{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,18]],"date-time":"2026-05-18T10:20:44Z","timestamp":1779099644517,"version":"3.51.4"},"reference-count":39,"publisher":"SAGE Publications","issue":"1-2","license":[{"start":{"date-parts":[[2023,12,8]],"date-time":"2023-12-08T00:00:00Z","timestamp":1701993600000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["DS"],"published-print":{"date-parts":[[2023,12,8]]},"abstract":"<jats:p>Sarcasm is a linguistic phenomenon often indicating a disparity between literal and inferred meanings. Due to its complexity, it is typically difficult to discern it within an online text message. Consequently, in recent years sarcasm detection has received considerable attention from both academia and industry. Nevertheless, the majority of current approaches simply model low-level indicators of sarcasm in various machine learning algorithms. This paper aims to present sarcasm in a new light by utilizing novel indicators in a deep weighted average ensemble-based framework (DWAEF). The novel indicators pertain to exploiting the presence of simile and metaphor in text and detecting the subtle shift in tone at a sentence\u2019s structural level. A\u00a0graph neural network (GNN) structure is implemented to detect the presence of simile, bidirectional encoder representations from transformers (BERT) embeddings are exploited to detect metaphorical instances and fuzzy logic is employed to account for the shift of tone. To account for the existence of sarcasm, the DWAEF integrates the inputs from the novel indicators. The performance of the framework is evaluated on a self-curated dataset of online text messages. A comparative report between the results acquired using primitive features and those obtained using a combination of primitive features and proposed indicators is provided. The highest accuracy of 92% was achieved after applying DWAEF, the proposed framework which combines the primitive features and novel indicators together as compared to 78.58% obtained using Support Vector Machine (SVM) which was the lowest among all classifiers.<\/jats:p>","DOI":"10.3233\/ds-220058","type":"journal-article","created":{"date-parts":[[2023,8,25]],"date-time":"2023-08-25T10:33:26Z","timestamp":1692959606000},"page":"17-44","source":"Crossref","is-referenced-by-count":5,"title":["DWAEF: a deep weighted average ensemble framework harnessing novel indicators for sarcasm\u00a0detection1"],"prefix":"10.1177","volume":"6","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4472-1681","authenticated-orcid":false,"given":"Richa","family":"Sharma","sequence":"first","affiliation":[{"name":"Department of Computer Science, Keshav Mahavidyalaya, University of Delhi, India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6785-9691","authenticated-orcid":false,"given":"Simrat","family":"Deol","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Keshav Mahavidyalaya, University of Delhi, India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0636-4000","authenticated-orcid":false,"given":"Udit","family":"Kaushish","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Keshav Mahavidyalaya, University of Delhi, India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3340-8112","authenticated-orcid":false,"given":"Prakher","family":"Pandey","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Keshav Mahavidyalaya, University of Delhi, India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5169-209X","authenticated-orcid":false,"given":"Vishal","family":"Maurya","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Keshav Mahavidyalaya, University of Delhi, India"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"179","reference":[{"key":"10.3233\/DS-220058_ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICICS55353.2022.9811196"},{"key":"10.3233\/DS-220058_ref2","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1908.07442"},{"issue":"5","key":"10.3233\/DS-220058_ref3","first-page":"683","article-title":"Sarcasm and similes","volume":"27","author":"Attardo","year":"1997","journal-title":"Journal of Pragmatics"},{"key":"10.3233\/DS-220058_ref4","doi-asserted-by":"publisher","DOI":"10.1007\/BF00116827"},{"key":"10.3233\/DS-220058_ref5","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/S15-2119"},{"key":"10.3233\/DS-220058_ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.figlang-1.12"},{"key":"10.3233\/DS-220058_ref7","unstructured":"V.