so',\n", " 'purposefully',\n", " ',',\n", " 'the',\n", " 'only',\n", " 'way',\n", " 'to',\n", " 'find',\n", " 'it',\n", " 'is',\n", " 'by',\n", " 'not',\n", " 'looking',\n", " '.'],\n", " 'obj'),\n", " (['as',\n", " 'a',\n", " 'young',\n", " 'teenager',\n", " ',',\n", " 'he',\n", " 'finds',\n", " 'out',\n", " 'who',\n", " 'his',\n", " 'father',\n", " 'is',\n", " '.'],\n", " 'obj'),\n", " (['in',\n", " 'life',\n", " ',',\n", " \"there's\",\n", " 'silver',\n", " ',',\n", " 'and',\n", " \"there's\",\n", " 'lead',\n", " ',',\n", " 'says',\n", " 'rikki',\n", " 'ortega',\n", " ',',\n", " 'as',\n", " 'he',\n", " 'moves',\n", " 'to',\n", " 'be',\n", " 'king',\n", " 'of',\n", " 'the',\n", " 'street',\n", " 'in',\n", " '\"',\n", " 'Á',\n", " ';',\n", " 'nglio',\n", " ',',\n", " '\"',\n", " 'l',\n", " '.',\n", " 'a',\n", " '.',\n", " \"'s\",\n", " 'east',\n", " 'side',\n", " '.'],\n", " 'obj'),\n", " (['all',\n", " 'these',\n", " 'games',\n", " 'of',\n", " 'chasing',\n", " ',',\n", " 'rejecting',\n", " 'and',\n", " 'seducing',\n", " 'are',\n", " 'played',\n", " 'out',\n", " 'in',\n", " 'an',\n", " 'economically',\n", " 'and',\n", " 'spiritually',\n", " 'depressed',\n", " 'hong',\n", " 'kong',\n", " ',',\n", " 'without',\n", " 'much',\n", " 'gusto',\n", " '.'],\n", " 'obj'),\n", " (['television',\n", " 'made',\n", " 'him',\n", " 'famous',\n", " ',',\n", " 'but',\n", " 'his',\n", " 'biggest',\n", " 'hits',\n", " 'happened',\n", " 'off',\n", " 'screen',\n", " '.'],\n", " 'obj'),\n", " (['jordan',\n", " 'is',\n", " 'a',\n", " 'mom',\n", " 'who',\n", " 'is',\n", " 'on',\n", " 'a',\n", " 'life',\n", " 'long',\n", " 'search',\n", " 'for',\n", " 'true',\n", " 'faith',\n", " 'as',\n", " 'she',\n", " 'tries',\n", " 'to',\n", " 'protect',\n", " 'her',\n", " 'only',\n", " 'child',\n", " 'from',\n", " 'what',\n", " 'she',\n", " 'believes',\n", " 'is',\n", " 'injustice',\n", " '.'],\n", " 'obj'),\n", " ([\"'bloody\",\n", " \"magic'\",\n", " 'is',\n", " 'the',\n", " 'story',\n", " 'of',\n", " 'zack',\n", " ',',\n", " 'an',\n", " 'eleven',\n", " 'year',\n", " 'old',\n", " 'school',\n", " 'boy',\n", " ',',\n", " \"who's\",\n", " 'family',\n", " 'is',\n", " 'visited',\n", " 'by',\n", " 'three',\n", " 'debt',\n", " 'collectors',\n", " '.'],\n", " 'obj'),\n", " (['however',\n", " ',',\n", " 'jane',\n", " ',',\n", " \"wendy's\",\n", " '12-year-old',\n", " 'daughter',\n", " ',',\n", " 'sees',\n", " 'it',\n", " 'all',\n", " 'as',\n", " 'make',\n", " 'believe',\n", " 'and',\n", " 'refuses',\n", " 'to',\n", " 'believe',\n", " 'in',\n", " 'the',\n", " 'tales',\n", " '.'],\n", " 'obj'),\n", " (['called',\n", " '\"',\n", " 'an',\n", " 'elegant',\n", " 'documentary',\n", " '\"',\n", " 'by',\n", " 'sundance',\n", " 'and',\n", " '\"',\n", " 'eloquent',\n", " 'and',\n", " 'deeply',\n", " 'moving',\n", " '\"',\n", " 'by',\n", " 'the',\n", " 'la',\n", " 'times',\n", " ',',\n", " 'toyo',\n", " 'miyatake',\n", " ':',\n", " 'infinite',\n", " 'shades',\n", " 'of',\n", " 'gray',\n", " 'is',\n", " 'a',\n", " 'penetrating',\n", " 'portrait',\n", " 'of',\n", " 'this',\n", " \"photographer's\",\n", " 'search',\n", " 'for',\n", " 'truth',\n", " 'and',\n", " 'beauty',\n", " 'in',\n", " 'a',\n", " 'world',\n", " 'of',\n", " 'impermanence',\n", " '.'],\n", " 'obj'),\n", " (['straight',\n", " 'up',\n", " ':',\n", " 'helicopters',\n", " 