wednesday 18 february 2009
DESCRIPTION
Wednesday 18 February 2009. The Languages of Emotion and Financial News Ann Devitt Khurshid Ahmad. Sentiment and the Markets. Sentiment and the Markets. Specialised Language of Financial News. - PowerPoint PPT PresentationTRANSCRIPT
![Page 1: Wednesday 18 February 2009](https://reader034.vdocument.in/reader034/viewer/2022051402/5681587a550346895dc5db50/html5/thumbnails/1.jpg)
Ann DevittTrinity College Dublin
Wednesday 18 February 2009
Wednesday 18 February 2009Wednesday 18 February 2009
The Languages of Emotion and Financial NewsAnn Devitt
Khurshid Ahmad
![Page 2: Wednesday 18 February 2009](https://reader034.vdocument.in/reader034/viewer/2022051402/5681587a550346895dc5db50/html5/thumbnails/2.jpg)
Ann DevittTrinity College Dublin
Wednesday 18 February 2009
Sentiment and the MarketsSentiment and the Markets
![Page 3: Wednesday 18 February 2009](https://reader034.vdocument.in/reader034/viewer/2022051402/5681587a550346895dc5db50/html5/thumbnails/3.jpg)
Ann DevittTrinity College Dublin
Wednesday 18 February 2009
Sentiment and the MarketsSentiment and the Markets
![Page 4: Wednesday 18 February 2009](https://reader034.vdocument.in/reader034/viewer/2022051402/5681587a550346895dc5db50/html5/thumbnails/4.jpg)
Ann DevittTrinity College Dublin
Wednesday 18 February 2009
Global chipmakers, battling slower technology
demand, are betting size matters as they pin their
hopes for future growth on small and easy to
carry mobile devices such as netbooks and
smartphones.
Specialised Language of Financial Specialised Language of Financial NewsNews
Bloomberg.com, 18/2/09
![Page 5: Wednesday 18 February 2009](https://reader034.vdocument.in/reader034/viewer/2022051402/5681587a550346895dc5db50/html5/thumbnails/5.jpg)
Ann DevittTrinity College Dublin
Wednesday 18 February 2009
Global chipmakers, battling slower
technology demand, are betting size matters as
they pin their hopes for future growth on small
and easy to carry mobile devices such as
netbooks and smartphones.
Specialised Language of Financial Specialised Language of Financial NewsNews
Bloomberg.com, 18/2/09
![Page 6: Wednesday 18 February 2009](https://reader034.vdocument.in/reader034/viewer/2022051402/5681587a550346895dc5db50/html5/thumbnails/6.jpg)
Ann DevittTrinity College Dublin
Wednesday 18 February 2009
Global chipmakers, battling slower technology
demand, are betting size matters as they pin their
hopes for future growth on small and
easy to carry mobile devices such as netbooks
and smartphones.
Specialised Language of Financial Specialised Language of Financial NewsNews
Bloomberg.com, 18/2/09
![Page 7: Wednesday 18 February 2009](https://reader034.vdocument.in/reader034/viewer/2022051402/5681587a550346895dc5db50/html5/thumbnails/7.jpg)
Ann DevittTrinity College Dublin
Wednesday 18 February 2009
Global chipmakers, battling slower
technology demand, are betting size matters as
they pin their hopes for future growth
on small and easy to carry mobile devices
such as netbooks and smartphones.