\u00a0Basile, It\u2019s the end of the gold standard as we know it. On the impact of pre-aggregation on the evaluation of highly subjective tasks, in: Proceedings of the AIxIA 2020 Discussion Papers Workshop Co-Located with the 19th International Conference of the Italian Association for Artificial Intelligence (AIxIA2020), Vols\u00a02776, CEUR-WS, 2020, pp.\u00a031\u201340, http:\/\/ceur-ws.org\/Vol-2776\/paper-4.pdf."},{"key":"10.3233\/DS-220058_ref9","doi-asserted-by":"publisher","first-page":"5477","DOI":"10.1109\/ACCESS.2016.2594194","article-title":"A pattern-based approach for sarcasm detection on Twitter","volume":"4","author":"Bouazizi","year":"2016","journal-title":"IEEE Access"},{"key":"10.3233\/DS-220058_ref10","doi-asserted-by":"publisher","DOI":"10.1109\/WiSPNET.2017.8300120"},{"issue":"2","key":"10.3233\/DS-220058_ref12","doi-asserted-by":"publisher","first-page":"241","DOI":"10.1007\/s11704-019-8208-z","article-title":"A survey on ensemble learning","volume":"14","author":"Dong","year":"2020","journal-title":"Frontiers of Computer Science"},{"key":"10.3233\/DS-220058_ref13","unstructured":"J.\u00a0Eisenstein, What to do about bad language on the Internet, in: Proceedings of the 2013 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Association for Computational Linguistics, Atlanta, Georgia, 2013, pp.\u00a0359\u2013369, https:\/\/aclanthology.org\/N13-1037."},{"key":"10.3233\/DS-220058_ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2021.116398"},{"key":"10.3233\/DS-220058_ref15","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-022-12930-z"},{"key":"10.3233\/DS-220058_ref16","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2005.1555942"},{"key":"10.3233\/DS-220058_ref17","doi-asserted-by":"crossref","unstructured":"K.\u00a0Hallmann, F.\u00a0Kunneman, C.\u00a0Liebrecht, A.\u00a0van den Bosch and M.\u00a0van Mulken, Sarcastic soulmates: Intimacy and irony markers in social media messaging, in: Linguistic Issues in Language Technology, Vols\u00a0Linguistic Issues in Language Technology, Volume 14, 2016 \u2013 Modality: Logic, Semantics, Annotation, and Machine Learning, 2016. https:\/\/aclanthology.org\/2016.lilt-14.7","DOI":"10.33011\/lilt.v14i.1405"},{"key":"10.3233\/DS-220058_ref18","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1706.02216"},{"key":"10.3233\/DS-220058_ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3422713.3422722"},{"key":"10.3233\/DS-220058_ref20","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1704.05579"},{"key":"10.3233\/DS-220058_ref21","doi-asserted-by":"publisher","DOI":"10.3115\/1611528.1611531"},{"key":"10.3233\/DS-220058_ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.figlang-1.36"},{"issue":"4","key":"10.3233\/DS-220058_ref24","doi-asserted-by":"publisher","first-page":"285","DOI":"10.1007\/BF00116827","article-title":"Learning quickly when irrelevant attributes abound: A new linear-threshold algorithm","volume":"2","author":"Littlestone","year":"1988","journal-title":"Machine Learning"},{"key":"10.3233\/DS-220058_ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3463061"},{"key":"10.3233\/DS-220058_ref28","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/P14-5010"},{"key":"10.3233\/DS-220058_ref29","unstructured":"D.G.\u00a0Maynard and M.A.\u00a0Greenwood, Who cares about sarcastic tweets? Investigating the impact of sarcasm on sentiment analysis, in: Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC\u201914), ELRA, 2014. http:\/\/www.lrec-conf.org\/proceedings\/lrec2014\/pdf\/67_Paper.pdf."