Sarcasm Analysis Using Conversation Context

Ghosh, Debanjan; Fabbri, Alexander R.; Muresan, Smaranda

doi:10.1162/coli_a_00336

Cited by 58 publications

(59 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…S-XGB: As the same with above methods [36], it depends on gradient boosting which uses a gradient-descentlike procedure to sequentially improve a tree classifier. [37]. MQA: It is our presented deep memory network with quote information and response information based on Bi-LSTM and attention mechanism.…”

Section: B Experimental Resultsmentioning

confidence: 99%

See 1 more Smart Citation

A Multi-Dimension Question Answering Network for Sarcasm Detection

et al. 2020

View full text Add to dashboard Cite

Sarcasm is a form of figurative language where the literal meaning of words cannot hold, and instead the opposite interpretation is intended in a text. Sarcasm detection is a significant task to mine fine-grained information, which is a much more difficult challenge for sentiment analysis. Both industry and academia have realized the importance of sarcasm detection. However, most existing methods do not work very well. Using a neural architecture, we propose a novel multi-dimension question answering (MQA) network in order to detect sarcasm. MQA not only introduces the abundant semantic information to understand the ambiguity of sarcasm by multi-dimension representations, but also builds the conversation context information by deep memory question answering network based on bidirectional LSTM and attention mechanism to discover sarcasm. The experimental results show that our model has ability to obviously outperform other state-of-the-art methods, and then further examples also verifies the advancement and effectiveness of our proposed network for detecting sarcasm.

show abstract

Section: B Experimental Resultsmentioning

confidence: 99%

“…Citation information: DOI 10.1109/ACCESS.2020.2967095, IEEE Access Yufeng Diao et al: A Multi-Dimension Question Answering Network for Sarcasm Detection The Statistics of the Dataset Comparison with previous approaches. The results with superscript * are reported in[36] and[37]. The best results in each type are highlighted.…”

mentioning

confidence: 99%

A Multi-Dimension Question Answering Network for Sarcasm Detection

et al. 2020

View full text Add to dashboard Cite

show abstract

“…The recognition of sarcasm is a hard task, due to lack of context, use of slang, and rhetorical questions. In Ghosh et al [61], the detection of sarcasm in social networks and discussion forums was investigated by using SVM and Long Short-Term Memory (LSTM). In their study, LSTM obtained better results than SVM.…”

Section: Machine Learning and Mixed Learning Based Solutionsmentioning

confidence: 99%

A Framework for Detecting Intentions of Criminal Acts in Social Media: A Case Study on Twitter

et al. 2020

View full text Add to dashboard Cite

Criminals use online social networks for various activities by including communication, planning, and execution of criminal acts. They often employ ciphered posts using slang expressions, which are restricted to specific groups. Although literature shows advances in analysis of posts in natural language messages, such as hate discourses, threats, and more notably in the sentiment analysis; research enabling intention analysis of posts using slang expressions is still underexplored. We propose a framework and construct software prototypes for the selection of social network posts with criminal slang expressions and automatic classification of these posts according to illocutionary classes. The developed framework explores computational ontologies and machine learning (ML) techniques. Our defined Ontology of Criminal Expressions represents crime concepts in a formal and flexible model, and associates them with criminal slang expressions. This ontology is used for selecting suspicious posts and decipher them. In our solution, the criminal intention in written posts is automatically classified relying on learned models from existing posts. This work carries out a case study to evaluate the framework with 8,835,290 tweets. The obtained results show its viability by demonstrating the benefits in deciphering posts and the effectiveness of detecting user’s intention in written criminal posts based on ML.

show abstract

“…Vários fatores dificultam o reconhecimento de sarcasmo, tais como a falta contexto, uso de gírias e o uso de perguntas retóricas. Em (Ghosh, Fabbri, & Muresan, 2018) busca-se analisar a detecção de sarcasmo em redes sociais e fóruns de discussão, por meio de SVM e de Long Short-Term Memory (LSTM); LSTM obteve melhores resultados do que SVM. Em Justo et al (2014) busca-se identificar sarcasmo e maldade em comentários realizados em redes sociais.…”

Section: Soluções Baseadas Em Aprendizagem De Máquina E Mistasunclassified

Um Estudo Sobre Análise, Representação E Detecção De Intenções De Criminosos Em Postagens Em Mídia Social

Mendonça¹,

Rosa²,

Bonacin³

2019

Atas Da Conferência Ibero-Americana WWW/Internet 2019

View full text Add to dashboard Cite

As mídias sociais se transformaram em um instrumento de comunicação entre criminosos, para planejamento e execução de crimes, bem como para recrutar novos membros. Eles utilizam diferentes estratégias de comunicação, tais como linguagens cifradas e gírias restritas a grupos ou facções para burlar investigações. A pesquisa por ferramentas e técnicas para apoiar a atividade investigativa e o processo de prevenção de crimes são de extrema importância; particularmente, a análise e detecção de intenções relacionadas a crimes. Os aspectos tecnológicos, humanos e sociais relacionados a este problema, torna-o um campo rico de estudo, envolvendo a interação entre IHC (Interação Humano-Computador) com diversas áreas de pesquisa. Pesquisas ligadas às áreas de segurança de informação, linguística, aprendizagem de máquina e processamento de linguagem natural, têm contribuído para o avanço na análise e detecção de intenções em mídia social. Este artigo apresenta uma revisão quasi-sistemática da literatura sobre análise, representação e detecção de intenções de criminosos em postagens em mídia social. 27 estudos foram analisados de acordo com as abordagens utilizadas (ex.: técnicas de aprendizagem de máquina), bem como seus fundamentos em aspectos linguísticos, ontologias, semiótica e teoria dos atos da fala. Os resultados apontam avanços na solução do problema e questões de pesquisas em aberto para a área de IHC e relacionadas.

show abstract

Sarcasm Analysis Using Conversation Context

Cited by 58 publications

References 41 publications

A Multi-Dimension Question Answering Network for Sarcasm Detection

A Multi-Dimension Question Answering Network for Sarcasm Detection

A Framework for Detecting Intentions of Criminal Acts in Social Media: A Case Study on Twitter

Um Estudo Sobre Análise, Representação E Detecção De Intenções De Criminosos Em Postagens Em Mídia Social

Contact Info

Product

Resources

About