A Deep Learning-Inspired Method for Social Media Satire Detection

Dutta, Sayandip; Chakraborty, Anit

doi:10.1007/978-981-13-3393-4_25

Cited by 6 publications

(4 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Various deep learning architectures have been utilized in the recent research in sarcasm detection. Dutta et al presented an approach that involved the stacking of Elman-type RNNs on top of each other to construct a deep RNN for text classification [12]. This work used GloVe embeddings which performed better than the BoW embeddings used by Porwal et al [13].…”

Section: Deep Learning Based Methodsmentioning

confidence: 99%

Performance Evaluation of Word Embeddings for Sarcasm Detection- A Deep Learning Approach

Johnson¹,

Karthik²

2021

Proceedings of the Fist International Conference on Advanced Scientific Innovation in Science, Engineering and Technology, ICA

View full text Add to dashboard Cite

Sarcasm detection is a critical step to sentiment analysis, with the aim of understanding, and exploiting the available information from platforms such as social media. The accuracy of sarcasm detection depends on the nature of word embeddings. This research performs a comprehensive analysis of different word embedding techniques for effective sarcasm detection. A hybrid combination of optimizers including; the Adaptive Moment Estimation (Adam), the Adaptive Gradient Algorithm (AdaGrad) and Adadelta functions and activation functions like Rectified Linear Unit (ReLU) and Leaky ReLU have been experimented with.Different word embedding techniques including; Bag of Words (BoW), BoW with Term Frequency-Inverse Document Frequency (TF-IDF), Word2vec and Global Vectors for word representation (GloVe) are evaluated. The highest accuracy of 61.68% was achieved with theGloVeembeddings and an AdaGrad optimizer and a ReLU activation function, used in the deep learning model.

show abstract

Section: Deep Learning Based Methodsmentioning

confidence: 99%

Performance Evaluation of Word Embeddings for Sarcasm Detection- A Deep Learning Approach

Johnson¹,

Karthik²

2021

Proceedings of the Fist International Conference on Advanced Scientific Innovation in Science, Engineering and Technology, ICA

View full text Add to dashboard Cite

show abstract

“…They mentioned that LIWC is a useful tool for the detection of these two FL categories. Dutta and Chakraborty [13] detected satire using both linguistics and machine learning tools and collected datasets, such as newswire documents, satire news articles, and NewYork Times articles. They extracted lexical (headlines, profanity, and slang) and semantic validity-based features.…”

Section: Related Workmentioning

confidence: 99%

“…Further, both satirical and non-satirical news contain news headlines and news body. We consider only news headlines for two reasons: (i) the proposed satire detection approach is based on short textual data, and (ii) news headline is an important indicator of satire [13]. The second dataset is collected from Thu and New [3], where satirical and non-satirical tweets are collected from several satirical news and true news related accounts, respectively from Twitter.…”

Section: Datasetsmentioning

confidence: 99%

Contextualized Satire Detection in Short Texts Using Deep Learning Techniques

Kamal,

Abulaish,

Jahiruddin

2024

JWE

View full text Add to dashboard Cite

Satire is prominent in user-generated content on various online platforms in the form of satirical news, customer reviews, blogs, articles, and short messages that are typically of an informal nature. As satire is also used to disseminate false information on the Internet, its computational detection has become a well-known issue. Existing work focuses primarily on formal document- or sentence-level textual data, whereas informal short texts have gotten less attention for satire detection. This paper presents a new model called BiLSTM self-attention (BiSAT) for detecting satire in informal short texts. It consists of various components such as input, embedding, self-attention, and two bi-directional long short-term memory (BiLSTM) layers for learning crucial contextual information pertaining to the satire present in the texts. The input layer uses the text as input to create an input vector, which is then given to the embedding layer to create the appropriate numeric vector. The output of the embedding layer is passed on to the first BiLSTM layer, which extracts contextual information-based sequences in the opposite direction. Between the first and second BiLSTM layers, a self-attention layer is employed to draw attention to the important satirical information that is acquired by the hidden layer of the first BiLSTM. The BiSAT model also takes a classic feature engineering approach, employing a 13-dimensional auxiliary feature vector comprised of features from four separate feature categories: sentiment, punctuation, hyperbole, and affective. The proposed BiSAT model is empirically evaluated on two benchmark datasets and a newly created dataset called Satire-280. It outperforms existing research and baseline methods by a significant margin. The Satire-280 dataset along with code can be downloaded from GitHub repository: https://github.com/Ashraf-Kamal/Satire-Detection.

show abstract

“…Notwithstanding a vast amount of deep learning-based methods have been proposed for irony detection, and the commonalities between irony and satire, few methods have addressed the problem of satire detection from a deep learning perspective. Recent works in this direction have been presented in (Yang et al, 2017a;Sarkar et al, 2018;Dutta & Chakraborty, 2019). In (Yang et al, 2017a) a four-level hierarchical network with attention mechanism was presented to differentiate satirical news from true ones.…”

Section: Deep Learning-based Approachesmentioning

confidence: 99%