'in',\n", " 'action',\n", " 'will',\n", " 'take',\n", " 'audiences',\n", " 'on',\n", " 'a',\n", " 'series',\n", " 'of',\n", " 'aerial',\n", " 'adventures',\n", " '.'],\n", " 'obj'),\n", " (['a',\n", " 'lapp',\n", " 'woman',\n", " 'anni',\n", " 'gives',\n", " 'a',\n", " 'shelter',\n", " 'to',\n", " 'both',\n", " 'of',\n", " 'them',\n", " 'at',\n", " 'her',\n", " 'farm',\n", " '.'],\n", " 'obj'),\n", " (['it',\n", " 'also',\n", " 'touches',\n", " 'on',\n", " 'the',\n", " 'encroachment',\n", " 'of',\n", " 'christianity',\n", " 'brought',\n", " 'by',\n", " 'the',\n", " 'missionaries',\n", " ',',\n", " 'which',\n", " 'is',\n", " 'at',\n", " 'odds',\n", " 'with',\n", " \"mepe's\",\n", " 'tribal',\n", " 'and',\n", " 'traditional',\n", " 'roots',\n", " '.'],\n", " 'obj'),\n", " (['a',\n", " 'set',\n", " 'of',\n", " 'grisly',\n", " 'murders',\n", " 'brings',\n", " 'fbi',\n", " 'agent',\n", " 'will',\n", " 'graham',\n", " '(',\n", " 'norton',\n", " ')',\n", " 'out',\n", " 'of',\n", " 'retirement',\n", " 'and',\n", " 'puts',\n", " 'him',\n", " 'in',\n", " 'search',\n", " 'of',\n", " 'an',\n", " 'atrocious',\n", " 'killer',\n", " '(',\n", " 'fiennes',\n", " ')',\n", " \"who's\",\n", " 'driven',\n", " 'by',\n", " 'the',\n", " 'image',\n", " 'of',\n", " 'a',\n", " 'painting',\n", " '.'],\n", " 'obj'),\n", " (['soon',\n", " ',',\n", " 'the',\n", " 'team',\n", " 'begins',\n", " 'to',\n", " 'suspect',\n", " 'that',\n", " \"knowles'\",\n", " 'main',\n", " 'objective',\n", " 'is',\n", " 'actually',\n", " 'to',\n", " 'recover',\n", " 'the',\n", " 'prototype',\n", " 'of',\n", " 'a',\n", " 'dna',\n", " 'testing',\n", " 'machine',\n", " 'called',\n", " 'the',\n", " 'huxley',\n", " 'project',\n", " ',',\n", " 'which',\n", " 'his',\n", " 'company',\n", " 'has',\n", " 'spent',\n", " 'years',\n", " 'and',\n", " 'millions',\n", " 'of',\n", " 'dollars',\n", " 'developing',\n", " '.'],\n", " 'obj'),\n", " (['his',\n", " 'mother',\n", " 'persuades',\n", " 'a',\n", " 'renowned',\n", " 'entomologist',\n", " 'to',\n", " 'take',\n", " 'them',\n", " 'on',\n", " 'a',\n", " 'trip',\n", " 'to',\n", " 'the',\n", " 'jungle',\n", " 'to',\n", " 'search',\n", " 'for',\n", " 'the',\n", " 'butterfly',\n", " ',',\n", " 'leading',\n", " 'to',\n", " 'an',\n", " 'adventure',\n", " 'that',\n", " 'will',\n", " 'transform',\n", " 'their',\n", " 'lives',\n", " '.'],\n", " 'obj'),\n", " (['with',\n", " 'a',\n", " 'rare',\n", " 'gift',\n", " 'for',\n", " 'melding',\n", " 'subjectivity',\n", " 'with',\n", " 'biographical',\n", " 'facts',\n", " ',',\n", " 'má',\n", " ';',\n", " 'rton',\n", " 'brings',\n", " 'sabina',\n", " 'spielrein',\n", " 'back',\n", " 'to',\n", " 'life',\n", " ',',\n", " 'body',\n", " 'and',\n", " 'soul',\n", " '.'],\n", " 'obj'),\n", " (['seeking',\n", " 'a',\n", " 'mental',\n", " 'escape',\n", " ',',\n", " 'simone',\n", " 'begins',\n", " 'to',\n", " 'tune',\n", " 'into',\n", " \"what's\",\n", " 'happening',\n", " 'with',\n", " 'the',\n", " 'other',\n", " 'couples',\n", " 'around',\n", " 'her',\n", " '.'],\n", " 'obj'),\n", " (['the',\n", " 'beatle',\n", " 'fan',\n", " 'is',\n", " 'a',\n", " 'drama',\n", " 'about',\n", " 'albert',\n", " ',',\n", " 'a',\n", " 'psychotic',\n", " 'prisoner',\n", " 'who',\n", " 'is',\n", " 'a',\n", " 'devoted',\n", " 'fan',\n", " 'of',\n", " 'john',\n", " 'lennon',\n", " 'and',\n", " 'the',\n", " 'beatles',\n", " '.'],\n", " 'obj'),\n", " (['then',\n", " ',',\n", " 'in',\n", " '1974',\n", " ',',\n", " 'something',\n", " 'incredible',\n", " 'happened',\n", " '-',\n", " 'they',\n", " 'fell',\n", " 'in',\n", " 'love',\n", " '.'],\n", " 'obj'),\n", " (['on',\n", " 'her',\n", " 'deathbed',\n", " ',',\n", " 'candice',\n", " 'klein',\n", " 'accidentally',\n", " 'asks',\n", " 'the',\n", " 'question',\n", " ',',\n", " '\"',\n", " 'what',\n", " 'did',\n", " 'i',\n", " 'ever',\n", " 'do',\n", " 'to',\n", " 'deserve',\n", " 'this',\n", " '?',\n", " '\"'],\n", " 'obj'),\n", " (['shot',\n", " 'as',\n", " 'a',\n", " '\"',\n", " 'behind-the-scenes',\n", " '\"',\n", " 'look',\n", " 'at',\n", " 'how',\n", " 'a',\n", " 'fictional',\n", " 'kung-fu',\n", " 'movie',\n", " 'is',\n", " 'made',\n", " ',',\n", " 'the',\n", " 'film',\n", " 'is',\n", " 'basically',\n", " 'a',\n", " 'movie',\n", " 'about',\n", " 'the',\n", " 'making',\n", " 'of',\n", " 'a',\n", " 'movie',\n", " '.'],\n", " 'obj'),\n", " (['before',\n", " 'the',\n", " 'investigation',\n", " 'ends',\n", " ',',\n", " \"we've\",\n", " 'met',\n", " 'boyfriends',\n", " ',',\n", " 'a',\n", " 'drug',\n", " 'dealer',\n", " ',',\n", " \"alicia's\",\n", " 'mom',\n", " ',',\n", " \"hadley's\",\n", " 'dad',\n", " ',',\n", " 'nurses',\n", " ',',\n", " 'doctors',\n", " ',',\n", " 'and',\n", " 'an',\n", " 'orderly',\n", " '.'],\n", " 'obj'),\n", " (['but',\n", " 'what',\n", " 'exactly',\n", " 'is',\n", " 'good',\n", " '&',\n", " ';',\n", " 'what',\n", " 'exactly',\n", " 'is',\n", " 'evil',\n", " '?'],\n", " 'obj'),\n", " (['the',\n", " 'movie',\n", " 'takes',\n", " 'place',\n", " 'in',\n", " 'mexico',\n", " ',',\n", " '2002',\n", " '(',\n", " 'based',\n", " 'on',\n", " 'a',\n", " 'story',\n", " 'from',\n", " 'the',\n", " \"1800's\",\n", " ')',\n", " '.'],\n", " 'obj'),\n", " ([\"rainone's\",\n", " 'love',\n", " 'affair',\n", " 'with',\n", " 'singing',\n", " 'sensation',\n", " 'kelly',\n", " 'mcguire',\n", " 'whom',\n", " 'he',\n", " 'discovered',\n", " 'and',\n", " 'his',\n", " 'near',\n", " 'demise',\n", " 'by',\n", " 'the',\n", " 'hands',\n", " 'of',\n", " 'his',\n", " 'own',\n", " 'proté',\n", " ';',\n", " 'gé',\n", " ';',\n", " 'vincent',\n", " 'riccola',\n", " 'is',\n", " 'the',\n", " 'juice',\n", " 'that',\n", " 'fuels',\n", " 'this',\n", " 'roller',\n", " 'coaster',\n", " 'ride',\n", " 'through',\n", " 'two',\n", " 'debauchery-filled',\n", " 'decades',\n", " 'of',\n", " 'greed',\n", " ',',\n", " 'sex',\n", " ',',\n", " 'drugs',\n", " 'and',\n", " 'rock',\n", " 'and',\n", " 'roll',\n", " '.'],\n", " 'obj'),\n", " (['trapped',\n", " 'in',\n", " 'a',\n", " 'lovers',\n", " 'triangle',\n", " 'and',\n", " 'ruthless',\n", " 'game',\n", " 'of',\n", " 'lust',\n", " ',',\n", " 'greed',\n", " ',',\n", " 'and',\n", " 'betrayal',\n", " 'we',\n", " 'follow',\n", " 'one',\n", " \"woman's\",\n", " 'hypnotic',\n", " 'journey',\n", " 'to',\n", " 'discover',\n", " 'her',\n", " 'true',\n", " 'self',\n", " '.',\n", " '.',\n", " '.'],\n", " 'obj'),\n", " (['decent-but-dull',\n", " 'dek',\n", " 'loves',\n", " 'shirley',\n", " ',',\n", " 'so',\n", " 'much',\n", " 'so',\n", " 'that',\n", " 'he',\n", " 'humiliates',\n", " 'her',\n", " 'by',\n", " 'proposing',\n", " 'without',\n", " 'warning',\n", " 'on',\n", " 'national',\n", " 