Skip to main content
SpringerLink
Log in

Exploiting stacked embeddings with LSTM for multilingual humor and irony detection

  • Original Article
  • Published:
Social Network Analysis and Mining Aims and scope Submit manuscript

Abstract

Humor and irony are types of communication that evoke laughter or contain hidden sarcasm. The opportunity to diversely express people’s opinions on social media using humorous content increased its popularity. Due to subjective aspects, humor may vary to gender, profession, generation, and classes of people. Detecting and analyzing humorous and ironic emplacement of informal user-generated content is crucial for various NLP and opinion mining tasks due to its perplexing characteristics. However, due to the idiosyncratic characteristics of informal texts, it is a challenging task to generate an effective representation of texts to understand the inherent contexts properly. In this paper, we propose a neural network architecture that couples a stacked embeddings strategy on top of the LSTM layer for the effective representation of textual context and determine the humorous and ironic orientation of texts in an efficient manner. Here, we perform the stacking of various fine-tuned word embeddings and transformer models including GloVe, ELMo, BERT, and Flair’s contextual embeddings to extract the diversified contextual features of texts. Later, we use the LSTM network on top of it to generate the unified document vector (UDV). Finally, the UDV is passed to the multiple feed-forward linear architectures for attaining the final prediction labels. We present the performance analysis of our proposed approach on benchmark datasets of English and Spanish language. Experimental outcomes exhibited the preponderance of our model over most of the state-of-the-art methods.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3

Similar content being viewed by others

Availability of data

The datasets used within this study are publicly available and respective references to these datasets are included in the manuscript.

Notes

  1. https://docs.fast.ai/

  2. https://github.com/flairNLP/flair/blob/master/resources/docs/embeddings.

  3. https://github.com/flairNLP/flair/blob/master/resources/docs/embeddings.

  4. https://github.com/NeelShah18/emot.

  5. https://github.com/rmit-ir/KrovetzStemmer.

  6. https://pypi.org/project/unicode/.

References

  • Akbik A, Blythe D, Vollgraf R (2018) Contextual string embeddings for sequence labeling. In: Proceedings of the 27th international conference on computational linguistics, pp 1638–1649. https://aclanthology.org/C18-1139/

  • Albawi S, Mohammed TA, Al-Zawi S (2017) Understanding of a convolutional neural network. In: 2017 International conference on engineering and technology (ICET), IEEE, pp 1–6. https://doi.org/10.1109/ICEngTechnol.2017.8308186

  • Altin LSM, Bravo À, Saggion H (2019) Lastus/taln at haha: Humor analysis based on human annotation. In: IberLEF@ SEPLN, pp 145–150

  • Alzubaidi L, Zhang J, Humaidi AJ et al (2021) Review of deep learning: concepts, cnn architectures, challenges, applications, future directions. J Big Data 8:1–74. https://doi.org/10.1186/s40537-021-00444-8

    Article  Google Scholar 

  • Amir S, Wallace BC, Lyu H, et al (2016) Modelling context with user embeddings for sarcasm detection in social media. arXiv preprint arXiv:1607.00976https://doi.org/10.48550/arXiv.1607.00976

  • Annamoradnejad I, Zoghi G (2020) Colbert: Using bert sentence embedding for humor detection. arXiv preprint arXiv:2004.12765https://doi.org/10.48550/arXiv.2004.12765

  • Annamoradnejad I, Zoghi G (2021) Colbert at haha 2021: Parallel neural networks for rating humor in spanish tweets. In: Proceedings of the Iberian languages evaluation forum (IberLEF 2021), CEUR workshop proceedings, Málaga, Spain

  • Barbieri F, Saggion H (2014) Modelling irony in twitter. In: Proceedings of the student research workshop at the 14th conference of the european chapter of the association for computational linguistics, pp 56–64. https://doi.org/10.3115/v1/e14-3007

