Package weka.filters.unsupervised.attribute

Class TweetToLexiconFeatureVector

java.lang.Object

weka.filters.Filter

weka.filters.SimpleFilter

weka.filters.SimpleBatchFilter

weka.filters.unsupervised.attribute.TweetToFeatureVector

weka.filters.unsupervised.attribute.TweetToLexiconFeatureVector

All Implemented Interfaces:

java.io.Serializable, CapabilitiesHandler, CapabilitiesIgnorer, CommandlineRunnable, OptionHandler, RevisionHandler

public class TweetToLexiconFeatureVector
extends TweetToFeatureVector

An attribute filter that calculates lexicon-based features for a tweet represented as a string attribute. Different lexicons are used. BibTeX:

 @Article{BravoMarquez2014,
 Title                    = {Meta-level sentiment models for big social data analysis },
 Author                   = {Felipe Bravo-Marquez and Marcelo Mendoza and Barbara Poblete},
 Journal                  = {Knowledge-Based Systems },
 Year                     = {2014},
 Number                   = {0},
 Pages                    = {86 - 99},
 Volume                   = {69},
 Doi                      = {http://dx.doi.org/10.1016/j.knosys.2014.05.016},
 ISSN                     = {0950-7051},
 Keywords                 = {Sentiment classification},
 Url                      = {http://www.sciencedirect.com/science/article/pii/S0950705114002068}
 }
 

Version:

$Revision: 2 $

Author:

Felipe Bravo-Marquez (fbravoma@waikato.ac.nz)

See Also:

Serialized Form

Field Summary

Fields

Modifier and Type	Field	Description
static java.lang.String	AFINN_FILE_NAME	The path of the AFINN lexicon.
static java.lang.String	BING_LIU_FILE_NAME	The path of the BingLiu lexicon.
static java.lang.String	EMOTICON_LIST_FILE_NAME	The path of the emoticon list.
static java.lang.String	LEXICON_FOLDER_NAME	Default path to where lexicons are stored.
static java.lang.String	MPQA_FILE_NAME	The path of the MPQA lexicon.
static java.lang.String	NEGATION_LIST_FILE_NAME	The path of the negation list.
static java.lang.String	NRC_HASH_EMO_FILE_NAME	The path of the NRC Hashtag Emotion lexicon.
static java.lang.String	NRC_HASH_SENT_FILE_NAME	The path of the NRC-Hashtag-Sentiment lexicon.
static java.lang.String	NRC10_EXPANDED_FILE_NAME	The path of the NRC-10-Expanded lexicon.
static java.lang.String	NRC10_FILE_NAME	The path of the NRC-emotion lexicon.
static java.lang.String	S140_FILE_NAME	The path of the S140 lexicon.
static java.lang.String	SENTIWORDNET_FILE_NAME	The path of SentiWordnet.

Constructor Summary

Constructors

Constructor	Description
TweetToLexiconFeatureVector()

Method Summary

Modifier and Type	Method	Description
TechnicalInformation	getTechnicalInformation()	Returns an instance of a TechnicalInformation object, containing detailed information about the technical background of this class, e.g., paper reference or book this class is based on.
java.lang.String	globalInfo()	Returns a string describing this filter.
boolean	isUseAfinn()
boolean	isUseBingLiu()
boolean	isUseEmoticons()
boolean	isUseMpqa()
boolean	isUseNegation()
boolean	isUseNrc10()
boolean	isUseNrc10Expanded()
boolean	isUseNrcHashEmo()
boolean	isUseNrcHashSent()
boolean	isUseS140()
boolean	isUseSentiWordnet()
static void	main(java.lang.String[] args)	Main method for testing this class.
void	setUseAfinn(boolean useAfinn)
void	setUseBingLiu(boolean useBingLiu)
void	setUseEmoticons(boolean useEmoticons)
void	setUseMpqa(boolean useMpqa)
void	setUseNegation(boolean useNegation)
void	setUseNrc10(boolean useNrc10)
void	setUseNrc10Expanded(boolean useNrc10Expanded)
void	setUseNrcHashEmo(boolean useNrcHashEmo)
void	setUseNrcHashSent(boolean useNrcHashSent)
void	setUseS140(boolean useS140)
void	setUseSentiWordnet(boolean useSentiWordnet)

Methods inherited from class weka.filters.Filter

batchFilterFile, debugTipText, doNotCheckCapabilitiesTipText, filterFile, getCapabilities, getCopyOfInputFormat, getDebug, getDoNotCheckCapabilities, getOutputFormat, getRevision, isFirstBatchDone, isNewBatch, isOutputFormatDefined, makeCopies, makeCopy, mayRemoveInstanceAfterFirstBatchDone, numPendingOutput, output, outputPeek, postExecution, preExecution, run, runFilter, setDebug, setDoNotCheckCapabilities, toString, useFilter, wekaStaticWrapper

Methods inherited from class java.lang.Object

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

Methods inherited from class weka.filters.SimpleBatchFilter

batchFinished, input

Methods inherited from class weka.filters.SimpleFilter

setInputFormat

Methods inherited from class weka.filters.unsupervised.attribute.TweetToFeatureVector

allowAccessToFullInputFormat, getCapabilities, getOptions, getStemmer, getStopwordsHandler, getTextIndex, getTokenizer, isReduceRepeatedLetters, isStandarizeUrlsUsers, isToLowerCase, listOptions, setOptions, setReduceRepeatedLetters, setStandarizeUrlsUsers, setStemmer, setStopwordsHandler, setTextIndex, setTokenizer, setToLowerCase

Field Detail

LEXICON_FOLDER_NAME

public static java.lang.String LEXICON_FOLDER_NAME

Default path to where lexicons are stored.

