MemeMind at ArAIEval Shared Task: Spotting Persuasive Spans in Arabic Text with Persuasion Techniques Identification

TL;DR

This paper presents a method using AraBERT for detecting propaganda spans and persuasion techniques in Arabic texts, achieving competitive F1 scores in a shared task.

Contribution

It introduces a two-phase fine-tuning approach for propaganda detection in Arabic, leveraging pre-trained language models and BIO tagging.

Findings

Achieved an F1 score of 0.2774 on the task

Secured 3rd place in the leaderboard

Demonstrated effectiveness of phased fine-tuning

Abstract

This paper focuses on detecting propagandistic spans and persuasion techniques in Arabic text from tweets and news paragraphs. Each entry in the dataset contains a text sample and corresponding labels that indicate the start and end positions of propaganda techniques within the text. Tokens falling within a labeled span were assigned "B" (Begin) or "I" (Inside), "O", corresponding to the specific propaganda technique. Using attention masks, we created uniform lengths for each span and assigned BIO tags to each token based on the provided labels. Then, we used AraBERT-base pre-trained model for Arabic text tokenization and embeddings with a token classification layer to identify propaganda techniques. Our training process involves a two-phase fine-tuning approach. First, we train only the classification layer for a few epochs, followed by full model fine-tuning, updating all parameters. This methodology allows the model to adapt to the specific characteristics of the propaganda detection task while leveraging the knowledge captured by the pre-trained AraBERT model. Our approach achieved an F1 score of 0.2774, securing the 3rd position in the leaderboard of Task 1.