  • Baziotis C, Pelekis N, Doulkeridis C (2017) Datastories at semeval-2017 task 4: Deep lstm with attention for message-level and topic-based sentiment analysis. In: Proceedings of the 11th international workshop on semantic evaluation (SemEval-2017), pp 747–754. https://doi.org/10.18653/v1/S17-2126

  • Baziotis C, Athanasiou N, Papalampidi P, et al (2018) Ntua-slp at semeval-2018 task 3: Tracking ironic tweets using ensembles of word and character level attentive rnns. arXiv preprint arXiv:1804.06659https://doi.org/10.48550/arXiv.1804.06659

  • Bharti SK, Babu KS, Jena SK (2015) Parsing-based sarcasm sentiment recognition in twitter data. In: 2015 IEEE/ACM international conference on advances in social networks analysis and mining (ASONAM), IEEE, pp 1373–1380. https://doi.org/10.1145/2808797.2808910

  • Bojanowski P, Grave E, Joulin A et al (2017) Enriching word vectors with subword information. Trans Assoc Comput Linguistics 5:135–146. https://doi.org/10.1162/tacl_a_00051

    Article  Google Scholar 

  • BREDIN H (1997) The semantic structure of verbal irony. J Literary Semantics 26(1):1–20

    Article  Google Scholar 

  • Brône G (2017) Cognitive linguistics and humor research. In: The Routledge handbook of language and humor. Routledge, pp 250–266

  • Brône G (2021) The multimodal negotiation of irony and humor in interaction. Figurative Language Intersubject Usage 11:109

    Article  Google Scholar 

  • Brône G, Feyaerts K, Veale T (2006) Introduction: cognitive linguistic approaches to humor. Humor Int J Humor Res 19(3):203–228

  • Buschmeier K, Cimiano P, Klinger R (2014) An impact analysis of features in a classification approach to irony detection in product reviews. In: Proceedings of the 5th workshop on computational approaches to subjectivity, sentiment and social media analysis, pp 42–49. https://doi.org/10.3115/v1/w14-2608

  • Canete J, Chaperon G, Fuentes R, et al (2020) Spanish pre-trained bert model and evaluation data. Pml4dc at iclr 2020:2020

  • Castro S, Chiruzzo L, Rosá A (2018) Overview of the haha task: Humor analysis based on human annotation at ibereval 2018. In: IberEval@ SEPLN, pp 187–194

  • Cattle AG, Zhao Z, Papalexakis EE, et al (2019) Generating document embeddings for humor recognition using tensor decomposition. In: CEUR workshop proceedings, p 151

  • Cañete J, Chaperon G, Fuentes R, et al (2020) Spanish pre-trained bert model and evaluation data. In: PML4DC at ICLR 2020

  • Chi N, Chi R (2021) Redwoodnlp at semeval-2021 task 7: Ensembled pretrained and lightweight models for humor detection. In: Proceedings of the 15th international workshop on semantic evaluation (SemEval-2021), pp 1209–1214. https://doi.org/10.18653/v1/2021.semeval-1.171

  • Chiruzzo L, Castro S, Etcheverry M, et al (2019) Overview of haha at iberlef 2019: Humor analysis based on human annotation. In: IberLEF@ SEPLN, pp 132–144

  • Chiruzzo L, Castro S, Góngora S, et al (2021) Overview of HAHA at IberLEF 2021: detecting, rating and analyzing humor in Spanish. Procesamiento del Lenguaje Natural 67

  • Chung J, Gulcehre C, Cho K, et al (2014) Empirical evaluation of gated recurrent neural networks on sequence modeling. arXiv preprint arXiv:1412.3555https://doi.org/10.48550/arXiv.1412.3555

  • CLARK H (1984) On the pretense theory of irony. J Exp Psychol General 113:121–126

    Article  Google Scholar 

  • Colston HL, Gibbs RW Jr (1998) Analogy and irony: rebuttal to “rebuttal analogy’’. Metaphor Symbol 13(1):69–75

