Irony Detection Using Neural Network Language Model, Psycholinguistic Features and Text Mining
Authors:
- 1 July 2018
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 254-260
Abstract
Irony is a form of figurative language, which is often used to make fun of an entity. We employ paragraph vector to capture syntactic and semantic features of the figurative language to subsequently detect satiric and ironic content in a given text using data mining. We extract psycholinguistic features with the help of a tool called Linguistic Inquiry Word Count. In order to extract useful insights of what constitutes figurative language, we combined syntactic, semantic, and psycholinguistic features together. We demonstrated the effectiveness of the proposed methodology on two satiric news datasets and one ironic customer review dataset. The proposed approach outperformed on the state of the art results.Keywords
This publication has 25 references indexed in Scilit:
- Metaphor Identification in Large Texts CorporaPLOS ONE, 2013
- From humor recognition to irony detection: The figurative language of social mediaData & Knowledge Engineering, 2012
- LIBSVMACM Transactions on Intelligent Systems and Technology, 2011
- An Ironic Fist in a Velvet Glove: Creative Mis-Representation in the Construction of Ironic SimilesMinds and Machines, 2010
- The Psychological Meaning of Words: LIWC and Computerized Text Analysis MethodsJournal of Language and Social Psychology, 2009
- The WEKA data mining softwareACM SIGKDD Explorations Newsletter, 2009
- Logistic Model TreesMachine Learning, 2005
- Literal vs. figurative language: Different or equal?Journal of Pragmatics, 2002
- Support-vector networksMachine Learning, 1995
- Ridge Estimators in Logistic RegressionJournal of the Royal Statistical Society Series C: Applied Statistics, 1992