'television',\n", " '.'],\n", " 'obj'),\n", " (['since',\n", " 'all',\n", " 'her',\n", " 'architects',\n", " 'are',\n", " 'either',\n", " 'busy',\n", " 'otherwise',\n", " 'or',\n", " 'too',\n", " 'conservative',\n", " 'in',\n", " 'style',\n", " ',',\n", " 'this',\n", " 'ambivalent',\n", " 'honour',\n", " 'falls',\n", " 'to',\n", " 'numerobis',\n", " '.'],\n", " 'obj'),\n", " ([\"there's\",\n", " 'a',\n", " 'story',\n", " 'that',\n", " 'goes',\n", " 'around',\n", " 'the',\n", " 'town',\n", " 'of',\n", " 'darkness',\n", " 'falls',\n", " 'about',\n", " 'her',\n", " ',',\n", " 'and',\n", " \"she's\",\n", " 'called',\n", " 'the',\n", " 'tooth',\n", " 'fairy',\n", " '.'],\n", " 'obj'),\n", " (['a',\n", " 'strange',\n", " 'film',\n", " 'employing',\n", " 'old',\n", " 'home',\n", " 'movies',\n", " 'and',\n", " 'newly',\n", " 'shot',\n", " 'footage',\n", " 'in',\n", " 'an',\n", " 'effort',\n", " 'to',\n", " 'expose',\n", " 'one',\n", " 'hungarian',\n", " 'family',\n", " 'and',\n", " 'their',\n", " 'mutiple',\n", " 'problems',\n", " 'from',\n", " 'the',\n", " '1940s',\n", " 'to',\n", " 'current',\n", " '.'],\n", " 'obj'),\n", " (['matsumoto',\n", " 'and',\n", " 'sawako',\n", " 'were',\n", " 'a',\n", " 'happy',\n", " 'couple',\n", " ',',\n", " 'but',\n", " 'meddling',\n", " 'parents',\n", " 'and',\n", " 'chase',\n", " 'for',\n", " 'success',\n", " 'push',\n", " 'the',\n", " 'boy',\n", " 'to',\n", " 'a',\n", " 'tragic',\n", " 'choice',\n", " '.'],\n", " 'obj'),\n", " (['elvis',\n", " 'teams',\n", " 'up',\n", " 'with',\n", " 'jack',\n", " '(',\n", " 'ossie',\n", " 'davis',\n", " ')',\n", " ',',\n", " 'a',\n", " 'fellow',\n", " 'nursing',\n", " 'home',\n", " 'resident',\n", " 'who',\n", " 'thinks',\n", " 'that',\n", " 'he',\n", " 'is',\n", " 'actually',\n", " 'president',\n", " 'john',\n", " 'f',\n", " '.',\n", " 'kennedy',\n", " ',',\n", " 'and',\n", " 'the',\n", " 'two',\n", " 'valiant',\n", " 'old',\n", " 'codgers',\n", " 'sally',\n", " 'forth',\n", " 'to',\n", " 'battle',\n", " 'an',\n", " 'evil',\n", " 'egyptian',\n", " 'entity',\n", " 'who',\n", " 'has',\n", " 'chosen',\n", " 'their',\n", " 'long-term',\n", " 'care',\n", " 'facility',\n", " 'as',\n", " 'his',\n", " 'happy',\n", " 'hunting',\n", " 'grounds',\n", " '.'],\n", " 'obj'),\n", " (['everywhere',\n", " 'he',\n", " 'goes',\n", " 'he',\n", " 'is',\n", " 'plagued',\n", " 'by',\n", " 'cats',\n", " 'and',\n", " 'when',\n", " 'by',\n", " 'chance',\n", " 'he',\n", " 'meets',\n", " 'carol',\n", " 'on',\n", " 'a',\n", " 'lonely',\n", " 'highway',\n", " 'they',\n", " 'must',\n", " 'begin',\n", " 'a',\n", " 'journey',\n", " ',',\n", " 'avoiding',\n", " 'the',\n", " 'mysterious',\n", " 'private',\n", " 'detective',\n", " 'mr',\n", " 'barlow',\n", " 'and',\n", " 'the',\n", " 'terrifying',\n", " 'inhuman',\n", " 'creature',\n", " 'jack',\n", " ',',\n", " 'to',\n", " 'uncover',\n", " 'the',\n", " 'dark',\n", " 'truth',\n", " 'to',\n", " \"charlie's\",\n", " 'life',\n", " '.'],\n", " 'obj'),\n", " (['used',\n", " 'to',\n", " 'living',\n", " 'in',\n", " 'poverty',\n", " ',',\n", " 'it',\n", " 'seemed',\n", " 'impossible',\n", " 'for',\n", " 'cass',\n", " 'and',\n", " 'cary',\n", " 'to',\n", " 'have',\n", " 'a',\n", " 'comfortable',\n", " 'and',\n", " 'bountiful',\n", " 'life',\n", " 'until',\n", " 'doqa',\n", " 'gracia',\n", " 