MPQA_FILE_NAME

public static java.lang.String MPQA_FILE_NAME

The path of the MPQA lexicon.

BING_LIU_FILE_NAME

public static java.lang.String BING_LIU_FILE_NAME

The path of the BingLiu lexicon.

AFINN_FILE_NAME

public static java.lang.String AFINN_FILE_NAME

The path of the AFINN lexicon.

S140_FILE_NAME

public static java.lang.String S140_FILE_NAME

The path of the S140 lexicon.

NRC_HASH_SENT_FILE_NAME

public static java.lang.String NRC_HASH_SENT_FILE_NAME

The path of the NRC-Hashtag-Sentiment lexicon.

NRC10_FILE_NAME

public static java.lang.String NRC10_FILE_NAME

The path of the NRC-emotion lexicon.

NRC10_EXPANDED_FILE_NAME

public static java.lang.String NRC10_EXPANDED_FILE_NAME

The path of the NRC-10-Expanded lexicon.

NRC_HASH_EMO_FILE_NAME

public static java.lang.String NRC_HASH_EMO_FILE_NAME

The path of the NRC Hashtag Emotion lexicon.

SENTIWORDNET_FILE_NAME

public static java.lang.String SENTIWORDNET_FILE_NAME

The path of SentiWordnet.

EMOTICON_LIST_FILE_NAME

public static java.lang.String EMOTICON_LIST_FILE_NAME

The path of the emoticon list.

NEGATION_LIST_FILE_NAME

public static java.lang.String NEGATION_LIST_FILE_NAME

The path of the negation list.

Constructor Detail

TweetToLexiconFeatureVector

public TweetToLexiconFeatureVector()

Method Detail

globalInfo

public java.lang.String globalInfo()

Returns a string describing this filter.

Specified by:

globalInfo in class SimpleFilter

Returns:

a description of the filter suitable for displaying in the explorer/experimenter gui

getTechnicalInformation

public TechnicalInformation getTechnicalInformation()

Returns an instance of a TechnicalInformation object, containing detailed information about the technical background of this class, e.g., paper reference or book this class is based on.

Returns:

the technical information about this class

isUseMpqa

@OptionMetadata(displayName="useMpqa",
                description="Counts the number of positive and negative words from the MPQA subjectivity lexicon.\nMore info at: http://mpqa.cs.pitt.edu/lexicons/subj_lexicon/ \nPublication: Theresa Wilson, Janyce Wiebe, and Paul Hoffmann, Recognizing Contextual Polarity in Phrase-Level Sentiment Analysis.",
                commandLineParamIsFlag=true,
                commandLineParamName="A",
                commandLineParamSynopsis="-A",
                displayOrder=6)
public boolean isUseMpqa()

setUseMpqa

public void setUseMpqa(boolean useMpqa)

isUseBingLiu

@OptionMetadata(displayName="useBingLiu",
                description="Counts the number of positive and negative words from the Bing Liu lexicon.\nMore info at: https://www.cs.uic.edu/~liub/FBS/sentiment-analysis.html#lexicon \nPublication: Minqing Hu and Bing Liu, Mining and summarizing customer reviews.",
                commandLineParamIsFlag=true,
                commandLineParamName="D",
                commandLineParamSynopsis="-D",
                displayOrder=7)
public boolean isUseBingLiu()

setUseBingLiu

public void setUseBingLiu(boolean useBingLiu)

isUseAfinn

@OptionMetadata(displayName="useAfinn",
                description="Calculates a positive and negative score by aggregating the word associations provided by the AFINN lexicon.\nMore info at: http://www2.imm.dtu.dk/pubdb/views/publication_details.php?id=6010 \nPublication: Finn Arup Nielsen, A new ANEW: Evaluation of a word list for sentiment analysis in microblogs.",
                commandLineParamIsFlag=true,
                commandLineParamName="F",
                commandLineParamSynopsis="-F",
                displayOrder=8)
public boolean isUseAfinn()

setUseAfinn

public void setUseAfinn(boolean useAfinn)

