Tag Archives: statistics

Text Classification for Sentiment Analysis – Eliminate Low Information Features

When your classification model has hundreds or thousands of features, as is the case for text categorization, it’s a good bet that many (if not most) of the features are low information. These are features that are common across all classes, and therefore contribute little information to the classification process. Individually they are harmless, but in aggregate, low information features can decrease performance.

Eliminating low information features gives your model clarity by removing noisy data. It can save you from overfitting and the curse of dimensionality. When you use only the higher information features, you can increase performance while also decreasing the size of the model, which results in less memory usage along with faster training and classification. Removing features may seem intuitively wrong, but wait till you see the results.

High Information Feature Selection

Using the same evaluate_classifier method as in the previous post on classifying with bigrams, I got the following results using the 10000 most informative words:

evaluating best word features
accuracy: 0.93
pos precision: 0.890909090909
pos recall: 0.98
neg precision: 0.977777777778
neg recall: 0.88
Most Informative Features
             magnificent = True              pos : neg    =     15.0 : 1.0
             outstanding = True              pos : neg    =     13.6 : 1.0
               insulting = True              neg : pos    =     13.0 : 1.0
              vulnerable = True              pos : neg    =     12.3 : 1.0
               ludicrous = True              neg : pos    =     11.8 : 1.0
                  avoids = True              pos : neg    =     11.7 : 1.0
             uninvolving = True              neg : pos    =     11.7 : 1.0
              astounding = True              pos : neg    =     10.3 : 1.0
             fascination = True              pos : neg    =     10.3 : 1.0
                 idiotic = True              neg : pos    =      9.8 : 1.0

Contrast this with the results from the first article on classification for sentiment analysis, where we use all the words as features:

evaluating single word features
accuracy: 0.728
pos precision: 0.651595744681
pos recall: 0.98
neg precision: 0.959677419355
neg recall: 0.476
Most Informative Features
         magnificent = True              pos : neg    =     15.0 : 1.0
         outstanding = True              pos : neg    =     13.6 : 1.0
           insulting = True              neg : pos    =     13.0 : 1.0
          vulnerable = True              pos : neg    =     12.3 : 1.0
           ludicrous = True              neg : pos    =     11.8 : 1.0
              avoids = True              pos : neg    =     11.7 : 1.0
         uninvolving = True              neg : pos    =     11.7 : 1.0
          astounding = True              pos : neg    =     10.3 : 1.0
         fascination = True              pos : neg    =     10.3 : 1.0
             idiotic = True              neg : pos    =      9.8 : 1.0

The accuracy is over 20% higher when using only the best 10000 words and pos precision has increased almost 24% while neg recall improved over 40%. These are huge increases with no reduction in pos recall and even a slight increase in neg precision. Here’s the full code I used to get these results, with an explanation below.

import collections, itertools
import nltk.classify.util, nltk.metrics
from nltk.classify import NaiveBayesClassifier
from nltk.corpus import movie_reviews, stopwords
from nltk.collocations import BigramCollocationFinder
from nltk.metrics import BigramAssocMeasures
from nltk.probability import FreqDist, ConditionalFreqDist

def evaluate_classifier(featx):
	negids = movie_reviews.fileids('neg')
	posids = movie_reviews.fileids('pos')

	negfeats = [(featx(movie_reviews.words(fileids=[f])), 'neg') for f in negids]
	posfeats = [(featx(movie_reviews.words(fileids=[f])), 'pos') for f in posids]

	negcutoff = len(negfeats)*3/4
	poscutoff = len(posfeats)*3/4

	trainfeats = negfeats[:negcutoff] + posfeats[:poscutoff]
	testfeats = negfeats[negcutoff:] + posfeats[poscutoff:]

	classifier = NaiveBayesClassifier.train(trainfeats)
	refsets = collections.defaultdict(set)
	testsets = collections.defaultdict(set)

	for i, (feats, label) in enumerate(testfeats):
			refsets[label].add(i)
			observed = classifier.classify(feats)
			testsets[observed].add(i)

	print 'accuracy:', nltk.classify.util.accuracy(classifier, testfeats)
	print 'pos precision:', nltk.metrics.precision(refsets['pos'], testsets['pos'])
	print 'pos recall:', nltk.metrics.recall(refsets['pos'], testsets['pos'])
	print 'neg precision:', nltk.metrics.precision(refsets['neg'], testsets['neg'])
	print 'neg recall:', nltk.metrics.recall(refsets['neg'], testsets['neg'])
	classifier.show_most_informative_features()

def word_feats(words):
	return dict([(word, True) for word in words])

print 'evaluating single word features'
evaluate_classifier(word_feats)

word_fd = FreqDist()
label_word_fd = ConditionalFreqDist()

for word in movie_reviews.words(categories=['pos']):
	word_fd.inc(word.lower())
	label_word_fd['pos'].inc(word.lower())

for word in movie_reviews.words(categories=['neg']):
	word_fd.inc(word.lower())
	label_word_fd['neg'].inc(word.lower())

