• Corpus ID: 1334001

The perfect solution for detecting sarcasm in tweets #not

  title={The perfect solution for detecting sarcasm in tweets \#not},
  author={Christine Liebrecht and Florian Kunneman and Antal van den Bosch},
To avoid a sarcastic message being understood in its unintended literal meaning, in microtexts such as messages on Twitter.com sarcasm is often explicitly marked with the hashtag ‘#sarcasm. [] Key Method Assuming that the human labeling is correct (annotation of a sample indicates that about 85% of these tweets are indeed sarcastic), we train a machine learning classifier on the harvested examples, and apply it to a test set of a day’s stream of 3.3 million Dutch tweets. Of the 135 explicitly marked tweets…

Figures and Tables from this paper

Signaling sarcasm: From hyperbole to hashtag
Who cares about Sarcastic Tweets? Investigating the Impact of Sarcasm on Sentiment Analysis
An analysis of the effect of sarcasm scope on the polarity of tweets, and a number of rules which enable the accuracy of sentiment analysis when sarcasm is known to be present are compiled.
An Efficient Approach for Sarcasm Recognition on Twitterusing Pattern-Based Method
This paper proposes an automated system for detection of sarcasm on Twitter by using features related to sentiments, punctuations, semantic and patterns, and assess its significance for the classification.
Sarcasm Detection in Social Media
A machine learning approach combined with Natural Language techniques is presented, thereby producing a model, which improves on the current research and shows that Bag-ofWords (BOW) tends to be more important than sentiment or topic probability-ties, which suggests that vocabulary is moreImportant than tone.
Automatic Sarcasm Detection in Twitter Messages
A system for automatic sarcasm detection in Twitter messages is presented and a dataset of tweets manually annotated with respect to the presence of sarcasm was built; the result was very similar to that of a previously made set, and both of them showed considerable deviation from automatic annotation.
Detecting Sarcastic Tweets : A SentiStrength Modeling Approach
A new Sarcasm Detection Model (SDM) is presented for identifying sarcastic tweets at the level of hashtag and non-hashtag sentiment, based on the strength level of the tweets.
A Pattern-Based Approach for Sarcasm Detection on Twitter
This paper proposes a pattern-based approach to detect sarcasm on Twitter and proposes four sets of features that cover the different types of sarcasm, which are used to classify tweets as sarcastic and non-sarcastic.
Sarcasm Annotation and Detection in Tweets
A comparison of three sets of tweets marked for sarcasm, two annotated manually and one annotated using the common strategy of relying on the authors correctly using hashtags to mark sarcasm indicates that using hashtagged is not a reliable approach to creating Twitter sarcasm corpora.
A qualitative analysis of sarcasm, irony and related #hashtags on Twitter
The prevalence of sarcastic and ironic language within social media posts is assessed and the need for future research studies to rethink their approach to data preparation and a more careful interpretation of sentiment analysis is highlighted.
“When Numbers Matter!”: Detecting Sarcasm in Numerical Portions of Text
This paper focuses on detecting sarcasm in tweets arising out of numbers, and implements a rule-based and a statistical machine learning-based (ML) classifier that conveys the crux of the numerical sarcasm problem, namely, incongruity arising in numbers.


ICWSM - A Great Catchy Name: Semi-Supervised Recognition of Sarcastic Sentences in Online Product Reviews
A novel Semi-supervised Algorithm for Sarcasm Identification that recognizes sarcastic sentences in product reviews and speculate on the motivation for using sarcasm in online communities and social networks is presented.
A multidimensional approach for detecting irony in Twitter
A new model of irony detection that is assessed along two dimensions: representativeness and relevance is constructed, and initial results are largely positive, and provide valuable insights into the figurative issues facing tasks such as sentiment analysis, assessment of online reputations, or decision making.
From humor recognition to irony detection: The figurative language of social media
Acoustic markers of sarcasm in Cantonese and English.
Results showed that sarcastic utterances in Cantonese were produced with an elevated mean F0, and reductions in amplitude- and F0-range, which differentiated them most from sincere utterances, which emphasize that prosody is instrumental for marking non-literal intentions in speech such as sarcasm in CantChinese as well as in other languages.
Irony and reversal of evaluation
Learning the Scope of Negation in Biomedical Texts
A machine learning system that finds the scope of negation in biomedical texts using supervised machine learning techniques, whereas most existing systems apply rule-based algorithms.
Vocal Features of Conversational Sarcasm: A Comparison of Methods
  • P. Rockwell
  • Physics
    Journal of psycholinguistic research
  • 2007
The acoustic analysis proved slightly more successful than the perceptual coding in discriminating between sarcastic and non-sarcastic utterances, and moderate correlations were found between the acoustic and perceptual variables.
On Negation as Mitigation: The Case of Negative Irony
Four experiments support the view of negation as mitigation (Giora, Balaban, Fein, & Alkabets, 2004). They show that when irony involves some sizable gap between what is said and what is criticized
Learning the Scope of Hedge Cues in Biomedical Texts
It is shown that the same scope finding approach can be applied to both negation and hedging, and the system is tested on the three subcorpora of the BioScope corpus that represent different text types.