'comes',\n", " 'to',\n", " 'bring',\n", " 'them',\n", " 'into',\n", " 'her',\n", " 'home',\n", " '.'],\n", " 'obj'),\n", " (['the',\n", " 'story',\n", " 'of',\n", " 'a',\n", " 'normal',\n", " 'family',\n", " 'in',\n", " 'which',\n", " 'come',\n", " 'out',\n", " 'the',\n", " 'dreams',\n", " 'of',\n", " 'those',\n", " 'who',\n", " 'have',\n", " 'lost',\n", " 'their',\n", " 'possibilities',\n", " 'and',\n", " 'of',\n", " 'those',\n", " 'who',\n", " 'want',\n", " 'to',\n", " 'realize',\n", " 'them',\n", " '.'],\n", " 'obj'),\n", " (['with',\n", " 'grit',\n", " 'and',\n", " 'determination',\n", " 'molly',\n", " 'guides',\n", " 'the',\n", " 'girls',\n", " 'on',\n", " 'an',\n", " 'epic',\n", " 'journey',\n", " ',',\n", " 'one',\n", " 'step',\n", " 'ahead',\n", " 'of',\n", " 'the',\n", " 'authorities',\n", " ',',\n", " 'over',\n", " '1',\n", " ',',\n", " '500',\n", " 'miles',\n", " 'of',\n", " \"australia's\",\n", " 'outback',\n", " 'in',\n", " 'search',\n", " 'of',\n", " 'the',\n", " 'rabbit-proof',\n", " 'fence',\n", " 'that',\n", " 'bisects',\n", " 'the',\n", " 'continent',\n", " 'and',\n", " 'will',\n", " 'lead',\n", " 'them',\n", " 'home',\n", " '.'],\n", " 'obj'),\n", " (['they',\n", " 'nevertherless',\n", " 'feel',\n", " 'responsible',\n", " 'to',\n", " 'protect',\n", " 'the',\n", " 'flag',\n", " 'until',\n", " \"monday's\",\n", " 'ceremony',\n", " '.'],\n", " 'obj'),\n", " (['the',\n", " 'doctor',\n", " 'realizes',\n", " \"it''s\",\n", " 'a',\n", " 'love',\n", " 'virus',\n", " 'so',\n", " 'he',\n", " 'advises',\n", " 'him',\n", " 'to',\n", " 'woo',\n", " 'the',\n", " 'girl',\n", " 'somehow',\n", " ',',\n", " 'not',\n", " 'realizing',\n", " 'that',\n", " 'munnabhai',\n", " 'has',\n", " 'fallen',\n", " 'for',\n", " 'none',\n", " 'other',\n", " 'than',\n", " 'his',\n", " 'own',\n", " 'younger',\n", " 'sister',\n", " 'komal',\n", " '.'],\n", " 'obj'),\n", " (['however',\n", " ',',\n", " 'he',\n", " 'can',\n", " 'only',\n", " 'inhabit',\n", " 'the',\n", " 'body',\n", " 'of',\n", " 'a',\n", " 'child',\n", " 'for',\n", " 'a',\n", " 'short',\n", " 'time',\n", " '.'],\n", " 'obj'),\n", " (['years',\n", " 'later',\n", " ',',\n", " 'on',\n", " 'a',\n", " 'hunting',\n", " 'trip',\n", " 'in',\n", " 'the',\n", " 'maine',\n", " 'woods',\n", " ',',\n", " 'they',\n", " 'are',\n", " 'overtaken',\n", " 'by',\n", " 'a',\n", " 'blizzard',\n", " ',',\n", " 'a',\n", " 'vicious',\n", " 'storm',\n", " 'in',\n", " 'which',\n", " 'something',\n", " 'much',\n", " 'more',\n", " 'ominous',\n", " 'moves',\n", " '.'],\n", " 'obj'),\n", " (['consequently',\n", " ',',\n", " 'what',\n", " 'begins',\n", " 'as',\n", " 'an',\n", " 'enthusiastic',\n", " 'road',\n", " 'trip',\n", " 'is',\n", " 'soon',\n", " 'plagued',\n", " 'with',\n", " 'mysterious',\n", " 'roadside',\n", " 'obstacles',\n", " 'that',\n", " 'threaten',\n", " 'to',\n", " 'prevent',\n", " 'the',\n", " 'boys',\n", " 'from',\n", " 'ever',\n", " 'making',\n", " 'it',\n", " 'to',\n", " 'the',\n", " 'competition',\n", " '.'],\n", " 'obj'),\n", " (['when',\n", " 'she',\n", " 'gets',\n", " 'into',\n", " 'trouble',\n", " 'with',\n", " 'the',\n", " 'police',\n", " 'simon',\n", " 'represses',\n", " 'his',\n", " 'death',\n", " 'wish',\n", " 'and',\n", " 'decides',\n", " 'to',\n", " 'help',\n", " 'her',\n", " 'out',\n", " '.'],\n", " 'obj'),\n", " (['chon',\n", " 