Date of Award
Winter 3-1-2025
Document Type
Thesis (Master's)
Department or Program
Computer Science
First Advisor
Soroush Vosoughi
Second Advisor
Lorie Loeb
Third Advisor
Elizabeth L. Murnane
Abstract
Memes are powerful in reflecting cultural trends and humor that resonate with specific audiences. Can artificial intelligence be used to generate memes that people enjoy? Will people appreciate AI’s creative ability when it comes to abstract forms of com- munication like memes? This thesis presents Memenify, a novel system for generating contextually appropriate memes by leveraging Artificial Intelligence. By combining the interpretative strengths of random forests with the text processing capabilities of GPT-4, Memenify produces meme dialogues and monologues tailored to a given context. Through the analysis of meme patterns with the Random Forests classifier, Memenify suggests and predicts appropriate meme templates, guiding the LLM to generate relevant and humorous content to construct a complete meme. To not only validate and test our system, but also evaluate people’s experience with AI powered meme generators, we implemented a website featuring an ’iMessage’-style chat inter- face, powered by a server running our algorithms. Our user study results indicate that Memenify effectively captures users’ context and produces relevant memes that users find relatable. This study demonstrates the potential of AI in meme generation while highlighting key challenges that current AI systems cannot solve, such as generating humor.
Recommended Citation
Wei, Xiaoyu, "Memenify: Leveraging Machine Learning and Large Language Models for Contextual Meme Creation" (2025). Dartmouth College Master’s Theses. 203.
https://digitalcommons.dartmouth.edu/masters_theses/203