# n_ii = label_word_fd[label][word]
# n_ix = word_fd[word]
# n_xi = label_word_fd[label].N()
# n_xx = label_word_fd.N()

pos_word_count = label_word_fd['pos'].N()
neg_word_count = label_word_fd['neg'].N()
total_word_count = pos_word_count + neg_word_count

word_scores = {}

for word, freq in word_fd.iteritems():
	pos_score = BigramAssocMeasures.chi_sq(label_word_fd['pos'][word],
		(freq, pos_word_count), total_word_count)
	neg_score = BigramAssocMeasures.chi_sq(label_word_fd['neg'][word],
		(freq, neg_word_count), total_word_count)
	word_scores[word] = pos_score + neg_score

best = sorted(word_scores.iteritems(), key=lambda (w,s): s, reverse=True)[:10000]
bestwords = set([w for w, s in best])

def best_word_feats(words):
	return dict([(word, True) for word in words if word in bestwords])

print 'evaluating best word features'
evaluate_classifier(best_word_feats)

def best_bigram_word_feats(words, score_fn=BigramAssocMeasures.chi_sq, n=200):
	bigram_finder = BigramCollocationFinder.from_words(words)
	bigrams = bigram_finder.nbest(score_fn, n)
	d = dict([(bigram, True) for bigram in bigrams])
	d.update(best_word_feats(words))
	return d

print 'evaluating best words + bigram chi_sq word features'
evaluate_classifier(best_bigram_word_feats)

Calculating Information Gain

To find the highest information features, we need to calculate information gain for each word. Information gain for classification is a measure of how common a feature is in a particular class compared to how common it is in all other classes. A word that occurs primarily in positive movie reviews and rarely in negative reviews is high information. For example, the presence of the word “magnificent” in a movie review is a strong indicator that the review is positive. That makes “magnificent” a high information word. Notice that the most informative features above did not change. That makes sense because the point is to use only the most informative features and ignore the rest.

One of the best metrics for information gain is chi square. NLTK includes this in the BigramAssocMeasures class in the metrics package. To use it, first we need to calculate a few frequencies for each word: its overall frequency and its frequency within each class. This is done with a FreqDist for overall frequency of words, and a ConditionalFreqDist where the conditions are the class labels. Once we have those numbers, we can score words with the BigramAssocMeasures.chi_sq function, then sort the words by score and take the top 10000. We then put these words into a set, and use a set membership test in our feature selection function to select only those words that appear in the set. Now each file is classified based on the presence of these high information words.

Signficant Bigrams

The code above also evaluates the inclusion of 200 significant bigram collocations. Here are the results:

evaluating best words + bigram chi_sq word features
accuracy: 0.92
pos precision: 0.913385826772
pos recall: 0.928
neg precision: 0.926829268293
neg recall: 0.912
Most Informative Features
             magnificent = True              pos : neg    =     15.0 : 1.0
             outstanding = True              pos : neg    =     13.6 : 1.0
               insulting = True              neg : pos    =     13.0 : 1.0
              vulnerable = True              pos : neg    =     12.3 : 1.0
       ('matt', 'damon') = True              pos : neg    =     12.3 : 1.0
          ('give', 'us') = True              neg : pos    =     12.3 : 1.0
               ludicrous = True              neg : pos    =     11.8 : 1.0
             uninvolving = True              neg : pos    =     11.7 : 1.0
                  avoids = True              pos : neg    =     11.7 : 1.0
    ('absolutely', 'no') = True              neg : pos    =     10.6 : 1.0

This shows that bigrams don’t matter much when using only high information words. In this case, the best way to evaluate the difference between including bigrams or not is to look at precision and recall. With the bigrams, you we get more uniform performance in each class. Without bigrams, precision and recall are less balanced. But the differences may depend on your particular data, so don’t assume these observations are always true.

