DATA ANALYTICS SYSTEM FOR OFFENSIVE MEMES TEXT CLASSIFICATION IN SOCIAL NETWORK
DOI:
https://doi.org/10.29121/shodhkosh.v5.i6.2024.4162Keywords:
Memes Classification, Convolutional Neural Network, Optical Character Recognition, VADER AlgorithmAbstract [English]
Sentiment analysis has evolved as a pivotal element of understanding mortal feelings and opinions in the digital period. Memes, as a popular form of online communication, frequently synopsize sentiments in a visually engaging manner. In the realm of online communication, the frequence of multi-modal content, particularly memes combining textbook and images, has raised enterprises regarding the dispersion of obnoxious or dangerous material. This exploration proposes a new approach grounded on deep literacy ways for the bracket of obnoxious memes in multi- modal data sets to address this issue. The vital task involves the comprehensive analysis of both textual and visual factors to directly identify and classify unhappy content. We're proposing a new approach in this study. sentiment analysis from meme images using Optical Character Recognition (OCR) technology with Deep literacy algorithms for textbook bracket and image bracket using Conventional neural network algorithm. Our approach involves rooting textbook content from meme images using OCR, enabling the analysis of textual rudiments to infer sentiments. Through this innovative approach, we aim to enhance analysis capabilities in the visual content using pretrained Conventional neural network model. The proposed methodology demonstrates promising results, slipping light on the eventuality for OCR driven VADER sentiment analysis and Pretrained CNN to classify the nuanced feelings bedded in meme culture and contribute to a further comprehensive understanding of online sentiment dynamics.
References
Cao, Rui, et al. "Prompting for multimodal hateful meme classification." arXiv preprint arXiv:2302.04156 (2023). DOI: https://doi.org/10.18653/v1/2022.emnlp-main.22
Suryawanshi, Shardul, eal."Multimodal Offensive Meme Classification with Natural Language Inference." Proceedings of the 4th Conference on Language, Data and Knowledge.2023.
Thakur, Abhinav Kumar, et al. "Explainable Classification of Internet Memes." (2023).
Grasso, Biagio, et al. "KERMIT: Knowledge- EmpoweRed Model In harmful meme deTection." Information Fusion 106(2024): 102269. DOI: https://doi.org/10.1016/j.inffus.2024.102269
Yang, Chuanpeng, et al. "Invariant Meets Specific: A Scalable Harmful Memes Detection Framework." Proceedings of the31st ACM International Conference on Multimedia. 2023. DOI: https://doi.org/10.1145/3581783.3611761
Pramanick, Shraman, et al. "Detecting harmful memes and their targets." arXiv preprint arXiv:2110.00413 (2021). DOI: https://doi.org/10.18653/v1/2021.findings-acl.246
Zhong, Xiayu. "Classification of Multimodal Hate Speech--The Winning Solution of Hateful Memes Challenge." arXiv preprint arXiv:2012.01002 (2020).
Suryawanshi, Shardul, et al."A dataset fortroll classification of TamilMemes." Proceedings of the WILDRE5–5th workshop on indian language data: resources and evaluation. 2020.
Ling, Chen, et al. "Dissecting the meme magic: Understanding indicators of virality in image memes." Proceedings of the ACM on human-computer interaction 5.CSCW1 (2021):1-24. DOI: https://doi.org/10.1145/3449155
Kumar, Gokul Karthik, and Karthik Nandakumar. "Hate-CLIPper:
Multimodal hateful meme classification based on crossmodal interaction of CLIP features." arXiv preprint arXiv:2210.05916 (2022)
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2024 Dr. Gowsic K, Shanmuga Sudhan K, Yogeshwaran H, Vignesh M, Deena R
This work is licensed under a Creative Commons Attribution 4.0 International License.
With the licence CC-BY, authors retain the copyright, allowing anyone to download, reuse, re-print, modify, distribute, and/or copy their contribution. The work must be properly attributed to its author.
It is not necessary to ask for further permission from the author or journal board.
This journal provides immediate open access to its content on the principle that making research freely available to the public supports a greater global exchange of knowledge.