    Article  Google Scholar 

  • Davidson T, Warmsley D, Macy M, et al (2017) Automated hate speech detection and the problem of offensive language. In: Proceedings of the international AAAI conference on web and social media, pp 512–515. https://doi.org/10.48550/arXiv.1703.04009

  • de Arriba Serra A, Oriol Hilari M, Franch Gutiérrez J (2021) Applying sentiment analysis on spanish tweets using beto. In: Proceedings of the Iberian Languages Evaluation Forum (IberLEF 2021): co-located with the Conference of the Spanish Society for Natural Language Processing (SEPLN 2021), XXXVII international conference of the Spanish society for natural language processing: Málaga, Spain, September, 2021, CEUR-WS. org, pp 1–8. http://hdl.handle.net/2117/356656

  • Desai S, Goh G, Babu A, et al (2020) Lightweight convolutional representations for on-device natural language processing. arXiv preprint arXiv:2002.01535https://doi.org/10.48550/arXiv.2002.01535

  • Devlin J, Chang MW, Lee K, et al (2018) Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805https://doi.org/10.48550/arXiv.1810.04805

  • Devlin J, Chang MW, Lee K (2019) Kristina, toutanova. Bert: pre-training of deep bidirectional, transformers for language understanding. In: NAACL 2(4):5

  • Faraj D, Abdullah M (2021) Sarcasmdet at semeval-2021 task 7: Detect humor and offensive based on demographic factors using roberta pre-trained model. In: Proceedings of the 15th international workshop on semantic evaluation (SemEval-2021), pp 527–533. https://doi.org/10.18653/v1/2021.semeval-1.64

  • Farzin B, Czapla P, Howard J (2019) Applying a pre-trained language model to spanish twitter humor prediction. arXiv preprint arXiv:1907.03187https://doi.org/10.48550/arXiv.1907.03187

  • Ghosh A, Li G, Veale T, et al (2015) Semeval-2015 task 11: sentiment analysis of figurative language in twitter. In: Proceedings of the 9th international workshop on semantic evaluation (SemEval 2015), pp 470–478. https://doi.org/10.18653/v1/s15-2080

  • Giora R, Fein O (1999) Irony: context and salience. Metaphor Symbol 14(4):241–257

    Article  Google Scholar 

  • Giudice V (2019) Aspie96 at haha (iberlef 2019): Humor detection in spanish tweets with character-level convolutional rnn. In: IberLEF@ SEPLN, pp 165–171

  • González JÁ, Hurtado LF, Pla F (2018) Elirf-upv at semeval-2018 tasks 1 and 3: affect and irony detection in tweets. In: Proceedings of The 12th international workshop on semantic evaluation, pp 565–569. https://doi.org/10.18653/v1/s18-1092

  • González-Ibánez R, Muresan S, Wacholder N (2011) Identifying sarcasm in twitter: a closer look. In: Proceedings of the 49th annual meeting of the association for computational linguistics: human language technologies, pp 581–586

  • Graff M, Tellez ES, Miranda-Jiménez S, et al (2016) Evodag: a semantic genetic programming python library. In: 2016 IEEE international autumn meeting on power, electronics and computing (ROPEC), IEEE, pp 1–6. https://doi.org/10.1109/ROPEC.2016.7830633

  • Graff M, Miranda-Jimenez S, Tellez ES et al (2020) Evomsa: a multilingual evolutionary approach for sentiment analysis [application notes]. IEEE Comput Intell Mag 15(1):76–88. https://doi.org/10.1109/MCI.2019.2954668

    Article  Google Scholar 

  • Graves A, Schmidhuber J (2005) Framewise phoneme classification with bidirectional lstm networks. In: Proceedings. 2005 IEEE international joint conference on neural networks, 2005., IEEE, pp 2047–2052. https://doi.org/10.1109/IJCNN.2005.1556215

  • Grover K, Goel T (2021) Haha@ iberlef2021: Humor analysis using ensembles of simple transformers. In: Proceedings of the Iberian languages evaluation forum (IberLEF 2021), CEUR Workshop Proceedings, Málaga, Spain

  • Guan Z, Zhou XZ (2021) Tsia at semeval-2021 task 7: Detecting and rating humor and offense. In: Proceedings of the 15th international workshop on semantic evaluation (SemEval-2021), pp 1108–1113. https://doi.org/10.18653/v1/2021.semeval-1.154

  • Han B, Cook P, Baldwin T (2012) Automatically constructing a normalisation dictionary for microblogs. In: Proceedings of the 2012 joint conference on empirical methods in natural language processing and computational natural language learning, pp 421–432. https://aclanthology.org/D12-1039

  • Hasan MK, Lee S, Rahman W, et al (2021) Humor knowledge enriched transformer for understanding multimodal humor. In: Proceedings of the AAAI conference on artificial intelligence, pp 12972–12980

  • Hochreiter S, Schmidhuber J (1997) Long short-term memory. Neural Comput 9(8):1735–1780. https://doi.org/10.1162/neco.1997.9.8.1735

    Article  Google Scholar 

  • Hoicka E (2014) The pragmatic development of humor. Prag Develop First Lang Acquisit 10:219

    Google Scholar 

  • Howard J, Gugger S (2020) Fastai: a layered api for deep learning. Information 11(2):108. https://doi.org/10.3390/info11020108

    Article  Google Scholar 

  • Howard J, Ruder S (2018) Universal language model fine-tuning for text classification. arXiv preprint arXiv:1801.06146https://doi.org/10.48550/arXiv.1801.06146

  • Huang HH, Chen CC, Chen HH (2018) Disambiguating false-alarm hashtag usages in tweets for irony detection. In: Proceedings of the 56th annual meeting of the association for computational linguistics (volume 2: Short Papers), pp 771–777. https://doi.org/10.18653/v1/p18-2122

  • Hulstijn J (1996) Automatic interpretation and generation of verbal humor. In: Proceedings o the IWCH96

  • Ilić S, Marrese-Taylor E, Balazs JA, et al (2018) Deep contextualized word representations for detecting sarcasm and irony. arXiv preprint arXiv:1809.09795https://doi.org/10.48550/arXiv.1809.09795

  • Ismailov A (2019) Humor analysis based on human annotation challenge at iberlef 2019: first-place solution. In: IberLEF@ SEPLN, pp 160–164

  • Joshi A, Sharma V, Bhattacharyya P (2015) Harnessing context incongruity for sarcasm detection. In: Proceedings of the 53rd annual meeting of the association for computational linguistics and the 7th international joint conference on natural language processing (volume 2: Short Papers), pp 757–762. https://doi.org/10.3115/v1/p15-2124

  • Jr RWG, O’Brien JE, Doolittle S (1995) Inferring meanings that are not intended: Speakers’ intentions and irony comprehension. Discourse Process 20(2):187–203. https://doi.org/10.1080/01638539509544937

  • Khandelwal A, Swami S, Akhtar SS, et al (2018) Humor detection in english-hindi code-mixed social media content: Corpus and baseline system. arXiv preprint arXiv:1806.05513https://doi.org/10.48550/arXiv.1806.05513

  • Kui Y (2021) Applying pre-trained model and fine-tune to conduct humor analysis on spanish tweets. In: Proceedings of the Iberian languages evaluation forum (IberLEF 2021), CEUR workshop proceedings, Málaga, Spain

  • Lan Z, Chen M, Goodman S, et al (2019) Albert: A lite bert for self-supervised learning of language representations. arXiv preprint arXiv:1909.11942https://doi.org/10.48550/arXiv.1909.11942

  • Liebrecht C, Kunneman F, van den Bosch A (2013) The perfect solution for detecting sarcasm in tweets# not. In: Proceedings of the 4th workshop on computational approaches to subjectivity, sentiment and social media analysis, pp 29–37

  • Liu F, Weng F, Jiang X (2012) A broad-coverage normalization system for social media language. In: Proceedings of the 50th annual meeting of the association for computational linguistics (volume 1: Long Papers), pp 1035–1044. https://aclanthology.org/P12-1109

  • Liu P, Li W, Zou L (2019a) Nuli at semeval-2019 task 6: Transfer learning for offensive language detection using bidirectional transformers. In: SemEval@ NAACL-HLT, pp 87–91, https://doi.org/10.18653/v1/s19-2011

  • Liu Y, Ott M, Goyal N, et al (2019b) Roberta: a robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692https://doi.org/10.48550/arXiv.1907.11692

  • Loper E, Bird S (2002) Nltk: the natural language toolkit. arXiv preprint cs/0205028 https://doi.org/10.48550/arXiv.cs/0205028

  • Lozano-Palacio I, de Mendoza Ibáñez FJR (2022) Modeling Irony: a cognitive-pragmatic account. John Benjamins

  • Mao J, Liu W (2019) A bert-based approach for automatic humor detection and scoring. In: IberLEF@ SEPLN, pp 197–202

  • Maynard DG, Greenwood MA (2014) Who cares about sarcastic tweets? investigating the impact of sarcasm on sentiment analysis. In: Lrec 2014 proceedings, ELRA

  • Meaney J, Wilson SR, Chiruzzo L, et al (2021) Semeval 2021 task 7, hahackathon, detecting and rating humor and offense. In: Proceedings of the 59th annual meeting of the association for computational linguistics and the 11th international joint conference on natural language processing. https://doi.org/10.18653/v1/2021.semeval-1.9

  • Meyer JC (2000) Humor as a double-edged sword: four functions of humor in communication. Commun Theory 10(3):310–331. https://doi.org/10.1111/j.1468-2885.2000.tb00194.x

    Article  Google Scholar 

  • Miller T, Do Dinh EL, Simpson E, et al (2019) Ofai-ukp at haha@ iberlef2019: predicting the humorousness of tweets using gaussian process preference learning. In: IberLEF@ SEPLN, pp 180–190

  • Miyato T, Dai AM, Goodfellow I (2016) Adversarial training methods for semi-supervised text classification. arXiv preprint arXiv:1605.07725https://doi.org/10.48550/arXiv.1605.07725

  • Mondal A, Sharma R (2021) Team_kgp at semeval-2021 task 7: a deep neural system to detect humor and offense with their ratings in the text data. In: Proceedings of the 15th international workshop on semantic evaluation (SemEval-2021), pp 1169–1174. https://doi.org/10.18653/v1/2021.semeval-1.164

  • Nanda A, Singh AP, Gupta A, et al (2021) Techssn at haha@ iberlef 2021: Humor detection and funniness score prediction using deep learning. In: Proceedings of the Iberian languages evaluation forum (IberLEF 2021), CEUR workshop proceedings, Málaga, Spain

  • Ortega-Bueno R, Muniz-Cuza CE, Pagola JEM, et al (2018) Uo upv: Deep linguistic humor detection in spanish social media. In: Proceedings of the third workshop on evaluation of human language technologies for Iberian languages (IberEval 2018) co-located with 34th conference of the Spanish society for natural language processing (SEPLN 2018), pp 204–213

  • Ortega-Bueno R, Rosso P, Pagola JEM (2019) Uo upv2 at haha 2019: Bigru neural network informed with linguistic features for humor recognition. In: Proceedings of the Iberian languages evaluation forum (IberLEF 2019). CEUR workshop proceedings, CEUR-WS, Bilbao, Spain (9 2019)

  • Ortiz-Bejar J, Salgado V, Graff M, et al (2018) Ingeotec at ibereval 2018 task haha: \(\mu\)tc and evomsa to detect and score humor in texts. In: Proceedings of the third workshop on evaluation of human language technologies for Iberian languages (IberEval 2018) co-located with 34th conference of the Spanish sSociety for natural language processing (SEPLN 2018)

