Skip to main navigation Skip to search Skip to main content

Prompt strategies for sarcastic meme detection: a comparative analysis

Faseela Abdullakutty*, Somaya Al-Maadeed, Usman Naseem

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference proceeding contributionpeer-review

Abstract

Memes, often characterized by subtle humour and irony, have become a prominent digital communication medium. Detecting sarcasm in memes presents a significant challenge due to its context-dependent nature, negatively impacting user experiences on social media platforms. To improve the ability of social media systems to recognize and manage sarcastic content, this study investigates the effectiveness of Large Language Models (LLMs) for sarcasm detection in memes. Specifically, we evaluate three prompting techniques: Standard Prompt, Chain of Thought (CoT), and Concise Chain of Thought (CCoT) to determine their impact on the classification of sarcastic memes. Using the GOAT dataset as a benchmark, the study employs four pre-trained LLMs: Flan-T5-XXL, Llama-2, Mistral 7B, and GPT-2. The research identifies the most effective prompting strategies for sarcasm detection through a comparative analysis. The results demonstrate that CoT and CCoT significantly enhance performance over the Standard Prompt, with CCoT achieving the highest accuracy, particularly with advanced models like Mistral 7B. However, the choice of prompting technique depends on both the model and task requirements, emphasizing the need for tailored approaches in sarcastic meme analysis.

Original languageEnglish
Title of host publicationWeb Information Systems Engineering – WISE 2024 PhD Symposium, Demos and Workshops
Subtitle of host publicationWEB-for-GOOD 2024, AIWDA 2024, SWIFT-AG 2024, and Demos, Doha, Qatar, December 2-5, 2024, proceedings
EditorsMahmoud Barhamgi, Hua Wang, Xin Wang, Esma Aïmeur, Michael Mrissa, Belkacem Chikhaoui, Khouloud Boukadi, Rima Grati, Zakaria Maamar
Place of PublicationSingapore
PublisherSpringer, Springer Nature
Pages285-298
Number of pages14
ISBN (Electronic)9789819614837
ISBN (Print)9789819614820
DOIs
Publication statusPublished - 2025
EventPhD Symposium, Posters, Demos, and A Web for more inclusive, sustainable and prosperous societies, WEB-for-GOOD 2024 and 1st International Workshop on AI and Web Data Analytics, AIWDA 2024 form the 25th International Conference on Web Information Systems Engineering, WISE 2024 - Doha, Qatar
Duration: 2 Dec 20245 Dec 2024

Publication series

NameLecture Notes in Computer Science
PublisherSpringer
Volume15463
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349

Conference

ConferencePhD Symposium, Posters, Demos, and A Web for more inclusive, sustainable and prosperous societies, WEB-for-GOOD 2024 and 1st International Workshop on AI and Web Data Analytics, AIWDA 2024 form the 25th International Conference on Web Information Systems Engineering, WISE 2024
Country/TerritoryQatar
CityDoha
Period2/12/245/12/24

Keywords

  • Meme detection
  • Prompting
  • LLMs

Fingerprint

Dive into the research topics of 'Prompt strategies for sarcastic meme detection: a comparative analysis'. Together they form a unique fingerprint.

Cite this