Improving Feature Selection

The big lesson here is that improving feature selection will improve your classifier. Reducing dimensionality is one of the single best things you can do to improve classifier performance. It’s ok to throw away data if that data is not adding value. And it’s especially recommended when that data is actually making your model worse.

Text Classification for Sentiment Analysis – Stopwords and Collocations

Improving feature extraction can often have a significant positive impact on classifier accuracy (and precision and recall). In this article, I’ll be evaluating two modifications of the word_feats feature extraction method:

  1. filter out stopwords
  2. include bigram collocations

To do this effectively, we’ll modify the previous code so that we can use an arbitrary feature extractor function that takes the words in a file and returns the feature dictionary. As before, we’ll use these features to train a Naive Bayes Classifier.

import collections
import nltk.classify.util, nltk.metrics
from nltk.classify import NaiveBayesClassifier
from nltk.corpus import movie_reviews

def evaluate_classifier(featx):
	negids = movie_reviews.fileids('neg')
	posids = movie_reviews.fileids('pos')

	negfeats = [(featx(movie_reviews.words(fileids=[f])), 'neg') for f in negids]
	posfeats = [(featx(movie_reviews.words(fileids=[f])), 'pos') for f in posids]

	negcutoff = len(negfeats)*3/4
	poscutoff = len(posfeats)*3/4

	trainfeats = negfeats[:negcutoff] + posfeats[:poscutoff]
	testfeats = negfeats[negcutoff:] + posfeats[poscutoff:]

	classifier = NaiveBayesClassifier.train(trainfeats)
	refsets = collections.defaultdict(set)
	testsets = collections.defaultdict(set)

	for i, (feats, label) in enumerate(testfeats):
			refsets[label].add(i)
			observed = classifier.classify(feats)
			testsets[observed].add(i)

	print 'accuracy:', nltk.classify.util.accuracy(classifier, testfeats)
	print 'pos precision:', nltk.metrics.precision(refsets['pos'], testsets['pos'])
	print 'pos recall:', nltk.metrics.recall(refsets['pos'], testsets['pos'])
	print 'neg precision:', nltk.metrics.precision(refsets['neg'], testsets['neg'])
	print 'neg recall:', nltk.metrics.recall(refsets['neg'], testsets['neg'])
	classifier.show_most_informative_features()

Baseline Bag of Words Feature Extraction

Here’s the baseline feature extractor for bag of words feature selection.

def word_feats(words):
	return dict([(word, True) for word in words])

evaluate_classifier(word_feats)

The results are the same as in the previous articles, but I’ve included them here for reference:

accuracy: 0.728
pos precision: 0.651595744681
pos recall: 0.98
neg precision: 0.959677419355
neg recall: 0.476
Most Informative Features
         magnificent = True              pos : neg    =     15.0 : 1.0
         outstanding = True              pos : neg    =     13.6 : 1.0
           insulting = True              neg : pos    =     13.0 : 1.0
          vulnerable = True              pos : neg    =     12.3 : 1.0
           ludicrous = True              neg : pos    =     11.8 : 1.0
              avoids = True              pos : neg    =     11.7 : 1.0
         uninvolving = True              neg : pos    =     11.7 : 1.0
          astounding = True              pos : neg    =     10.3 : 1.0
         fascination = True              pos : neg    =     10.3 : 1.0
             idiotic = True              neg : pos    =      9.8 : 1.0

Stopword Filtering

Stopwords are words that are generally considered useless. Most search engines ignore these words because they are so common that including them would greatly increase the size of the index without improving precision or recall. NLTK comes with a stopwords corpus that includes a list of 128 english stopwords. Let’s see what happens when we filter out these words.

from nltk.corpus import stopwords
stopset = set(stopwords.words('english'))

def stopword_filtered_word_feats(words):
	return dict([(word, True) for word in words if word not in stopset])

evaluate_classifier(stopword_filtered_word_feats)

And the results for a stopword filtered bag of words are:

accuracy: 0.726
pos precision: 0.649867374005
pos recall: 0.98
neg precision: 0.959349593496
neg recall: 0.472

Accuracy went down .2%, and pos precision and neg recall dropped as well! Apparently stopwords add information to sentiment analysis classification. I did not include the most informative features since they did not change.

Bigram Collocations

As mentioned at the end of the article on precision and recall, it’s possible that including bigrams will improve classification accuracy. The hypothesis is that people say things like “not great”, which is a negative expression that the bag of words model could interpret as positive since it sees “great” as a separate word.