},{"issue":"4","key":"10.3233\/DS-220058_ref30","doi-asserted-by":"publisher","first-page":"465","DOI":"10.1080\/09720529.2019.1637152","article-title":"Identification of sarcasm using word embeddings and hyperparameters tuning","volume":"22","author":"Mehndiratta","year":"2019","journal-title":"Journal of Discrete Mathematical Sciences and Cryptography"},{"issue":"11","key":"10.3233\/DS-220058_ref32","doi-asserted-by":"publisher","first-page":"2725","DOI":"10.1002\/asi.23624","article-title":"Identification of nonliteral language in social media: A case study on sarcasm","volume":"67","author":"Muresan","year":"2016","journal-title":"Journal of the Association for Information Science and Technology"},{"key":"10.3233\/DS-220058_ref34","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1215"},{"key":"10.3233\/DS-220058_ref35","first-page":"125","article-title":"Is a metaphor (like) a simile? Differences in meaning, effect and processing","volume":"21","author":"O\u2019Donoghue","year":"2009","journal-title":"UCL Working Papers in Linguistics"},{"key":"10.3233\/DS-220058_ref36","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2021.102544"},{"key":"10.3233\/DS-220058_ref37","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2106.09462"},{"key":"10.3233\/DS-220058_ref39","unstructured":"M.\u00a0Popa-Wyatt, Ironic metaphor: A case for metaphor\u2019s contribution to truth-conditions, in: The Mind and Across Minds: A Relevance-Theoretic Perspective on Communication and Translation, E.\u00a0Walaszewska, M.\u00a0Kisielewska-Krysiuk and A.\u00a0Piskorska, eds, 2010. https:\/\/philarchive.org\/archive\/MIHIMA."},{"key":"10.3233\/DS-220058_ref40","doi-asserted-by":"publisher","DOI":"10.1145\/2684822.2685316"},{"key":"10.3233\/DS-220058_ref41","doi-asserted-by":"publisher","first-page":"68609","DOI":"10.1109\/ACCESS.2021.3076789","article-title":"Sarcasm detection using deep learning with contextual features","volume":"9","author":"Razali","year":"2021","journal-title":"IEEE Access"},{"issue":"4","key":"10.3233\/DS-220058_ref42","doi-asserted-by":"publisher","first-page":"754","DOI":"10.1016\/j.dss.2012.05.027","article-title":"Making objective decisions from subjective data: Detecting irony in customer reviews","volume":"53","author":"Reyes","year":"2012","journal-title":"Decision Support Systems"},{"key":"10.3233\/DS-220058_ref43","unstructured":"E.\u00a0Riloff, A.\u00a0Qadir, P.\u00a0Surve, L.\u00a0De Silva, N.\u00a0Gilbert and R.\u00a0Huang, Sarcasm as contrast between a positive sentiment and negative situation, in: Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing, 2013, pp.\u00a0704\u2013714. https:\/\/aclanthology.org\/D13-1066.pdf."},{"issue":"5","key":"10.3233\/DS-220058_ref44","doi-asserted-by":"publisher","first-page":"578","DOI":"10.1177\/1470785320921779","article-title":"Sarcasm detection using machine learning algorithms in Twitter: A systematic review","volume":"62","author":"Sarsam","year":"2020","journal-title":"International Journal of Market Research"},{"issue":"1","key":"10.3233\/DS-220058_ref45","doi-asserted-by":"publisher","first-page":"1687","DOI":"10.2991\/ijcis.d.201012.002","article-title":"Simpful: A user-friendly python library for fuzzy logic","volume":"13","author":"Spolaor","year":"2020","journal-title":"International Journal of Computational Intelligence Systems"},{"key":"10.3233\/DS-220058_ref46","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462809"},{"issue":"4","key":"10.3233\/DS-220058_ref48","doi-asserted-by":"publisher","first-page":"83","DOI":"10.1109\/2.53","article-title":"Fuzzy logic","volume":"21","author":"Zadeh","year":"1988","journal-title":"Computer"}],"container-title":["Data Science"],"original-title":[],"link":[{"URL":"https:\/\/content.iospress.com\/download?id=10.3233\/DS-220058","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,28]],"date-time":"2026-04-28T18:10:10Z","timestamp":1777399810000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/full\/10.3233\/DS-220058"}},"subtitle":[],"editor":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5098-5667","authenticated-orcid":false,"given":"Jodi","family":"Schneider","sequence":"additional","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1267-0234","authenticated-orcid":false,"given":"Tobias","family":"Kuhn","sequence":"additional","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2023,12,8]]},"references-count":39,"journal-issue":{"issue":"1-2"},"URL":"https:\/\/doi.org\/10.3233\/ds-220058","relation":{},"ISSN":["2451-8492","2451-8484"],"issn-type":[{"value":"2451-8492","type":"electronic"},{"value":"2451-8484","type":"print"}],"subject":[],"published":{"date-parts":[[2023,12,8]]}}}