Specialised Language of Financial Specialised Language of Financial NewsNews
Bloomberg.com, 18/2/09
![Page 8: Wednesday 18 February 2009](https://reader034.vdocument.in/reader034/viewer/2022051402/5681587a550346895dc5db50/html5/thumbnails/8.jpg)
Ann DevittTrinity College Dublin
Wednesday 18 February 2009
Sentiment and the MarketsSentiment and the Markets
![Page 9: Wednesday 18 February 2009](https://reader034.vdocument.in/reader034/viewer/2022051402/5681587a550346895dc5db50/html5/thumbnails/9.jpg)
Ann DevittTrinity College Dublin
Wednesday 18 February 2009
Sentiment and the MarketsSentiment and the Markets
![Page 10: Wednesday 18 February 2009](https://reader034.vdocument.in/reader034/viewer/2022051402/5681587a550346895dc5db50/html5/thumbnails/10.jpg)
Ann DevittTrinity College Dublin
Wednesday 18 February 2009
Engle Ng (1993) Asymmetry CurveEngle Ng (1993) Asymmetry Curve
![Page 11: Wednesday 18 February 2009](https://reader034.vdocument.in/reader034/viewer/2022051402/5681587a550346895dc5db50/html5/thumbnails/11.jpg)
Ann DevittTrinity College Dublin
Wednesday 18 February 2009
OutlineOutline
Current psychological theory of emotion
Evaluation of lexical “emotion” resources
Corpus analysis of language of “emotion”
![Page 12: Wednesday 18 February 2009](https://reader034.vdocument.in/reader034/viewer/2022051402/5681587a550346895dc5db50/html5/thumbnails/12.jpg)
Ann DevittTrinity College Dublin
Wednesday 18 February 2009
OutlineOutline
Current psychological theory of emotion
Evaluation of lexical “emotion” resources
Corpus analysis of language of “emotion”
![Page 13: Wednesday 18 February 2009](https://reader034.vdocument.in/reader034/viewer/2022051402/5681587a550346895dc5db50/html5/thumbnails/13.jpg)
Ann DevittTrinity College Dublin
Wednesday 18 February 2009
Cognitive Theory of Emotion:Cognitive Theory of Emotion:CategoricalCategorical
Ekman (1975)
![Page 14: Wednesday 18 February 2009](https://reader034.vdocument.in/reader034/viewer/2022051402/5681587a550346895dc5db50/html5/thumbnails/14.jpg)
Ann DevittTrinity College Dublin
Wednesday 18 February 2009
Cognitive Theory of Emotion:Cognitive Theory of Emotion:DimensionsDimensions
Osgood / RussellEvaluationActivityPotency
Mehabrian PADPleasureActivationDominance
![Page 15: Wednesday 18 February 2009](https://reader034.vdocument.in/reader034/viewer/2022051402/5681587a550346895dc5db50/html5/thumbnails/15.jpg)
Ann DevittTrinity College Dublin
Wednesday 18 February 2009
Cognitive Theory of EmotionCognitive Theory of Emotion
Watson and Tellegen (1985)
![Page 16: Wednesday 18 February 2009](https://reader034.vdocument.in/reader034/viewer/2022051402/5681587a550346895dc5db50/html5/thumbnails/16.jpg)
Ann DevittTrinity College Dublin
Wednesday 18 February 2009
OutlineOutline
Current psychological theory of emotion
Evaluation of lexical “emotion” resources
Corpus analysis of language of “emotion”
![Page 17: Wednesday 18 February 2009](https://reader034.vdocument.in/reader034/viewer/2022051402/5681587a550346895dc5db50/html5/thumbnails/17.jpg)
Ann DevittTrinity College Dublin
Wednesday 18 February 2009
Lexical Resource EvaluationLexical Resource Evaluation
SentiWordNet
WhisselWNA
General Inquirer
![Page 18: Wednesday 18 February 2009](https://reader034.vdocument.in/reader034/viewer/2022051402/5681587a550346895dc5db50/html5/thumbnails/18.jpg)
Ann DevittTrinity College Dublin
Wednesday 18 February 2009
Whissel
Lexical Resource Evaluation Lexical Resource Evaluation Senti WordNetSenti WordNet
SentiWordNet
WNA
General Inquirer
![Page 19: Wednesday 18 February 2009](https://reader034.vdocument.in/reader034/viewer/2022051402/5681587a550346895dc5db50/html5/thumbnails/19.jpg)
Ann DevittTrinity College Dublin
Wednesday 18 February 2009
Lexical Resource Evaluation Lexical Resource Evaluation Senti WordNetSenti WordNet