  • Ortiz-Bejar J, Tellez ES, Graff M, et al (2019) Ingeotec at iberlef 2019 task haha. In: IberLEF@ SEPLN, pp 203–211

  • Padró L, Stanilovsky E (2012) Freeling 3.0: towards wider multilinguality. In: LREC2012. http://hdl.handle.net/2117/15986

  • Pamungkas EW, Patti V (2018) # nondicevosulserio at semeval-2018 task 3: Exploiting emojis and affective content for irony detection in english tweets. In: International workshop on semantic evaluation, Association for Computational Linguistics, pp 649–654. https://doi.org/10.18653/v1/s18-1106

  • Pannu A (2015) Artificial intelligence and its application in different areas. Artif Intell 4(10):79–84

    Google Scholar 

  • Peña MS, Ruiz de Mendoza FJ (2017) Construing and constructing hyperbole. Stud Figurative Thought Lang 56:41

    Google Scholar 

  • Pennebaker JW, Francis ME, Booth RJ (2001) Linguistic inquiry and word count: Liwc 2001. Mahway: Lawrence Erlbaum Associates 71(2001):2001

  • Pennington J, Socher R, Manning CD (2014) Glove: global vectors for word representation. In: Proceedings of the 2014 conference on empirical methods in natural language processing (EMNLP), pp 1532–1543. https://doi.org/10.3115/v1/d14-1162

  • Peters ME, Neumann M, Iyyer M, et al (2018) Deep contextualized word representations. In: Proceedings of the NAACL. https://doi.org/10.18653/v1/n18-1202

  • Raghunathan A, Xie SM, Yang F, et al (2019) Adversarial training can hurt generalization. arXiv preprint arXiv:1906.06032https://doi.org/10.48550/arXiv.1906.06032

  • Rangwani H, Kulshreshtha D, Singh AK (2018) Nlprl-iitbhu at semeval-2018 task 3: combining linguistic features and emoji pre-trained cnn for irony detection in tweets. In: Proceedings of the 12th international workshop on semantic evaluation, pp 638–642. https://doi.org/10.18653/v1/s18-1104

  • Reyes A, Rosso P, Buscaldi D (2012) From humor recognition to irony detection: The figurative language of social media. Data Knowl Eng 74:1–12. https://doi.org/10.1016/j.datak.2012.02.005, www.sciencedirect.com/science/article/pii/S0169023X12000237, applications of Natural Language to Information Systems

  • Reyes A, Rosso P, Buscaldi D (2012) From humor recognition to irony detection: the figurative language of social media. Data Knowl Eng 74:1–12. https://doi.org/10.1016/j.datak.2012.02.005

    Article  Google Scholar 

  • Reyes A, Rosso P, Veale T (2013) A multidimensional approach for detecting irony in twitter. Lang Res Eval 47(1):239–268. https://doi.org/10.1007/s10579-012-9196-x

    Article  Google Scholar 

  • Ribeiro MT, Singh S, Guestrin C (2016) “ why should i trust you?” explaining the predictions of any classifier. In: Proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining, pp 1135–1144. https://doi.org/10.1145/2939672.2939778

  • Rohanian O, Taslimipoor S, Evans R, et al (2018) Wlv at semeval-2018 task 3: Dissecting tweets in search of irony. Association for Computational Linguistics. https://doi.org/10.18653/v1/s18-1090

  • Ruiz de Mendoza F, Lozano I (2021) On verbal and situational irony: towards a unified approach. https://doi.org/10.1075/ftl.11.07rui

  • Sennrich R, Haddow B, Birch A (2015) Neural machine translation of rare words with subword units. arXiv preprint arXiv:1508.07909https://doi.org/10.48550/arXiv.1508.07909

  • Sharma C, Bhageria D, Scott W, et al (2020) Semeval-2020 task 8: Memotion analysis–the visuo-lingual metaphor! arXiv preprint arXiv:2008.03781https://doi.org/10.48550/arXiv.2008.03781