'then',\n", " 'travels',\n", " 'to',\n", " 'new',\n", " 'york',\n", " 'for',\n", " 'roy',\n", " \"o'bannon\",\n", " '(',\n", " 'owen',\n", " 'wilson',\n", " ')',\n", " '.'],\n", " 'obj'),\n", " (['not',\n", " 'only',\n", " 'must',\n", " 'they',\n", " 'overcome',\n", " 'an',\n", " 'enemy',\n", " 'adept',\n", " 'at',\n", " 'technological',\n", " 'witchery',\n", " ',',\n", " 'they',\n", " 'must',\n", " 'overcome',\n", " 'the',\n", " 'curse',\n", " 'that',\n", " 'marks',\n", " 'their',\n", " 'destiny',\n", " '.'],\n", " 'obj'),\n", " (['their',\n", " 'life',\n", " 'becomes',\n", " 'less',\n", " 'ordinary',\n", " 'when',\n", " 'they',\n", " 'encounter',\n", " 'herb',\n", " ',',\n", " 'a',\n", " 'mischievous',\n", " 'and',\n", " 'malevolent',\n", " 'geek',\n", " '.'],\n", " 'obj'),\n", " (['they', 'call', 'themselves', 'd', '.', 'e', '.', 'b', '.', 's', '.'],\n", " 'obj'),\n", " (['the',\n", " 'story',\n", " 'starts',\n", " 'with',\n", " 'hakimi',\n", " ',',\n", " 'a',\n", " 'freelance',\n", " 'scriptwriter',\n", " 'who',\n", " 'is',\n", " 'on',\n", " 'his',\n", " 'way',\n", " 'to',\n", " 'send',\n", " 'his',\n", " '7-year-old',\n", " 'daughter',\n", " ',',\n", " 'imelda',\n", " ',',\n", " 'to',\n", " 'his',\n", " \"ex-wife's\",\n", " 'house',\n", " 'on',\n", " 'one',\n", " 'stormy',\n", " 'night',\n", " '.'],\n", " 'obj'),\n", " (['they',\n", " 'follow',\n", " 'leads',\n", " ',',\n", " 'informants',\n", " 'turn',\n", " 'up',\n", " 'dead',\n", " ',',\n", " \"nick's\",\n", " 'wife',\n", " 'is',\n", " 'unhappy',\n", " \"he's\",\n", " 'back',\n", " 'on',\n", " 'the',\n", " 'street',\n", " ',',\n", " \"henry's\",\n", " 'protective',\n", " 'of',\n", " 'the',\n", " 'dead',\n", " \"cop's\",\n", " 'wife',\n", " '.'],\n", " 'obj'),\n", " (['the',\n", " 'second',\n", " 'part',\n", " 'of',\n", " 'aki',\n", " 'kaurismä',\n", " ';',\n", " \"ki's\",\n", " '\"',\n", " 'finland',\n", " '\"',\n", " 'trilogy',\n", " ',',\n", " 'the',\n", " 'film',\n", " 'follows',\n", " 'a',\n", " 'man',\n", " 'who',\n", " 'arrives',\n", " 'in',\n", " 'helsinki',\n", " 'and',\n", " 'gets',\n", " 'beaten',\n", " 'up',\n", " 'so',\n", " 'severely',\n", " 'he',\n", " 'develops',\n", " 'amnesia',\n", " '.'],\n", " 'obj'),\n", " (['soon',\n", " 'after',\n", " 'the',\n", " 'accident',\n", " ',',\n", " 'the',\n", " 'survivors',\n", " 'of',\n", " 'the',\n", " 'accident',\n", " 'start',\n", " 'dropping',\n", " 'like',\n", " 'flies',\n", " '.'],\n", " 'obj'),\n", " (['edgar',\n", " 'becomes',\n", " 'intent',\n", " 'on',\n", " 'laying',\n", " 'down',\n", " 'some',\n", " 'new',\n", " 'rules',\n", " 'and',\n", " 'turning',\n", " 'his',\n", " 'coddled',\n", " 'son',\n", " 'into',\n", " 'someone',\n", " 'who',\n", " 'can',\n", " 'take',\n", " 'on',\n", " 'the',\n", " 'family',\n", " 'farm',\n", " '.'],\n", " 'obj'),\n", " (['bound',\n", " 'by',\n", " 'a',\n", " 'long',\n", " 'red',\n", " 'cord',\n", " ',',\n", " 'a',\n", " 'young',\n", " 'couple',\n", " 'wanders',\n", " 'in',\n", " 'search',\n", " 'of',\n", " 'something',\n", " 'they',\n", " 'have',\n", " 'forgotten',\n", " '.'],\n", " 'obj'),\n", " (['sudden',\n", " 'fame',\n", " 'does',\n", " 'not',\n", " 'seem',\n", " 'to',\n", " 'solve',\n", " 'everything',\n", " ',',\n", " 'however',\n", " '.'],\n", " 'obj'),\n", " (['with',\n", " 'no',\n", " 'option',\n", " ',',\n", " 