[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-85884-en":3,"doc-seo-85884-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":21,"is_downloadable":21,"audit_status":21,"page_count":22,"language":23,"language_code":24,"site_id":25,"html_lang":24,"table_of_contents":26,"faqs":27,"seo_title":13,"seo_description":14,"update_tm":28,"read_time":29},85884,687197207639,"Asher","https://ap-avatar.wpscdn.com/davatar_a8503ba1806abce46bf441b54a3ca4cd",8,"Research & Report","Polarization Detection: A Hybrid Approach with AfroXLMR-Social and DeBERTa for Low- and High-Resource Settings","Online polarization is reshaping digital discourse through hostility and reduced empathy, threatening social cohesion and requiring reliable automated detection across diverse languages. This work describes a system for the POLAR Shared Task 2026, targeting polarization detection and fine-grained characterization in English and Hausa. A hybrid strategy selects DeBERTa for English binary detection and AfroXLMR-Social for Hausa plus all type and manifestation subtasks. Domain-adaptive pretraining, LoRA fine-tuning, and nlpaug-based augmentation address low-resource constraints and class imbalance, achieving competitive results.","Polarization Detection: A Hybrid Approach with AfroXLMR-Social and DeBERTa for Low-and High-Resource Settings  \nMuhammad Abdullahi Said  \nAfrican Institute for Mathematical Sciences (AIMS)  \n[mohdasaid@aims.ac.za](mohdasaid@aims.ac.za)  \narXiv :2607 . 103 12v 1 [ cs .CL] 11 Jul 2026  \nAbstract  \nThe rapid proliferation of online polarization threatens social cohesion, necessitating robust automated detection systems that operate effectively across diverse linguistic contexts. This paper presents our system description for the POLAR Shared Task 2026, focusing on the detection and characterization of polarized discourse in English and Hausa. We propose a hybrid modeling strategy: for English binary detection, we leverage the monolingual strength of DeBERTa, while for Hausa and all fine-grained subtasks (Types and Manifestations), we utilize AfroXLMRSocial. This domain-adapted multilingual model proved critical for capturing the nuances of polarization in social media text. To further address computational constraints and data scarcity, we implement Low-Rank Adaptation (LoRA) and textual data augmentation via nlpaug. We report competitive results across all three subtasks, demonstrating that model selection tailored to specific subtask requirements yields the best balance of performance. [https://github.com/mohdasaid/](https://github.com/mohdasaid/)  \n[NLP-LLM/blob/main/Polarization.ipynb](NLP-LLM/blob/main/Polarization.ipynb)  \n1 Introduction  \nOnline polarization defined as the sharp division  \nof public opinion into opposing factions characterized by hostility and lack of empathy has become a pervasive issue in digital discourse. The POLAR Shared Task 2026 aims to benchmark Natural Language Processing (NLP) systems on their ability to detect this phenomenon across a wide range of languages and cultures (Naseem et al., 2025) .  \nDetecting polarization extends beyond traditional sentiment analysis. It requires capturing subtle rhetorical strategies such as \"us vs. them\" framing, invalidation, and dehumanization. This complexity is exacerbated in low-resource languages like Hausa, where labeled data is scarce and stan-  \ndard multilingual models often lack sufficient exposure to dialectal variations.  \nIn this work, we propose a strategic, hybrid training pipeline. Our key contributions are:  \n1. Task-Specific Model Selection: We observe that while English benefits from specialized monolingual models for binary detection (Subtask 1), the fine-grained tasks (Subtasks 2 & 3) in both languages require the robust socialmedia understanding provided by AfroXLMRSocial(Belay et al., 2025) .  \n2. Domain-Adaptive Efficacy: We demonstrate that AfroXLMR-Social, a model continuedpre-trained on African social media content, is indispensable for the Hausa subtasks, significantly outperforming generic multilingual baselines.  \n3. Parameter Efficiency & Augmentation: We employ LoRA (Low-Rank Adaptation) (Hu et al., 2021) to fine-tune effectively on consumer hardware and use nlpaug (Ma, 2019) to generate synthetic examples, addressing severe class imbalance in the manifestation labels.  \n2 Related Work  \n2.1 Polarization Detection  \nEarly computational approaches to polarization relied on network topology, inferring ideological stance from retweet or follower graphs. However, content-based approaches using Transformers have recently gained traction. Studies have shown that models like BERT and RoBERTa can detect stance and toxicity, which are proxies for polarization. The POLAR benchmark advances this by explicitly taxonomizing polarization into types (political, religious) and rhetorical manifestations.  \n2.2 Multilingual Models for African NLP  \nMassively multilingual models like mBERT and XLM-R often underperform on African languages due to the \"curse of multilinguality,\" where capacity is diluted across too many languages. AfroXLMR-Social (Belay et al., 2025) builds upon the success of the original AfroXLMR (Alabi et al., 2022) by incorporatin","cbCaiepLPCTJgFmv","https://ap.wps.com/l/cbCaiepLPCTJgFmv","pdf",155196,5,1,4,"English","en",105,"# Introduction\n# Related Work\n## Polarization Detection\n## Multilingual Models for African NLP\n## Efficient Fine-Tuning\n# Task Description\n# Methodology\n## Model Architecture Strategy\n### English Subtask 1: DeBERTa\n### Hausa & Subtasks 2/3: AfroXLMR-Social","[{\"question\":\"What problem does the paper address and why is it challenging?\",\"answer\":\"The paper targets online polarization, defined as sharp divisions of public opinion marked by hostility and lack of empathy. The challenge is detecting subtle rhetorical strategies and doing so especially in low-resource languages like Hausa with scarce labeled data.\"},{\"question\":\"How does the proposed hybrid approach differ between English and Hausa tasks?\",\"answer\":\"For English Subtask 1 (binary detection), the system uses DeBERTa-v3-base. For Hausa and the fine-grained subtasks (Types and Manifestations), the system uses AfroXLMR-Social to better capture social media language nuances.\"},{\"question\":\"Which techniques are used to handle computational and data constraints?\",\"answer\":\"The paper fine-tunes models using Low-Rank Adaptation (LoRA) to improve parameter efficiency and reduce cost. It also applies textual data augmentation with nlpaug to generate synthetic examples and mitigate severe class imbalance.\"}]",1784206937,10,{"code":4,"msg":31,"data":32},"ok",{"site_id":25,"language":24,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"polarization-detection-a-hybrid-approach-with-afroxlmr-social-and-deberta-for-low-and-high-resource-settings","",{"@graph":36,"@context":85},[37,53,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":22},"https://docshare.wps.com/document/polarization-detection-a-hybrid-approach-with-afroxlmr-social-and-deberta-for-low-and-high-resource-settings/85884/",{"url":52,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":24,"description":14,"dateModified":61,"datePublished":62,"encodingFormat":60,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":41,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-26","2026-07-16",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What problem does the paper address and why is it challenging?","Question",{"text":75,"@type":76},"The paper targets online polarization, defined as sharp divisions of public opinion marked by hostility and lack of empathy. The challenge is detecting subtle rhetorical strategies and doing so especially in low-resource languages like Hausa with scarce labeled data.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does the proposed hybrid approach differ between English and Hausa tasks?",{"text":80,"@type":76},"For English Subtask 1 (binary detection), the system uses DeBERTa-v3-base. For Hausa and the fine-grained subtasks (Types and Manifestations), the system uses AfroXLMR-Social to better capture social media language nuances.",{"name":82,"@type":73,"acceptedAnswer":83},"Which techniques are used to handle computational and data constraints?",{"text":84,"@type":76},"The paper fine-tunes models using Low-Rank Adaptation (LoRA) to improve parameter efficiency and reduce cost. It also applies textual data augmentation with nlpaug to generate synthetic examples and mitigate severe class imbalance.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":92},[93,97,101,105,109,114,119,122,127,130,133],{"id":21,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":22,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":20,"doc_module":4,"doc_module_name":46,"category_name":106,"show_sort_weight":107,"slug":108},"Comic",60,"comic",{"id":110,"doc_module":4,"doc_module_name":46,"category_name":111,"show_sort_weight":112,"slug":113},6,"Technology",50,"technology",{"id":115,"doc_module":4,"doc_module_name":46,"category_name":116,"show_sort_weight":117,"slug":118},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":120,"slug":121},30,"research-report",{"id":123,"doc_module":4,"doc_module_name":46,"category_name":124,"show_sort_weight":125,"slug":126},9,"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":29,"doc_module":4,"doc_module_name":46,"category_name":131,"show_sort_weight":29,"slug":132},"Lifestyle","lifestyle",{"id":134,"doc_module":4,"doc_module_name":46,"category_name":135,"show_sort_weight":20,"slug":136},19,"General","general"]