Facebook pixel tracking

The Science and Information (SAI) Organization publishes open-access peer-reviewed journals in computer science and artificial intelligence.

Contact Info
Website thesai.org
Follow Us
Contact Info
Follow Us
Research Article | Open Access |

Modeling of Artificial Intelligence-Driven Context-Aware Memotion Analysis Using Integrated Large-Scale Multimodal Corpora

Author 1: Rania Aboalela
International Journal of Advanced Computer Science and Applications (IJACSA) · Vol. 17, No. 10 · Published 2026

DOI: 10.14569/IJACSA.2026.0171063

Abstract

Memotion analysis is a complex task designed to accurately identify the sentiments and feelings conveyed within internet memes. A meme is any trend, skill, or belief learned from others, rather than inherited genetically, and shared through imitation. The spread of malicious and aggressive memes has aggravated issues on social media, driving the need for this research to address and overcome such digital threats. Based on the fact that challenging memes require visual and language knowledge, recognizing offensive memes is more complex than sensing invasive texts. With the expansion of artificial intelligence (AI) and deep learning (DL) techniques, there has been an increasing interest in automatic analysis of such creative multimodal content, where the natural language processing (NLP) and computer vision (CV) research communities have usually been attentive to a single dominant modality in isolation. This study presents an Artificial Intelligence Driven Context-Aware Memotion Analysis Using Integrated Large-Scale Multimodal Corpora (AICAMA-ILSMC) model. The proposed work aims to effectively analyze and classify memes by jointly exploiting visual and textual contexts in a unified learning architecture. In the data preprocessing stage, bilateral filtering is applied for image noise removal, while textual content is processed through optical character recognition, lowercasing, punctuation, stop-word removal, tokenization, and handling slang, emojis, and abbreviations. For feature extraction, an improved Swin Transformer is utilized to extract discriminative visual features, whereas RoBERTa-Large is employed to obtain deep contextualized text embeddings. Furthermore, the multi-modal representations are combined using a cross-modal attention-based fusion strategy to enable efficient interaction between visual and embedded textual information, producing a text-dominant fused representation. Moreover, the fused features are passed into a bidirectional long short-term memory network with a self-attention mechanism for accurate memotion classification, such as Negative and Very Negative, Positive and Very Positive, and Neutral. Finally, the Nadam optimizer is integrated into the proposed model to enhance convergence and overall model performance. A series of experimental analyses is conducted, and the outcomes can be inspected under numerous aspects. The comparison study showed the improved performance of the AICAMA-ILSMC technique compared to existing approaches.

Keywords

How to Cite this Article

Aboalela, R. (2026). Modeling of Artificial Intelligence-Driven Context-Aware Memotion Analysis Using Integrated Large-Scale Multimodal Corpora. International Journal of Advanced Computer Science and Applications, 17(10). https://doi.org/10.14569/IJACSA.2026.0171063

Aboalela, Rania. "Modeling of Artificial Intelligence-Driven Context-Aware Memotion Analysis Using Integrated Large-Scale Multimodal Corpora." International Journal of Advanced Computer Science and Applications, vol. 17, no. 10, 2026, https://doi.org/10.14569/IJACSA.2026.0171063.

@article{Aboalela2026,
  title     = {Modeling of Artificial Intelligence-Driven Context-Aware Memotion Analysis Using Integrated Large-Scale Multimodal Corpora},
  journal   = {International Journal of Advanced Computer Science and Applications},
  volume    = {17},
  number    = {10},
  year      = {2026},
  publisher = {The Science and Information Organization},
  author    = {Rania Aboalela},
  doi       = {10.14569/IJACSA.2026.0171063},
  url       = {https://doi.org/10.14569/IJACSA.2026.0171063}
}

Open Access — licensed under a Creative Commons Attribution 4.0 International License. Unrestricted use, distribution, and reproduction in any medium, even commercially, as long as the original work is properly cited.

Call for Papers - Important Dates

Volume 17 No. 12, December 2026
Paper Submission Due November 25, 2026
Review Notification December 15, 2026
Publication Date December 31, 2026