Human communication often involves the use of irony. In many cases, it is far from obvious if an utterance is meant ironical or not. Context and world knowledge are needed to discriminate literal from ironic intent.
Linguists have worked on describing the nature of irony and come up with ideas which reflect the intuitive understanding of irony.
Parallely, computational linguists are confronted with the challenge of automatically detecting irony. When an utterance contains irony, the only chance of getting the intent, is understanding and interpreting the irony in it.
I review different theories of irony in chapter 2.
Chapter 3 describes the state-of-the-art of automatic irony detection, covers the importance of corpus study for future research and proposes a fusion between theory, corpus study and automatic detection.
Table of Contents
1 Introduction
2 Linguistic theories of irony
2.1 Echoic mention theory
2.2 Pretense theory
2.3 Allusional pretense theory
2.4 Unified theory
2.5 Discussion
3 Automatic detection of irony
3.1 “Yeah Right”: Sarcasm Recognition for Spoken Dialogue Systems
3.1.1 Material
3.1.2 Method
3.1.3 Results
3.1.4 Discussion
3.2 Lexical Influences on the Perception of Sarcasm
3.2.1 Material
3.2.2 Method
3.2.3 Results
3.2.4 Discussion
3.3 Using LSA to detect Irony
3.3.1 Material
3.3.2 Method
3.3.3 Results
3.3.4 Discussion
3.4 Clues for Detecting Irony in User-Generated Contents: Oh...!! It’s “so easy” ;-)
3.4.1 Material
3.4.2 Method
3.4.3 Results
3.4.4 Discussion
3.5 Detecting Ironic Intent in Creative Comparisons
3.5.1 Material
3.5.2 Method
3.5.3 Results
3.5.4 Discussion
3.6 Automatic Satire Detection: Are You Having a Laugh?
3.6.1 Material
3.6.2 Method
3.6.3 Results
3.6.4 Discussion
3.7 Semi-Supervised Recognition of Sarcastic Sentences in Twitter and Amazon
3.7.1 Material
3.7.2 Method
3.7.3 Results
3.7.4 Discussion
3.8 Summary
4 Future Work
Research Objectives and Themes
This work explores the linguistic foundations of verbal irony and examines the state-of-the-art computational methods for its automatic detection, aiming to bridge the gap between theoretical understanding and practical application.
- Linguistic theories of irony including echoic mention, pretense, and allusional pretense theories.
- Computational approaches using prosodic, contextual, and lexical features for sarcasm detection.
- Application of Latent Semantic Analysis (LSA) and machine learning for identifying ironic intent.
- Evaluation of syntactic patterns and semantic validity in social media and news content.
- Future integration of corpus studies and semantic-inducing syntactic rules.
Excerpt from the Book
2.2 Pretense theory
As an alternative to the echoic mention theory, Clark and Gerrig (1984) propose the pretense theory of irony. When speaking ironically, the theory goes, the speaker pretends to be someone else. When uttering (4), the speaker may pretend to be someone who did not get the game’s rules he just lost. By pretending to be such a person, the speaker ridicules the person he pretends to be. Since pretending to be another person is close to imitation, the pretense may (but does not have to) be indicated by a special tone of voice characteristical for the pretended (type of) person. While noted by several theorists, the special tone of voice was empirically investigated by Gibbs (2000) and Traum and Narayanan (2006).
So, when uttering (4), the speaker may pretend being some person who did not get the game’s rules and just lost. Opposing to the echoic mention theory, in the pretense theory there does not need to be any antecedent to echo. The sentence does not need to have been uttered before or reflect a common opinion or thought. The only common ground there should be, Clark and Gerrig (henceforth CG) argue, is some common knowledge in the audience. The audience may only recognize the speaker’s ironic intent if they can infer which person or stereotype the pretended speaker is ought to be. At the very least, the audience has to figure out that the speaker is pretending at all.
Chapter Summaries
1 Introduction: Introduces the concept of verbal irony, establishes the synonyms irony and sarcasm for the scope of the work, and outlines the structure of the paper.
2 Linguistic theories of irony: Reviews post-Gricean theories of irony, including echoic mention, pretense, allusional pretense, and the unified theory.
3 Automatic detection of irony: Surveys current computational approaches to detecting irony, ranging from dialogue systems and LSA to pattern-based machine learning for satire and user-generated content.
4 Future Work: Proposes a fusion of theory and practice, suggesting that robust detection systems should combine syntactic and semantic approaches supported by extensive corpus studies.
Keywords
Verbal irony, Sarcasm, Echoic mention, Pretense theory, Allusional pretense, Unified theory, Automatic detection, Latent semantic analysis, LSA, Computational linguistics, Prosodic features, User-generated content, Satire detection, Corpus study, Pragmatic insincerity.
Frequently Asked Questions
What is the primary focus of this work?
The work focuses on verbal irony and the computational challenges associated with automatically detecting ironic utterances in various forms of language.
What are the main thematic fields covered?
It covers linguistic theories of irony and examines how these theories are applied or challenged by computational methods in natural language processing.
What is the primary research goal?
The goal is to review existing linguistic theories and the state-of-the-art in computational irony detection, proposing a future path that combines these fields effectively.
Which scientific methods are analyzed?
The work analyzes methods such as Latent Semantic Analysis (LSA), Support Vector Machines (SVM) with feature engineering, and semi-supervised k-nearest-neighbor strategies.
What topics are discussed in the main section?
The main section discusses specific approaches for sarcasm recognition in spoken dialogue, online reviews, social media, and satirical news articles.
Which keywords best characterize this research?
Key terms include verbal irony, sarcasm, automatic detection, linguistic theories, and computational linguistics.
How does the pretense theory differ from the echoic mention theory?
The pretense theory posits that the speaker pretends to be someone else to ridicule them, whereas the echoic mention theory views irony as an indirect quotation of a previous utterance or thought.
What conclusion does the author draw regarding LSA's effectiveness for irony detection?
The author concludes that LSA is generally too shallow to grasp irony, as irony often relies on specific syntactic markers and deeper semantic contexts that simple vector representations cannot capture.
- Quote paper
- Michael Fell (Author), 2010, Verbal Irony: Theories and Automatic Detection, Munich, GRIN Verlag, https://www.hausarbeiten.de/document/184355
