Memotion 2.0 - Sentiment Analysis and Emotion classification of Memes

Bhapkar, Nilam Pandurang (2022) Memotion 2.0 - Sentiment Analysis and Emotion classification of Memes. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (1MB) | Preview
Preview	PDF (Configuration manual) Download (985kB) | Preview

Abstract

Modern scientific advances in the Internet and media adoption have contributed to the emergence of more adequate methods for communicating. These platforms, which comprise visual, textual, and voice mediums, have given rise to a distinct social phenomenon known as Internet memes. Internet memes are photographs with humorous, eye-catching, or satirical text captions attached. Nowadays, memes are a very widespread way of expression on social networks. Their multi-modal feature, as a result of a combination of text and pictures, makes them a difficult research item for machine analysis. By categorizing memes based on their emotional content, we can better understand what they are about and avoid the proliferation of sarcasm or negative attitudes. It is the primary goal of this scientific report to shed light on the segmentation of memes into three distinct categories by utilizing the Memotion analysis dataset available through Google Colab. The F1 score,Weighted Avg score, Precision, Recall, and computational duration for execution are all used to evaluate the approach’s overall performance and effectiveness. The Deep neural network achieves the highest F1 score possible, which is 64%.

Item Type:	Thesis (Masters)
Subjects:	Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science P Language and Literature > P Philology. Linguistics > Computational linguistics. Natural language processing B Philosophy. Psychology. Religion > Psychology > Emotions
Divisions:	School of Computing > Master of Science in Data Analytics
Depositing User:	Tamara Malone
Date Deposited:	18 Jan 2023 17:40
Last Modified:	06 Mar 2023 16:30
URI:	https://norma.ncirl.ie/id/eprint/6088

Actions (login required)

View Item