Word PositiveVal NegativeValHappy 0.9 0.0Sad 0.0 0.9
39066 termsEvaluation dimension scale: 0 - 1Low average: Pos=0.18, Neg=0.23More extreme Neg valuesError-prone: rude (pos 0.875), gladsome (neg 0.875)
![Page 20: Wednesday 18 February 2009](https://reader034.vdocument.in/reader034/viewer/2022051402/5681587a550346895dc5db50/html5/thumbnails/20.jpg)
Ann DevittTrinity College Dublin
Wednesday 18 February 2009
Lexical Resource Evaluation Lexical Resource Evaluation General InquirerGeneral Inquirer
SentiWordNet
WhisselWNA
General Inquirer
![Page 21: Wednesday 18 February 2009](https://reader034.vdocument.in/reader034/viewer/2022051402/5681587a550346895dc5db50/html5/thumbnails/21.jpg)
Ann DevittTrinity College Dublin
Wednesday 18 February 2009
Lexical Resource Evaluation Lexical Resource Evaluation General InquirerGeneral Inquirer
ECSTATIC Pos PleasureSORROWFUL Neg Pain
Hand-coded, content analysis basis8641 terms184 binary categories (including MAB dimensions)Negative > PositiveActive > PassiveStrong > Weak
![Page 22: Wednesday 18 February 2009](https://reader034.vdocument.in/reader034/viewer/2022051402/5681587a550346895dc5db50/html5/thumbnails/22.jpg)
Ann DevittTrinity College Dublin
Wednesday 18 February 2009
Lexical Resource Evaluation Lexical Resource Evaluation Whissel Dictionary of AffectWhissel Dictionary of Affect
SentiWordNet
WhisselWNA
General Inquirer
![Page 23: Wednesday 18 February 2009](https://reader034.vdocument.in/reader034/viewer/2022051402/5681587a550346895dc5db50/html5/thumbnails/23.jpg)
Ann DevittTrinity College Dublin
Wednesday 18 February 2009
Lexical Resource Evaluation Lexical Resource Evaluation Whissel Dictionary of AffectWhissel Dictionary of Affect
Word Eval ActivImag
great 2.6250 2.1250 1.0
disastrous 1.4444 2.4000 2.0Corpus selection, hand-coded8742 termsDimensional representation: 1-3 scaleEvaluation, Activation, Imagery
![Page 24: Wednesday 18 February 2009](https://reader034.vdocument.in/reader034/viewer/2022051402/5681587a550346895dc5db50/html5/thumbnails/24.jpg)
Ann DevittTrinity College Dublin
Wednesday 18 February 2009
Lexical Resource Evaluation Lexical Resource Evaluation WordNet AffectWordNet Affect
SentiWordNet
WhisselWNA
General Inquirer
![Page 25: Wednesday 18 February 2009](https://reader034.vdocument.in/reader034/viewer/2022051402/5681587a550346895dc5db50/html5/thumbnails/25.jpg)
Ann DevittTrinity College Dublin
Wednesday 18 February 2009
Lexical Resource EvaluationLexical Resource EvaluationWordNet AffectWordNet AffectWord BinaryFeatures
Loneliness cognitive state, emotionHappiness cognitive state, emotion
5432 termsDomains of emotional experienceNo PolarityShort-term: Mood, MannerLong-term: Attribute, Trait
![Page 26: Wednesday 18 February 2009](https://reader034.vdocument.in/reader034/viewer/2022051402/5681587a550346895dc5db50/html5/thumbnails/26.jpg)
Ann DevittTrinity College Dublin
Wednesday 18 February 2009
Lexical Resource EvaluationLexical Resource EvaluationLexical OverlapLexical Overlap
Are the lexica consistent?
Are they mutually exclusive?
Dice, Jaccard, Asymmetric coefficients
![Page 27: Wednesday 18 February 2009](https://reader034.vdocument.in/reader034/viewer/2022051402/5681587a550346895dc5db50/html5/thumbnails/27.jpg)
Ann DevittTrinity College Dublin
Wednesday 18 February 2009
Whissel
Lexical Resource EvaluationLexical Resource Evaluation Lexical OverlapLexical Overlap
SentiWordNet
WNA
General Inquirer
![Page 28: Wednesday 18 February 2009](https://reader034.vdocument.in/reader034/viewer/2022051402/5681587a550346895dc5db50/html5/thumbnails/28.jpg)
Ann DevittTrinity College Dublin
Wednesday 18 February 2009
SentiWordNet
Lexical Resource EvaluationLexical Resource Evaluation Lexical OverlapLexical Overlap
