Class SentimentME

java.lang.Object

opennlp.tools.sentiment.SentimentME

All Implemented Interfaces:

opennlp.tools.sentiment.SentimentDetector

public class SentimentME
extends Object
implements opennlp.tools.sentiment.SentimentDetector

A SentimentDetector implementation for creating and using maximum-entropy-based Sentiment Analysis models.

See Also:

• SentimentModel

Constructor Summary

Constructors

Constructor	Description
SentimentME(SentimentModel sentModel)	Instantiates a SentimentME with the specified model.

Method Summary

Modifier and Type	Method	Description
String	getBestSentiment(double[] outcome)	Returns the best chosen sentiment for the given probability distribution.
String	predict(String sentence)
String	predict(String[] tokens)
double[]	probabilities(String[] text)	Returns the probability distribution over sentiment labels for the given tokens.
static SentimentModel	train(String languageCode, opennlp.tools.util.ObjectStream<opennlp.tools.sentiment.SentimentSample> samples, opennlp.tools.util.TrainingParameters trainParams, SentimentFactory factory)	Trains a Sentiment Analysis model.

Methods inherited from class Object

equals, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Constructor Details

SentimentME

public SentimentME(SentimentModel sentModel)

Instantiates a SentimentME with the specified model.

Parameters:

sentModel - The sentiment analysis model to use. It must not be null.

Throws:

IllegalArgumentException - Thrown if parameters are invalid.

Method Details

train

public static SentimentModel train(String languageCode,
 opennlp.tools.util.ObjectStream<opennlp.tools.sentiment.SentimentSample> samples,
 opennlp.tools.util.TrainingParameters trainParams,
 SentimentFactory factory)
                            throws IOException

Trains a Sentiment Analysis model.

Parameters:

languageCode - the code for the language of the text, e.g. "en"

samples - the sentiment samples to be used

trainParams - parameters for training

factory - a Sentiment Analysis factory

Returns:

A valid SentimentModel.

Throws:

IOException - Thrown if IO errors occurred during training.

predict

public String predict(String sentence)

Specified by:

predict in interface opennlp.tools.sentiment.SentimentDetector

predict

public String predict(String[] tokens)

Specified by:

predict in interface opennlp.tools.sentiment.SentimentDetector

getBestSentiment

public String getBestSentiment(double[] outcome)

Returns the best chosen sentiment for the given probability distribution.

Parameters:

outcome - the probability distribution over outcomes.

Returns:

the best sentiment label.

probabilities

public double[] probabilities(String[] text)

Returns the probability distribution over sentiment labels for the given tokens.

Parameters:

text - the tokens to classify.

Returns:

the probability distribution over sentiment labels.