What question did this study set out to answer?

The aim is to improve sentiment analysis of Algerian Arabic using federated learning methods on social media data.

April 23, 2026Open Access

Federated Fine-Tuning of DziriBERT for Algerian Dialect Sentiment Analysis

Key Points

The aim is to improve sentiment analysis of Algerian Arabic using federated learning methods on social media data.
Collected a corpus of 13,260 comments via X platform API, labeled for sentiment.
Fine-tuned DziriBERT and tested it against other models using federated learning techniques.
Evaluated performance metrics including accuracy and macro-F1 score across different clients.
DziriBERT obtained an accuracy of 86.35% and macro-F1 score of 86.35% as a baseline.
FedProx improved accuracy to 85.41%, while FedAvg with DziriBERT achieved 84.77%.
Semi-supervised federated learning reached 80.69% accuracy with only 20% labeled data.

Abstract

This study examines federated learning for sentiment analysis in Algerian Arabic and code-switched social media content using transformer-based language models. A corpus of 13,260 user-generated comments collected via the X platform API with balanced positive and negative labels is preprocessed, stratified into train, validation, and test splits, and divided into ten highly non-IID clients using a Dirichlet procedure. We first fine-tune DziriBERT centrally as a solid baseline, obtaining roughly 86.35% accuracy and 86.35 macro-F1 on the held-out test set. We then implement FedAvg, FedProx, and a semisupervised FL variant with only 20% labeled clients using DziriBERT, and evaluate multilingual DistilBERT with FedAvg as an alternative backbone. FedAvg achieves 84.77% accuracy with DziriBERT, FedProx improves to 85.41%, semi-supervised FL achieves 80.69% with limited labels, and DistilBERT FedAvg reaches 81.37% accuracy. All results are based on a single random seed and partition.

Read Full Paperexternally

AI에게 질문

Bookmark

View Full Paper