To find significant bigrams, we can use nltk.collocations.BigramCollocationFinder along with nltk.metrics.BigramAssocMeasures. The BigramCollocationFinder maintains 2 internal FreqDists, one for individual word frequencies, another for bigram frequencies. Once it has these frequency distributions, it can score individual bigrams using a scoring function provided by BigramAssocMeasures, such chi-square. These scoring functions measure the collocation correlation of 2 words, basically whether the bigram occurs about as frequently as each individual word.

import itertools
from nltk.collocations import BigramCollocationFinder
from nltk.metrics import BigramAssocMeasures

def bigram_word_feats(words, score_fn=BigramAssocMeasures.chi_sq, n=200):
	bigram_finder = BigramCollocationFinder.from_words(words)
	bigrams = bigram_finder.nbest(score_fn, n)
	return dict([(ngram, True) for ngram in itertools.chain(words, bigrams)])

evaluate_classifier(bigram_word_feats)

After some experimentation, I found that using the 200 best bigrams from each file produced great results:

accuracy: 0.816
pos precision: 0.753205128205
pos recall: 0.94
neg precision: 0.920212765957
neg recall: 0.692
Most Informative Features
         magnificent = True              pos : neg    =     15.0 : 1.0
         outstanding = True              pos : neg    =     13.6 : 1.0
           insulting = True              neg : pos    =     13.0 : 1.0
          vulnerable = True              pos : neg    =     12.3 : 1.0
   ('matt', 'damon') = True              pos : neg    =     12.3 : 1.0
      ('give', 'us') = True              neg : pos    =     12.3 : 1.0
           ludicrous = True              neg : pos    =     11.8 : 1.0
         uninvolving = True              neg : pos    =     11.7 : 1.0
              avoids = True              pos : neg    =     11.7 : 1.0
('absolutely', 'no') = True              neg : pos    =     10.6 : 1.0

Yes, you read that right, Matt Damon is apparently one of the best predictors for positive sentiment in movie reviews. But despite this chuckle-worthy result

  • accuracy is up almost 9%
  • pos precision has increased over 10% with only 4% drop in recall
  • neg recall has increased over 21% with just under 4% drop in precision

So it appears that the bigram hypothesis is correct, and including significant bigrams can increase classifier effectiveness. Note that it’s significant bigrams that enhance effectiveness. I tried using nltk.util.bigrams to include all bigrams, and the results were only a few points above baseline. This points to the idea that including only significant features can improve accuracy compared to using all features. In a future article, I’ll try trimming down the single word features to only include significant words.

Text Classification for Sentiment Analysis – Naive Bayes Classifier

Sentiment analysis is becoming a popular area of research and social media analysis, especially around user reviews and tweets. It is a special case of text mining generally focused on identifying opinion polarity, and while it’s often not very accurate, it can still be useful. For simplicity (and because the training data is easily accessible) I’ll focus on 2 possible sentiment classifications: positive and negative.

NLTK Naive Bayes Classification

NLTK comes with all the pieces you need to get started on sentiment analysis: a movie reviews corpus with reviews categorized into pos and neg categories, and a number of trainable classifiers. We’ll start with a simple NaiveBayesClassifier as a baseline, using boolean word feature extraction.

Bag of Words Feature Extraction

All of the NLTK classifiers work with featstructs, which can be simple dictionaries mapping a feature name to a feature value. For text, we’ll use a simplified bag of words model where every word is feature name with a value of True. Here’s the feature extraction method:

def word_feats(words):
		return dict([(word, True) for word in words])

Training Set vs Test Set and Accuracy

The movie reviews corpus has 1000 positive files and 1000 negative files. We’ll use 3/4 of them as the training set, and the rest as the test set. This gives us 1500 training instances and 500 test instances. The classifier training method expects to be given a list of tokens in the form of [(feats, label)] where feats is a feature dictionary and label is the classification label. In our case, feats will be of the form {word: True} and label will be one of ‘pos’ or ‘neg’. For accuracy evaluation, we can use nltk.classify.util.accuracy with the test set as the gold standard.

