Pinpointing Fine-Grained Relationships between Hateful Tweets and Replies

Authors: Abdullah Albanyan, Eduardo Blanco10418-10426

AAAI 2022 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Experimental results show improvements (a) taking into account the hateful tweet in addition to the reply and (b) pretraining with related tasks.
Researcher Affiliation Academia Abdullah Albanyan1, Eduardo Blanco2 1 University of North Texas 2 Arizona State University
Pseudocode No The paper does not contain any structured pseudocode or algorithm blocks.
Open Source Code Yes Corpus and implementation available at https://github.com/albanyan/hateful-tweets-replies
Open Datasets Yes The main contribution of this paper are:4 (a) a corpus of 5,652 replies to hateful tweets published by real users and annotated with finegrained relationship information... Corpus and implementation available at https://github.com/albanyan/hateful-tweets-replies
Dataset Splits Yes we split the dataset as follows: 70% for training, 10% for validation, and 20% for testing.
Hardware Specification No The paper mentions using BERT-based transformers and deep learning libraries but does not specify any hardware details such as GPU or CPU models.
Software Dependencies No The paper mentions software like the Transformers library by Hugging Face, TensorFlow, and PyTorch, but does not provide specific version numbers for these dependencies.
Experiment Setup No The paper states, 'We report hyperparameters and other implementation details in the supplementary materials,' indicating these details are not provided within the main text of the paper.