isUseS140

@OptionMetadata(displayName="useS140",
                description="Calculates a positive and negative score by aggregating the word associations provided by the S140 lexicon.\nMore info at: http://saifmohammad.com/WebPages/lexicons.html \nPublication: Svetlana Kiritchenko, Xiaodan Zhu and Saif Mohammad, Sentiment Analysis of Short Informal Texts.",
                commandLineParamIsFlag=true,
                commandLineParamName="H",
                commandLineParamSynopsis="-H",
                displayOrder=9)
public boolean isUseS140()

setUseS140

public void setUseS140(boolean useS140)

isUseNrcHashSent

@OptionMetadata(displayName="useNrcHashSent",
                description="Calculates a positive and negative score by aggregating the word associations provided by the NRC Hashtag Sentiment lexicon.\nMore info at: http://saifmohammad.com/WebPages/lexicons.html \nPublication: Svetlana Kiritchenko, Xiaodan Zhu and Saif Mohammad, Sentiment Analysis of Short Informal Texts.",
                commandLineParamIsFlag=true,
                commandLineParamName="J",
                commandLineParamSynopsis="-J",
                displayOrder=10)
public boolean isUseNrcHashSent()

setUseNrcHashSent

public void setUseNrcHashSent(boolean useNrcHashSent)

isUseNrc10

@OptionMetadata(displayName="useNrc10",
                description="Counts the number of words matching each emotion from the NRC Word-Emotion Association Lexicon.\nMore info at: http://saifmohammad.com/WebPages/NRC-Emotion-Lexicon.htm\nPublication: Saif Mohammad and Peter Turney, Crowdsourcing a Word-Emotion Association Lexicon.",
                commandLineParamIsFlag=true,
                commandLineParamName="L",
                commandLineParamSynopsis="-L",
                displayOrder=11)
public boolean isUseNrc10()

setUseNrc10

public void setUseNrc10(boolean useNrc10)

isUseNrc10Expanded

@OptionMetadata(displayName="useNrc10Expanded",
                description="Adds the emotion associations of the words matching the Twitter Specific expansion of the NRC Word-Emotion Association Lexicon.\nMore info at: http://www.cs.waikato.ac.nz/ml/sa/lex.html#emolextwitter\nPublication: F. Bravo-Marquez, E. Frank, S. M. Mohammad, and B. Pfahringer, Determining Word--Emotion Associations from Tweets by Multi-Label Classification.",
                commandLineParamIsFlag=true,
                commandLineParamName="N",
                commandLineParamSynopsis="-N",
                displayOrder=12)
public boolean isUseNrc10Expanded()

setUseNrc10Expanded

public void setUseNrc10Expanded(boolean useNrc10Expanded)

isUseNrcHashEmo

@OptionMetadata(displayName="useNrcHashEmo",
                description="Adds the emotion associations of the words matching the NRC Hashtag Emotion Association Lexicon.\nMore info at: http://saifmohammad.com/WebPages/lexicons.html\nPublication: Saif M. Mohammad, Svetlana Kiritchenko, Using Hashtags to Capture Fine Emotion Categories from Tweets.",
                commandLineParamIsFlag=true,
                commandLineParamName="P",
                commandLineParamSynopsis="-P",
                displayOrder=13)
public boolean isUseNrcHashEmo()

setUseNrcHashEmo

public void setUseNrcHashEmo(boolean useNrcHashEmo)

isUseSentiWordnet

@OptionMetadata(displayName="useSentiWordnet",
                description="Calculates positive and negative scores using SentiWordnet. We calculate a weighted average of the sentiment distributions of the synsets for word occuring in multiple synsets. The weights correspond to the reciprocal ranks of the senses in order to give higher weights to most popular senses. \nMore info at: http://sentiwordnet.isti.cnr.it/\nPublication: Stefano Baccianella, Andrea Esuli, and Fabrizio Sebastiani, SENTIWORDNET 3.0: An Enhanced Lexical Resource for Sentiment Analysis and Opinion Mining.",
                commandLineParamIsFlag=true,
                commandLineParamName="Q",
                commandLineParamSynopsis="-Q",
                displayOrder=14)
public boolean isUseSentiWordnet()

setUseSentiWordnet

public void setUseSentiWordnet(boolean useSentiWordnet)

isUseEmoticons

@OptionMetadata(displayName="useEmoticons",
                description="Calculates a positive and a negative score by aggregating the word associations provided by a list of emoticons.\nThe list is taken from the AFINN project.\nMore info at: https://github.com/fnielsen/afinn \n",
                commandLineParamIsFlag=true,
                commandLineParamName="R",
                commandLineParamSynopsis="-R",
                displayOrder=15)
public boolean isUseEmoticons()

setUseEmoticons

public void setUseEmoticons(boolean useEmoticons)

isUseNegation

@OptionMetadata(displayName="useNegation",
                description="Counts the number of negating words in the tweet.",
                commandLineParamIsFlag=true,
                commandLineParamName="T",
                commandLineParamSynopsis="-T",
                displayOrder=16)
public boolean isUseNegation()

setUseNegation

public void setUseNegation(boolean useNegation)

main

public static void main(java.lang.String[] args)

Main method for testing this class.

Parameters:

args - should contain arguments to the filter: use -h for help