General Inquirer
Whissel
WNA
1. Statistically significant agreement for Polarity Assignment (Chi square test)
2. Very weak correlation for activation features.
![Page 29: Wednesday 18 February 2009](https://reader034.vdocument.in/reader034/viewer/2022051402/5681587a550346895dc5db50/html5/thumbnails/29.jpg)
Ann DevittTrinity College Dublin
Wednesday 18 February 2009
SentiWordNet
Lexical Resource EvaluationLexical Resource Evaluation Lexical OverlapLexical Overlap
General Inquirer
Whissel
WNA
1. Weak correlation of SWN with Whissel evaluation
2. No correlation with Whissel activation dimension
3. SWN positive negatively correlated with imageability
![Page 30: Wednesday 18 February 2009](https://reader034.vdocument.in/reader034/viewer/2022051402/5681587a550346895dc5db50/html5/thumbnails/30.jpg)
Ann DevittTrinity College Dublin
Wednesday 18 February 2009
SentiWordNet
Lexical Resource EvaluationLexical Resource Evaluation Lexical OverlapLexical Overlap
WNAGeneral InquirerWhissel
1. SWN tends to negative for short term WNA features
2. SWN tends to positive for long-term WNA features
![Page 31: Wednesday 18 February 2009](https://reader034.vdocument.in/reader034/viewer/2022051402/5681587a550346895dc5db50/html5/thumbnails/31.jpg)
Ann DevittTrinity College Dublin
Wednesday 18 February 2009
Whissel
Lexical Resource EvaluationLexical Resource Evaluation Lexical OverlapLexical Overlap
SentiWordNet
WNA
General Inquirer
![Page 32: Wednesday 18 February 2009](https://reader034.vdocument.in/reader034/viewer/2022051402/5681587a550346895dc5db50/html5/thumbnails/32.jpg)
Ann DevittTrinity College Dublin
Wednesday 18 February 2009
Lexical Resource EvaluationLexical Resource Evaluation Lexical OverlapLexical Overlap
WNA feature division:Short-term Long-term
Negative Positive
Physical Cognitive
More active Less active
Internal External
Less abstract More concrete
![Page 33: Wednesday 18 February 2009](https://reader034.vdocument.in/reader034/viewer/2022051402/5681587a550346895dc5db50/html5/thumbnails/33.jpg)
Ann DevittTrinity College Dublin
Wednesday 18 February 2009
Lexical Resource EvaluationLexical Resource EvaluationSome conclusionsSome conclusions
The lexica:Are quite consistent
Can be used in combination
SentiWN: Largely unexplored territory
![Page 34: Wednesday 18 February 2009](https://reader034.vdocument.in/reader034/viewer/2022051402/5681587a550346895dc5db50/html5/thumbnails/34.jpg)
Ann DevittTrinity College Dublin
Wednesday 18 February 2009
OutlineOutline
Current psychological theory of emotion
Evaluation of lexical “emotion” resources
Corpus analysis of language of “emotion”
General Language
![Page 35: Wednesday 18 February 2009](https://reader034.vdocument.in/reader034/viewer/2022051402/5681587a550346895dc5db50/html5/thumbnails/35.jpg)
Ann DevittTrinity College Dublin
Wednesday 18 February 2009
Emotion in General LanguageEmotion in General LanguageCorpus Study AimsCorpus Study Aims
Does “emotion” constitute a distinct sub-language?
Is there a polarity bias in General Language? (the Polyanna Hypothesis of Boucher and Osgood)
What is the impact of using different lexica?
![Page 36: Wednesday 18 February 2009](https://reader034.vdocument.in/reader034/viewer/2022051402/5681587a550346895dc5db50/html5/thumbnails/36.jpg)
Ann DevittTrinity College Dublin
Wednesday 18 February 2009
Corpus AnalysisCorpus AnalysisThe DataThe Data
BNC100 million words
Balanced, broad corpus
![Page 37: Wednesday 18 February 2009](https://reader034.vdocument.in/reader034/viewer/2022051402/5681587a550346895dc5db50/html5/thumbnails/37.jpg)
Ann DevittTrinity College Dublin
Wednesday 18 February 2009
Corpus AnalysisCorpus AnalysisMethodologyMethodology
Is emotion a distinct sub-language?
Examine distribution type
Examine distribution spread
Bootstrap sampling distribution
![Page 38: Wednesday 18 February 2009](https://reader034.vdocument.in/reader034/viewer/2022051402/5681587a550346895dc5db50/html5/thumbnails/38.jpg)
Ann DevittTrinity College Dublin
Wednesday 18 February 2009
Corpus AnalysisCorpus AnalysisDistribution TypeDistribution Type
Zipfian: BNC=Emotion Lexica
![Page 39: Wednesday 18 February 2009](https://reader034.vdocument.in/reader034/viewer/2022051402/5681587a550346895dc5db50/html5/thumbnails/39.jpg)
Ann DevittTrinity College Dublin
Wednesday 18 February 2009
Corpus AnalysisCorpus AnalysisDistribution shapeDistribution shape
Comparison of means: student t-test
BNC ≠ Emotion Lexica (p<0.000)
Different sample means5-30 times more frequent than gen. languageAssumptions of test?