  • Song B, Pan C, Wang S, et al (2021) Deepblueai at semeval-2021 task 7: Detecting and rating humor and offense with stacking diverse language model-based methods. In: Proceedings of the 15th international workshop on semantic evaluation (SemEval-2021), pp 1130–1134. https://doi.org/10.18653/v1/2021.semeval-1.158

  • Sperber D, Wilson D (1981) Irony and the use-mention distinction. Philosophy 3:143–184

    Google Scholar 

  • Swamy SD, Jamatia A, Gambäck B, et al (2019) Nit_agartala_nlp_team at semeval-2019 task 6: An ensemble approach to identifying and categorizing offensive language in twitter social media corpora. In: NAACL HLT 2019 the international workshop on semantic evaluation proceedings of the thirteenth workshop, Association for Computational Linguistics. https://doi.org/10.18653/v1/s19-2124

  • Swamy SD, Laddha S, Abdussalam B, et al (2020) Nit-agartala-nlp-team at semeval-2020 task 8: building multimodal classifiers to tackle internet humor. arXiv preprint arXiv:2005.06943https://doi.org/10.48550/arXiv.2005.06943

  • Tasneem F, Naim J, Chy AN (2020) Harnessing ensemble of data preprocessing and hand-crafted features for irony detection in tweets. In: 2020 23rd international conference on computer and information technology (ICCIT), IEEE, pp 1–6, https://doi.org/10.1109/iccit51783.2020.9392711

  • Tay Y, Zhang A, Tuan LA, et al (2019) Lightweight and efficient neural natural language processing with quaternion networks. arXiv preprint arXiv:1906.04393https://doi.org/10.48550/arXiv.1906.04393

  • Tay Y, Dehghani M, Bahri D, et al (2020) Efficient transformers: a survey. arXiv preprint arXiv:2009.06732https://doi.org/10.48550/arXiv.2009.06732

  • Tellez ES, Miranda-Jiménez S, Graff M, et al (2017) A simple approach to multilingual polarity classification in twitter. Pattern Recogn Lett 94:68–74. https://doi.org/10.48550/arXiv.1612.05270

  • Tellez ES, Moctezuma D, Miranda-Jiménez S, et al (2018) An automated text categorization framework based on hyperparameter optimization. Knowl Based Syst 149:110–123. https://doi.org/10.48550/arXiv.1704.01975

  • Tobin V, Israel M (2012) Irony as a viewpoint phenomenon. In: Viewpoint in language: a multimodal perspective, pp 25–46

  • Tomás D, Ortega-Bueno R, Zhang G, et al (2022) Transformer-based models for multimodal irony detection. J Ambient Intell Human Comput, pp 1–12

  • Tsipras D, Santurkar S, Engstrom L, et al (2018) Robustness may be at odds with accuracy. arXiv preprint arXiv:1805.12152https://doi.org/10.48550/arXiv.1805.12152

  • van den Beukel S, Aroyo L (2018) Homonym detection for humor recognition in short text. In: Proceedings of the 9th workshop on computational approaches to subjectivity, sentiment and social media analysis, pp 286–291. https://doi.org/10.18653/v1/w18-6242

  • Van Hee C, Lefever E, Hoste V (2018) Semeval-2018 task 3: Irony detection in english tweets. In: Proceedings of The 12th international workshop on semantic evaluation, pp 39–50. https://doi.org/10.18653/v1/s18-1005

  • Wang SI, Manning CD (2012) Baselines and bigrams: Simple, good sentiment and topic classification. In: Proceedings of the 50th annual meeting of the association for computational linguistics (volume 2: Short Papers), pp 90–94. https://aclanthology.org/P12-2018

  • Weller O, Seppi K (2019) Humor detection: a transformer gets the last laugh. arXiv preprint arXiv:1909.00252https://doi.org/10.48550/arXiv.1909.00252

  • Wilson D (2006) The pragmatics of verbal irony: Echo or pretence? Lingua 116(10):1722–1743. https://doi.org/10.1016/j.lingua.2006.05.001. (Language in mind: a tribute to Neil Smith on the Occasion of his Retirement)

