Saved in:
Bibliographic Details
Main Authors: Majidi, Farideh, Beheshtifard, Ziaeddin
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2507.11634
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913943499309056
author Majidi, Farideh
Beheshtifard, Ziaeddin
author_facet Majidi, Farideh
Beheshtifard, Ziaeddin
contents This research examines cross-lingual sentiment analysis using few-shot learning and incremental learning methods in Persian. The main objective is to develop a model capable of performing sentiment analysis in Persian using limited data, while getting prior knowledge from high-resource languages. To achieve this, three pre-trained multilingual models (XLM-RoBERTa, mDeBERTa, and DistilBERT) were employed, which were fine-tuned using few-shot and incremental learning approaches on small samples of Persian data from diverse sources, including X, Instagram, Digikala, Snappfood, and Taaghche. This variety enabled the models to learn from a broad range of contexts. Experimental results show that the mDeBERTa and XLM-RoBERTa achieved high performances, reaching 96% accuracy on Persian sentiment analysis. These findings highlight the effectiveness of combining few-shot learning and incremental learning with multilingual pre-trained models.
format Preprint
id arxiv_https___arxiv_org_abs_2507_11634
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Cross-lingual Few-shot Learning for Persian Sentiment Analysis with Incremental Adaptation
Majidi, Farideh
Beheshtifard, Ziaeddin
Computation and Language
Artificial Intelligence
This research examines cross-lingual sentiment analysis using few-shot learning and incremental learning methods in Persian. The main objective is to develop a model capable of performing sentiment analysis in Persian using limited data, while getting prior knowledge from high-resource languages. To achieve this, three pre-trained multilingual models (XLM-RoBERTa, mDeBERTa, and DistilBERT) were employed, which were fine-tuned using few-shot and incremental learning approaches on small samples of Persian data from diverse sources, including X, Instagram, Digikala, Snappfood, and Taaghche. This variety enabled the models to learn from a broad range of contexts. Experimental results show that the mDeBERTa and XLM-RoBERTa achieved high performances, reaching 96% accuracy on Persian sentiment analysis. These findings highlight the effectiveness of combining few-shot learning and incremental learning with multilingual pre-trained models.
title Cross-lingual Few-shot Learning for Persian Sentiment Analysis with Incremental Adaptation
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2507.11634