Advanced search
1 file | 837.23 KB

Exploring the fine-grained analysis and automatic detection of irony on Twitter

Cynthia Van Hee (UGent) , Els Lefever (UGent) and Veronique Hoste (UGent)
Author
Organization
Abstract
To push the state of the art in text mining applications, research in natural language processing has increasingly been investigating automatic irony detection, but manually annotated irony corpora are scarce. We present the construction of a manually annotated irony corpus based on a fine-grained annotation scheme for irony that allows to identify different irony types. We conduct a series of binary classification experiments for automatic irony recognition using a support vector machine exploiting a varied feature set and a deep learning approach making use of an LSTM network and (pre-trained) word embeddings. Evaluation on a held-out corpus shows that the SVM model outperforms the neural network approach and benefits from combining lexical, semantic and syntactic information sources. A qualitative analysis of the classification output reveals that the classifier performance may be further enhanced by integrating implicit sentiment information and context- and user-based features.
Keywords
LT3

Downloads

  • (...).pdf
    • full text
    • |
    • UGent only
    • |
    • PDF
    • |
    • 837.23 KB

Citation

Please use this url to cite or link to this publication:

Chicago
Van Hee, Cynthia, Els Lefever, and Veronique Hoste. 2018. “Exploring the Fine-grained Analysis and Automatic Detection of Irony on Twitter.” Language Resources and Evaluation  52 (3): 707–731.
APA
Van Hee, C., Lefever, E., & Hoste, V. (2018). Exploring the fine-grained analysis and automatic detection of irony on Twitter. LANGUAGE RESOURCES AND EVALUATION  , 52(3), 707–731.
Vancouver
1.
Van Hee C, Lefever E, Hoste V. Exploring the fine-grained analysis and automatic detection of irony on Twitter. LANGUAGE RESOURCES AND EVALUATION  . 2018;52(3):707–31.
MLA
Van Hee, Cynthia, Els Lefever, and Veronique Hoste. “Exploring the Fine-grained Analysis and Automatic Detection of Irony on Twitter.” LANGUAGE RESOURCES AND EVALUATION  52.3 (2018): 707–731. Print.
@article{8547909,
  abstract     = {To push the state of the art in text mining applications, research in natural language
processing has increasingly been investigating automatic irony detection, but manually
annotated irony corpora are scarce. We present the construction of a manually
annotated irony corpus based on a fine-grained annotation scheme for irony that
allows to identify different irony types. We conduct a series of binary classification
experiments for automatic irony recognition using a support vector machine exploiting
a varied feature set and a deep learning approach making use of an LSTM network
and (pre-trained) word embeddings. Evaluation on a held-out corpus shows that the
SVM model outperforms the neural network approach and benefits from combining
lexical, semantic and syntactic information sources. A qualitative analysis of the
classification output reveals that the classifier performance may be further enhanced
by integrating implicit sentiment information and context- and user-based features.},
  author       = {Van Hee, Cynthia and Lefever, Els and Hoste, Veronique},
  issn         = {1574-0218},
  journal      = {LANGUAGE RESOURCES AND EVALUATION                                        },
  keyword      = {LT3},
  language     = {eng},
  number       = {3},
  pages        = {707--731},
  title        = {Exploring the fine-grained analysis and automatic detection of irony on Twitter},
  url          = {http://dx.doi.org/10.1007/s10579-018-9414-2},
  volume       = {52},
  year         = {2018},
}

Altmetric
View in Altmetric
Web of Science
Times cited: