BERT-Based Arabic Social Media Author Profiling

2019/09/09 by Chiyu Zhang, Muhammad Abdul-Mageed, Zhang, Chiyu +1
Computer Science · #Authorship Attribution and Profiling #Computation and Language (cs.CL) #FOS: Computer and information sciences #Hate Speech and Cyberbullying Detection #Spam and Phishing Detection

paper · pdf · doi:10.48550/arxiv.1909.04181

openalex publication_date 2019/09/09 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

We report our models for detecting age, language variety, and gender from social media data in the context of the Arabic author profiling and deception detection shared task (APDA). We build simple models based on pre-trained bidirectional encoders from transformers (BERT). We first fine-tune the pre-trained BERT model on each of the three datasets with shared task released data. Then we augment shared task data with in-house data for gender and dialect, showing the utility of augmenting training data. Our best models on the shared task test data are acquired with a majority voting of various BERT models trained under different data conditions. We acquire 54.72% accuracy for age, 93.75% for dialect, 81.67% for gender, and 40.97% joint accuracy across the three tasks.

Citations

• Echo Chamber or Public Sphere? Predicting Political Orientation and Measuring Political Homophily in Twitter Using Big Data

Related

• Sentence-Level BERT and Multi-Task Learning of Age and Gender in Social Media
• Pre-Training BERT on Arabic Tweets: Practical Considerations
• KUISAIL at SemEval-2020 Task 12: BERT-CNN for Offensive Speech Identification in Social Media
• AraNet: A Deep Learning Toolkit for Arabic Social Media
• Transfer Learning Approach for Arabic Offensive Language Detection System -- BERT-Based Model