Crowdsourced Explanations for Humorous Internet Memes

Authors: Chi-Chin Lin, Jane Yung-jen Hsu

AAAI 2014 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Since 9GAG is one of the most popular websites for funny images, we chose it as our meme source and crawl 39447 posts from it. From the posts, we automatically recognize 3051 memes in 38 unique meme templates. Among them, 5 memes are randomly selected and used in our pilot study. After we went through the task process and received 30 responses of the tasks, we generated explanations for each of the 5 memes.
Researcher Affiliation Academia Chi-Chin Lin Graduate Institute of Networking and Multimedia National Taiwan University No. 1, Sec. 4, Roosevelt Road, Taipei, 10617 Taiwan(R.O.C) +886-923-869-910 r01944018@csie.ntu.edu.tw Jane Yung-jen Hsu Department of Computer Science and Information Engineering National Taiwan University
Pseudocode No The paper describes a '4-move template' and 'Humor Tasks Design' in structured steps, but it does not include a formally labeled 'Pseudocode' or 'Algorithm' block.
Open Source Code No The paper states 'Complete datasets and results are in http://www.csie.ntu.edu. tw/ r01944018/meme-explanations/', but this link is for datasets and results, not explicitly for the source code of their methodology.
Open Datasets Yes Complete datasets and results are in http://www.csie.ntu.edu. tw/ r01944018/meme-explanations/
Dataset Splits No The paper mentions that '5 memes are randomly selected and used in our pilot study' and 'received 30 responses of the tasks', but it does not specify any explicit training, validation, or test dataset splits, percentages, or sample counts.
Hardware Specification No The paper does not provide any specific hardware details such as GPU/CPU models, processor types, or memory used for running its experiments.
Software Dependencies No The paper does not provide specific ancillary software details with version numbers (e.g., library or solver names with version numbers) needed to replicate the experiment.
Experiment Setup No The paper describes the 'Humor Tasks Design' but does not provide specific experimental setup details such as concrete hyperparameter values, training configurations, or system-level settings.