Combating propaganda texts using transfer learning

Abdullah M.; Abujaber D.; Al-Qarqaz A.Abbott R.Hadzikadic M.

首页> 外文期刊>IAES International Journal of Artificial Intelligence >Combating propaganda texts using transfer learning

【24h】

Combating propaganda texts using transfer learning

机译：

获取原文

获取原文并翻译 | 示例

获取外文期刊封面封底 >>

开具论文收录证明 >>

文献代查 >>

页面导航

摘要
著录项
相似文献
相关主题

摘要

Recently, it has been observed that people are shifting away from traditional news media sources towards trusting social networks to gather news information. Social networks have become the primary news source, although the validity and reliability of the information provided are uncertain. Memes are crucial content types that are very popular among young people and play a vital role in social media. It spreads quickly and continues to spread rapidly among people in a peer-to-peer manner rather than a prescriptive. Unfortunately, promoters and propagandists have adopted memes to indirectly manipulate public opinion and influence their attitudes using psychological and rhetorical techniques. This type of content could lead to unpleasant consequences in communities. This paper introduces an ensemble model system that resolves one of the most recent natural language processing research topics; propaganda techniques detection in texts extracted from memes. The paper also explores state-of-the-art pre-trained language models. The proposed model also uses different optimization tech-niques, such as data augmentation and model ensemble. It has been evaluated using a reference dataset from SemEval-2021 task 6. Our system outperforms the baseline and state-of-the-art results by achieving an F1-micro score of 0.604 on the test set. © 2023, Institute of Advanced Engineering and Science. All rights reserved.

著录项

来源
《IAES International Journal of Artificial Intelligence》 |2023年第2期|956-965|共10页
作者
Abdullah M.; Abujaber D.; Al-Qarqaz A.Abbott R.Hadzikadic M.;
展开▼
作者单位

Department of Computer Science, Jordan University of Science and Technology;

Department of Computer Science, University of North Carolina;

展开▼
收录信息
原文格式 PDF
正文语种英语
中图分类
关键词
BERT pretraining approach; Bidirectioal encoder representations from transformers; Machine learning; Propaganda; Robustly optimized; Transformers;

相似文献

外文文献
中文文献
专利

1. Text style transfer between classical and modern chinese through prompt-based reinforcement learning [J] . Minzhang Xu, Min Peng, Fang Liu World wide web . 2023,第2期

机译：Text style transfer between classical and modern chinese through prompt-based reinforcement learning
2. Data from National Polytechnic Institute Provide New Insights into Networks (Multi-label Emotion Classification In Texts Using Transfer Learning) [J] . Network Daily News . 2023,第8期

机译：Data from National Polytechnic Institute Provide New Insights into Networks (Multi-label Emotion Classification In Texts Using Transfer Learning)
3. BERT-based Transfer Learning in Sentence-level Anatomic Classification of Free-Text Radiology Reports [J] . Nishigaki D, Suzuki Y, Wataya TKita KYamagata KSato JKido STomiyama N Radiology. Artificial intelligence. . 2023,第2期

机译：BERT-based Transfer Learning in Sentence-level Anatomic Classification of Free-Text Radiology Reports
4. Traffic Signs Recognition in a mobile-based application using TensorFlow and Transfer Learning technics [C] . Abdallah Benhamida, Annamária R. Várkonyi-Kóczy, Miklos Kozlovszky IEEE International Conference of System of Systems Engineering . 2020

机译：使用TensorFlow和Transfer Learning技术在基于移动的应用程序中进行交通标志识别
5. Build Operate Transfer (BOT) project delivery system in Saudi Arabia. [D] . Shah, Mohammed Jalaluddin. 2001

机译：在沙特阿拉伯建立Operate Transfer（BOT）项目交付系统。
6. Rationale and design of the DP-TRANSFERS project: diabetes prevention-transferring findings from European research to society in Catalonia [O] . Bernardo Costa, Conxa Castell, Xavier Cos, 2016

机译：DP-TRANSFERS项目的原理和设计：从欧洲研究到加泰罗尼亚的社会预防糖尿病的成果
7. New learning strategies for automatic text categorization. [O] . 2001

机译：New learning strategies for automatic text categorization.
8. Installation Restoration Program (IRP). Site Investigation Report for IRP SitesNumber 1 and Number 2. Volume 2: Appendices A-F. 162nd Combat Communications Group and 149th Combat Communications Squadron, California Air National Guard, North Highlands Air [R] . 1995

机译：安装恢复计划（IRp）。 IRp sitesNumber 1和Number 2的现场调查报告。第2卷：附录a-F。 162nd Combat Communications Group和149th Combat Communications squadron，California air National Guard，North Highlands air

Combating propaganda texts using transfer learning

摘要

著录项

相似文献

相关主题

期刊订阅