![Page 40: Wednesday 18 February 2009](https://reader034.vdocument.in/reader034/viewer/2022051402/5681587a550346895dc5db50/html5/thumbnails/40.jpg)
Ann DevittTrinity College Dublin
Wednesday 18 February 2009
Corpus AnalysisCorpus AnalysisBootstrap Sampling DistributionBootstrap Sampling Distribution
Are sentiment-bearing terms a statistically distinct and highly frequent subset of English?
1000 random samples of terms from BNCSample size = size of sentiment lexiconH0: Observed sample falls inside within 95% of bootstrap random sampling distribution of means
![Page 41: Wednesday 18 February 2009](https://reader034.vdocument.in/reader034/viewer/2022051402/5681587a550346895dc5db50/html5/thumbnails/41.jpg)
Ann DevittTrinity College Dublin
Wednesday 18 February 2009
Corpus AnalysisCorpus AnalysisBootstrap Sampling DistributionBootstrap Sampling Distribution
Are sentiment-bearing terms a statistically distinct and highly frequent subset of English?
For all lexica: Mean term frequency of lexicon well outside 95%Sentiment lexica are not representative of BNC (p<0.05)
![Page 42: Wednesday 18 February 2009](https://reader034.vdocument.in/reader034/viewer/2022051402/5681587a550346895dc5db50/html5/thumbnails/42.jpg)
Ann DevittTrinity College Dublin
Wednesday 18 February 2009
Corpus AnalysisCorpus AnalysisSentiment FeaturesSentiment Features
Is there a polarity bias in General Language?
Positive polarity biasStatistically significant for all lexica (χ2 test of independence)
![Page 43: Wednesday 18 February 2009](https://reader034.vdocument.in/reader034/viewer/2022051402/5681587a550346895dc5db50/html5/thumbnails/43.jpg)
Ann DevittTrinity College Dublin
Wednesday 18 February 2009
Corpus AnalysisCorpus AnalysisSentiment FeaturesSentiment Features
Is there a polarity bias in General Language when you include intensity of polarity?
Positive polarity biasStatistically significant for all lexicaχ2 = 158.5, df=1, p<0.0001 for General Inquirerχ2 = 63.6, df=1, p<0.0001 for Whissel
![Page 44: Wednesday 18 February 2009](https://reader034.vdocument.in/reader034/viewer/2022051402/5681587a550346895dc5db50/html5/thumbnails/44.jpg)
Ann DevittTrinity College Dublin
Wednesday 18 February 2009
Corpus AnalysisCorpus AnalysisSome conclusionsSome conclusions
Sentiment-bearing terms are a distinct subset of English
Positive polarity bias in BNC
General Inquirer and Whissel: Low coverage and high frequency
SentiwordNet:Wide coverage and much lower frequency
![Page 45: Wednesday 18 February 2009](https://reader034.vdocument.in/reader034/viewer/2022051402/5681587a550346895dc5db50/html5/thumbnails/45.jpg)
Ann DevittTrinity College Dublin
Wednesday 18 February 2009
OutlineOutline
Current psychological theory of emotion
Evaluation of lexical “emotion” resources
Corpus analysis of language of “emotion”Comparative
![Page 46: Wednesday 18 February 2009](https://reader034.vdocument.in/reader034/viewer/2022051402/5681587a550346895dc5db50/html5/thumbnails/46.jpg)
Ann DevittTrinity College Dublin
Wednesday 18 February 2009
Comparative Corpus AnalysisComparative Corpus AnalysisAimsAims
Examine affective term use
Identify statistically different distributions
Is there a dominant feature/polarity?