'joe',\n", " 'and',\n", " 'katsuragi',\n", " 'must',\n", " 'use',\n", " 'their',\n", " 'martial',\n", " 'arts',\n", " 'skills',\n", " 'to',\n", " 'fight',\n", " 'in',\n", " 'the',\n", " 'muscle',\n", " 'dome',\n", " '.'],\n", " 'obj'),\n", " (['drawing',\n", " 'from',\n", " 'his',\n", " 'time',\n", " 'with',\n", " 'the',\n", " 'kids',\n", " ',',\n", " 'he',\n", " 'writes',\n", " 'a',\n", " 'story',\n", " 'about',\n", " 'children',\n", " 'who',\n", " \"don't\",\n", " 'want',\n", " 'to',\n", " 'grow',\n", " 'up',\n", " '.'],\n", " 'obj'),\n", " ([\"she's\",\n", " 'an',\n", " 'artist',\n", " ',',\n", " 'but',\n", " \"hasn't\",\n", " 'picked',\n", " 'up',\n", " 'a',\n", " 'brush',\n", " 'in',\n", " 'a',\n", " 'year',\n", " '.'],\n", " 'obj'),\n", " (['when',\n", " 'his',\n", " 'daughter',\n", " 'is',\n", " 'kidnapped',\n", " 'and',\n", " 'held',\n", " 'in',\n", " 'exchange',\n", " 'for',\n", " 'priceless',\n", " 'diamonds',\n", " ',',\n", " 'the',\n", " 'leader',\n", " 'of',\n", " 'a',\n", " 'crew',\n", " 'of',\n", " 'highly',\n", " 'skilled',\n", " 'urban',\n", " 'thieves',\n", " '(',\n", " 'dmx',\n", " ')',\n", " 'forges',\n", " 'an',\n", " 'unlikely',\n", " 'alliance',\n", " 'with',\n", " 'a',\n", " 'taiwanese',\n", " 'intelligence',\n", " 'officer',\n", " '(',\n", " 'jet',\n", " 'li',\n", " ')',\n", " 'to',\n", " 'rescue',\n", " 'her',\n", " '.'],\n", " 'obj'),\n", " (['\"',\n", " 'garmento',\n", " '\"',\n", " 'tells',\n", " 'the',\n", " 'other',\n", " 'side',\n", " 'of',\n", " 'the',\n", " 'story',\n", " ',',\n", " 'with',\n", " 'a',\n", " 'dark',\n", " 'and',\n", " 'satirical',\n", " 'look',\n", " 'at',\n", " 'new',\n", " \"york's\",\n", " 'wholesale',\n", " 'garment',\n", " 'industry',\n", " ',',\n", " 'where',\n", " 'shady',\n", " 'deals',\n", " 'are',\n", " 'made',\n", " 'for',\n", " 'a',\n", " 'buck',\n", " 'and',\n", " 'ruthlessness',\n", " 'is',\n", " 'a',\n", " 'prerequisite',\n", " 'for',\n", " 'career',\n", " 'success',\n", " '.'],\n", " 'obj'),\n", " (['rudy',\n", " 'yellowshirt',\n", " 'is',\n", " 'an',\n", " 'investigator',\n", " 'with',\n", " 'the',\n", " 'police',\n", " 'department',\n", " 'and',\n", " 'witnesses',\n", " 'firsthand',\n", " 'the',\n", " 'painful',\n", " 'legacy',\n", " 'of',\n", " 'indian',\n", " 'existence',\n", " '.'],\n", " 'obj'),\n", " (['journeying',\n", " 'from',\n", " 'the',\n", " 'vietnam',\n", " 'war',\n", " 'to',\n", " 'pulaski',\n", " ',',\n", " 'tennessee',\n", " 'and',\n", " 'back',\n", " 'to',\n", " 'vietnam',\n", " ',',\n", " 'daughter',\n", " 'from',\n", " 'danang',\n", " 'tensely',\n", " 'unfolds',\n", " 'as',\n", " 'cultural',\n", " 'differences',\n", " 'and',\n", " 'the',\n", " 'years',\n", " 'of',\n", " 'separation',\n", " 'take',\n", " 'their',\n", " 'toll',\n", " 'in',\n", " 'a',\n", " 'riveting',\n", " 'film',\n", " 'about',\n", " 'longing',\n", " 'and',\n", " 'the',\n", " 'personal',\n", " 'legacy',\n", " 'of',\n", " 'war',\n", " '.'],\n", " 'obj'),\n", " (['each',\n", " 'weekend',\n", " 'they',\n", " 'come',\n", " 'back',\n", " 'with',\n", " 'nothing',\n", " 'but',\n", " 'a',\n", " 'hangover',\n", " '.'],\n", " 'obj')]" ] }, "execution_count": 6, "metadata": {}, "output_type": "execute_result" } ], "source": [ "training_docs" ] }, { "cell_type": "code", "execution_count": 7, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "['.',\n", " 