    Article  Google Scholar 

  • Wilson D, Sperber D (1992) On verbal irony. Lingua 87(1):53–76

    Article  Google Scholar 

  • Wilson D, Sperber D (2012) Explaining irony. Meaning Relevance, pp 123–145

  • Wu C, Wu F, Wu S, et al (2018) Thu_ngn at semeval-2018 task 3: Tweet irony detection with densely connected lstm and multi-task learning. In: Proceedings of The 12th international workshop on semantic evaluation, pp 51–56. https://doi.org/10.18653/v1/s18-1006

  • Zampieri M, Malmasi S, Nakov P, et al (2019) Semeval-2019 task 6: Identifying and categorizing offensive language in social media (offenseval). arXiv preprint arXiv:1903.08983https://doi.org/10.48550/arXiv.1903.08983

  • Zhang M, Yang J, Teng Z, et al (2016) Libn3l: a lightweight package for neural nlp. In: Proceedings of the tenth international conference on language resources and evaluation (LREC’16), pp 225–229. https://aclanthology.org/L16-1034

  • Zhao X, Xu B, Zheng D, et al (2018) Tweet irony detection using ensembles of word level attentive long short-term memory and convolutional neural network. In: 2018 14th international conference on natural computation, fuzzy systems and knowledge discovery (ICNC-FSKD), IEEE, pp 524–529. https://doi.org/10.1109/fskd.2018.8687128

  • Zhao Y, Tao X (2021) Zyj at semeval-2021 task 7: Hahackathon: Detecting and rating humor and offense with albert-based model. In: Proceedings of the 15th international workshop on semantic evaluation (SemEval-2021), pp 1175–1178. https://doi.org/10.18653/v1/2021.semeval-1.165

  • Zhou C, Sun C, Liu Z, et al (2015) A c-lstm neural network for text classification. arXiv preprint arXiv:1511.08630https://doi.org/10.48550/arXiv.1511.08630

  • Zylich B, Gugnani A, Brookman G, et al (2021) Amherst685 at semeval-2021 task 7: joint modeling of classification and regression for humor and offense. In: Proceedings of the 15th international workshop on semantic evaluation (SemEval-2021), pp 1190–1195. https://doi.org/10.18653/v1/2021.semeval-1.168

Download references

Funding

Not applicable.

Author information

Author notes

  1. Radiathun Tasnia, Nabila Ayman, Afrin Sultana have contributed equally to this work.

Authors and Affiliations

  1. Department of Computer Science and Engineering, University of Chittagong, Hathazari, Chittagong, 4331, Bangladesh

    Radiathun Tasnia, Nabila Ayman, Afrin Sultana & Abu Nowshed Chy

  2. Department of Computer Science and Engineering, Toyohashi University of Technology, 1-1 Hibarigaoka, Tempaku-cho, Toyohashi, Aichi, 441-8580, Japan

    Masaki Aono

Authors
  1. Radiathun Tasnia
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Nabila Ayman
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Afrin Sultana
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Abu Nowshed Chy
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Masaki Aono
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

Radiathun Tasnia, Nabila Ayman, and Afrin Sultana were responsible for conceptualization, methodology, software, investigation, writing the original draft, and reviewing. Abu Nowshed Chy was involved in conceptualization, methodology, validation, writing—reviewing and editing, and supervision. Masaki Aono contributed to conceptualization, methodology, writing—review and editing, and supervision.

Corresponding author

Correspondence to Radiathun Tasnia.

Ethics declarations

Conflict of interest

The authors declare no competing interests.

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Tasnia, R., Ayman, N., Sultana, A. et al. Exploiting stacked embeddings with LSTM for multilingual humor and irony detection. Soc. Netw. Anal. Min. 13, 43 (2023). https://doi.org/10.1007/s13278-023-01049-0

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • DOI: https://doi.org/10.1007/s13278-023-01049-0

Keywords

Search

Navigation