Training and Testing the Naive Bayes Classifier

Here’s the complete python code for training and testing a Naive Bayes Classifier on the movie review corpus.

import nltk.classify.util
from nltk.classify import NaiveBayesClassifier
from nltk.corpus import movie_reviews

def word_feats(words):
	return dict([(word, True) for word in words])

negids = movie_reviews.fileids('neg')
posids = movie_reviews.fileids('pos')

negfeats = [(word_feats(movie_reviews.words(fileids=[f])), 'neg') for f in negids]
posfeats = [(word_feats(movie_reviews.words(fileids=[f])), 'pos') for f in posids]

negcutoff = len(negfeats)*3/4
poscutoff = len(posfeats)*3/4

trainfeats = negfeats[:negcutoff] + posfeats[:poscutoff]
testfeats = negfeats[negcutoff:] + posfeats[poscutoff:]
print 'train on %d instances, test on %d instances' % (len(trainfeats), len(testfeats))

classifier = NaiveBayesClassifier.train(trainfeats)
print 'accuracy:', nltk.classify.util.accuracy(classifier, testfeats)
classifier.show_most_informative_features()

And the output is:

train on 1500 instances, test on 500 instances
accuracy: 0.728
Most Informative Features
         magnificent = True              pos : neg    =     15.0 : 1.0
         outstanding = True              pos : neg    =     13.6 : 1.0
           insulting = True              neg : pos    =     13.0 : 1.0
          vulnerable = True              pos : neg    =     12.3 : 1.0
           ludicrous = True              neg : pos    =     11.8 : 1.0
              avoids = True              pos : neg    =     11.7 : 1.0
         uninvolving = True              neg : pos    =     11.7 : 1.0
          astounding = True              pos : neg    =     10.3 : 1.0
         fascination = True              pos : neg    =     10.3 : 1.0
             idiotic = True              neg : pos    =      9.8 : 1.0

As you can see, the 10 most informative features are, for the most part, highly descriptive adjectives. The only 2 words that seem a bit odd are “vulnerable” and “avoids”. Perhaps these words refer to important plot points or character development that signify a good movie. Whatever the case, with simple assumptions and very little code we’re able to get almost 73% accuracy. This is somewhat near human accuracy, as apparently people agree on sentiment only around 80% of the time. Future articles in this series will cover precision & recall metrics, alternative classifiers, and techniques for improving accuracy.

Machine Learning Links

Building a NLTK FreqDist on Redis

Say you want to build a frequency distribution of many thousands of samples with the following characteristics:

  • fast to build
  • persistent data
  • network accessible (with no locking requirements)
  • can store large sliceable index lists

The only solution I know that meets those requirements is Redis. NLTK’s FreqDist is not persistent , shelve is far too slow, BerkeleyDB is not network accessible (and is generally a PITA to manage), and AFAIK there’s no other key-value store that makes sliceable lists really easy to create & access. So far I’ve been quite pleased with Redis, especially given how new it is. It’s quite fast, is network accessible, atomic operations make locking unnecessary, supports sortable and sliceable list structures, and is very easy to configure.

Why build a NLTK FreqDist on Redis

Building a NLTK FreqDist on top of Redis allows you to create a ProbDist, which in turn can be used for classification. Having it be persistent lets you examine the data later. And the ability to create sliceable lists allows you to make sorted indexes for paging thru your samples.

Here’s some more concrete use cases for persistent frequency distributions:

RedisFreqDist

I put the code I’ve been using to build frequency distributions over large sets of words up at BitBucketprobablity.py contains RedisFreqDist, which works just like the NTLK FreqDist, except it stores samples and frequencies as keys and values in Redis. That means samples must be strings. Internally, RedisFreqDist also stores a set of all the samples under the key __samples__ for efficient lookup and sorting. Here’s some example code for using it. For more info, checkout the wiki, or read the code.

def make_freq_dist(samples, host='localhost', port=6379, db=0):
	freqs = RedisFreqDist(host=host, port=port, db=db)

	for sample in samples:
		freqs.inc(sample)

Unfortunately, I had to muck about with some of FreqDist’s internal implementation to remain compatible, so I can’t promise the code will work beyond NLTK version 0.9.9. probablity.py also includes ConditionalRedisFreqDist for creating ConditionalProbDists.

Lists

For creating lists of samples, that very much depends on your use case, but here’s some example code for doing so. r is a redis object, key is the index key for storing the list, and samples is assumed to be a sorted list. The get_samples function demonstrates how to get a slice of samples from the list.

def index_samples(r, key, samples):
	r.delete(key)

	for word in words:
		r.push(key, word, tail=True)

def get_samples(r, key, start, end):
	return r.lrange(key, start, end)

Yes, Redis is still fairly alpha, so I wouldn’t use it for critical systems. But I’ve had very few issues so far, especially compared to dealing with BerkeleyDB. I highly recommend it for your non-critical computational needs :) Redis has been quite stable for a while now, and many sites are using it successfully in production