'and',\n", " 'just',\n", " 'enough',\n", " 'science',\n", " 'to',\n", " 'send',\n", " 'you',\n", " 'home',\n", " 'thinking',\n", " '.',\n", " 'it',\n", " 'is',\n", " 'not',\n", " 'a_NEG',\n", " 'mass-market_NEG',\n", " 'entertainment_NEG',\n", " 'but_NEG',\n", " 'an_NEG',\n", " 'uncompromising_NEG']" ] }, "execution_count": 7, "metadata": {}, "output_type": "execute_result" } ], "source": [ "all_words_neg[25:45]" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "#### Note how this sentiment analyzer is marking everything after a negation word with '_NEG'\n", "This is one of many ways we can determine sentiment" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### STEP 6: Use `unigram_word_feats` to get unigrams features" ] }, { "cell_type": "code", "execution_count": 8, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "83" ] }, "execution_count": 8, "metadata": {}, "output_type": "execute_result" } ], "source": [ "unigram_feats = sentim_analyzer.unigram_word_feats(all_words_neg, min_freq=4)\n", "len(unigram_feats)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### STEP 7: Use `add_feat_extractor` to get a feature-value representation of our data \n", "#### Apply to both `training_set` and `testing_set`" ] }, { "cell_type": "code", "execution_count": 62, "metadata": {}, "outputs": [], "source": [ "sentim_analyzer.add_feat_extractor(extract_unigram_feats, unigrams=unigram_feats)" ] }, { "cell_type": "code", "execution_count": 63, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "[({'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')]" ] }, "execution_count": 63, "metadata": {}, "output_type": "execute_result" } ], "source": [ "training_set = sentim_analyzer.apply_features(training_docs)\n", "training_set[:1]" ] }, { "cell_type": "code", "execution_count": 64, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "[({'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')]" ] }, "execution_count": 64, "metadata": {}, "output_type": "execute_result" } ], "source": [ "test_set = sentim_analyzer.apply_features(testing_docs)\n", "test_set[:1]" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### STEP 8: FINAL STEP!! We use Naive Bayes to create a trainer and FINALLY classify our data!" ] }, { "cell_type": "code", "execution_count": 65, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Training classifier\n" ] } ], "source": [ "trainer = NaiveBayesClassifier.train\n", "classifier = sentim_analyzer.train(trainer, training_set)" ] }, { "cell_type": "code", "execution_count": 66, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Evaluating NaiveBayesClassifier results...\n", "Accuracy: 0.8\n", "F-measure [obj]: 0.8\n", "F-measure [subj]: 0.8\n", "Precision [obj]: 0.8\n", "Precision [subj]: 0.8\n", "Recall [obj]: 0.8\n", "Recall [subj]: 0.8\n" ] } ], "source": [ "for key,value in sorted(sentim_analyzer.evaluate(test_set).items()):\n", " print('{0}: {1}'.format(key,value))" ] } ], "metadata": { "kernelspec": { "display_name": "Python 3", "language": "python", "name": "python3" }, "language_info": { "codemirror_mode": { "name": "ipython", "version": 3 }, "file_extension": ".py", "mimetype": "text/x-python", "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", "version": "3.7.3" } }, "nbformat": 4, "nbformat_minor": 2 }