![Page 47: Wednesday 18 February 2009](https://reader034.vdocument.in/reader034/viewer/2022051402/5681587a550346895dc5db50/html5/thumbnails/47.jpg)
Ann DevittTrinity College Dublin
Wednesday 18 February 2009
Comparative Corpus AnalysisComparative Corpus AnalysisThe DataThe Data
Financial Language
2 million words
On-line financial news:•Reuters, CNN, Bloomberg
•Newspapers
General Language
BNC100 million words
Balanced, broad corpus
![Page 48: Wednesday 18 February 2009](https://reader034.vdocument.in/reader034/viewer/2022051402/5681587a550346895dc5db50/html5/thumbnails/48.jpg)
Ann DevittTrinity College Dublin
Wednesday 18 February 2009
Comparative Corpus AnalysisComparative Corpus Analysis The Data The Data
BNC sub-corpora
Imaginative written English16 million words
Informative written English70 million words
![Page 49: Wednesday 18 February 2009](https://reader034.vdocument.in/reader034/viewer/2022051402/5681587a550346895dc5db50/html5/thumbnails/49.jpg)
Ann DevittTrinity College Dublin
Wednesday 18 February 2009
Comparative Corpus AnalysisComparative Corpus AnalysisMethodologyMethodology
Compare proportions of Sentiment Features
χ2 Test of Independence
H0: π FinCorpus = π BNC
![Page 50: Wednesday 18 February 2009](https://reader034.vdocument.in/reader034/viewer/2022051402/5681587a550346895dc5db50/html5/thumbnails/50.jpg)
Ann DevittTrinity College Dublin
Wednesday 18 February 2009
Comparative Corpus AnalysisComparative Corpus Analysis Methodology Methodology
Statistical significance of different proportionχ2 > 7.8794p >= 0.005
Features: 41 Lexicon Sentiment Features from 4 lexicaFrequency per million words
![Page 51: Wednesday 18 February 2009](https://reader034.vdocument.in/reader034/viewer/2022051402/5681587a550346895dc5db50/html5/thumbnails/51.jpg)
Ann DevittTrinity College Dublin
Wednesday 18 February 2009
Comparative Corpus AnalysisComparative Corpus AnalysisFinancial CorpusFinancial Corpus
WRT Imaginative: More affective terms
WRT Informative: Many more affective terms
WRT BNC: Dependent on feature typeDistributions are statistically distinct
![Page 52: Wednesday 18 February 2009](https://reader034.vdocument.in/reader034/viewer/2022051402/5681587a550346895dc5db50/html5/thumbnails/52.jpg)
Ann DevittTrinity College Dublin
Wednesday 18 February 2009
Comparative Corpus AnalysisComparative Corpus AnalysisPositive GI FeaturesPositive GI Features
![Page 53: Wednesday 18 February 2009](https://reader034.vdocument.in/reader034/viewer/2022051402/5681587a550346895dc5db50/html5/thumbnails/53.jpg)
Ann DevittTrinity College Dublin
Wednesday 18 February 2009
Comparative Corpus AnalysisComparative Corpus AnalysisPositive GI FeaturesPositive GI Features
![Page 54: Wednesday 18 February 2009](https://reader034.vdocument.in/reader034/viewer/2022051402/5681587a550346895dc5db50/html5/thumbnails/54.jpg)
Ann DevittTrinity College Dublin
Wednesday 18 February 2009
Comparative Corpus AnalysisComparative Corpus AnalysisNegative GI FeaturesNegative GI Features
![Page 55: Wednesday 18 February 2009](https://reader034.vdocument.in/reader034/viewer/2022051402/5681587a550346895dc5db50/html5/thumbnails/55.jpg)
Ann DevittTrinity College Dublin
Wednesday 18 February 2009
Comparative Corpus AnalysisComparative Corpus AnalysisNegative GI FeaturesNegative GI Features
![Page 56: Wednesday 18 February 2009](https://reader034.vdocument.in/reader034/viewer/2022051402/5681587a550346895dc5db50/html5/thumbnails/56.jpg)
Ann DevittTrinity College Dublin
Wednesday 18 February 2009
Comparative Corpus AnalysisComparative Corpus AnalysisNegative GI FeaturesNegative GI Features
![Page 57: Wednesday 18 February 2009](https://reader034.vdocument.in/reader034/viewer/2022051402/5681587a550346895dc5db50/html5/thumbnails/57.jpg)
Ann DevittTrinity College Dublin
Wednesday 18 February 2009
Some conclusionsSome conclusions
Lexical resources for sentiment are consistent
Financial news is a sub-language: Affective content is statistically distinct relative to general language
Text polarity is asymmetric, positive skewDifferent skews for different domains
![Page 58: Wednesday 18 February 2009](https://reader034.vdocument.in/reader034/viewer/2022051402/5681587a550346895dc5db50/html5/thumbnails/58.jpg)
Ann DevittTrinity College Dublin
Wednesday 18 February 2009
Something to think aboutSomething to think about
If different language varieties and domains have distinct use of sentiment terms and their own polarity bias:Individual sentiment values are not informativeSo what do we need??