The spread of fake news on social media has increased dramatically in recent years. Hence, fake news detection systems have received researchers' attention globally. During the COVID-19 outbreak in 2019 and the worldwide epidemic, the importance of this issue becomes more apparent. Due to the importance of the issue, a large number of researchers have begun to collect English datasets and to study COVID-19 fake news detection. However, there are a large number of low-resource languages, including Persian, that cannot develop accurate tools for automatic COVID-19 fake news detection due to the lack of annotated data for the task. In this article, we aim to develop a corpus for Persian in the domain of COVID-19 where the fake news is annotated and to provide a model for detecting Persian COVID-19 fake news. With the impressive advancement of multilingual pre-trained language models, the idea of cross-lingual transfer learning can be proposed to improve the generalization of models trained with low-resource language datasets. Accordingly, we use the state-of-the-art deep cross-lingual contextualized language model, XLM-RoBERTa, and the parallel convolutional neural networks to detect Persian COVID-19 fake news. Moreover, we use the idea of knowledge transferring across-domains to improve the results by using both the English COVID-19 dataset and the general domain Persian fake news dataset. The combination of both cross-lingual and cross-domain transfer learning has outperformed the models and it has beaten the baseline by 2.39% significantly.
{"title":"Deep transfer learning for COVID-19 fake news detection in Persian.","authors":"Masood Ghayoomi, Maryam Mousavian","doi":"10.1111/exsy.13008","DOIUrl":"10.1111/exsy.13008","url":null,"abstract":"<p><p>The spread of fake news on social media has increased dramatically in recent years. Hence, fake news detection systems have received researchers' attention globally. During the COVID-19 outbreak in 2019 and the worldwide epidemic, the importance of this issue becomes more apparent. Due to the importance of the issue, a large number of researchers have begun to collect English datasets and to study COVID-19 fake news detection. However, there are a large number of low-resource languages, including Persian, that cannot develop accurate tools for automatic COVID-19 fake news detection due to the lack of annotated data for the task. In this article, we aim to develop a corpus for Persian in the domain of COVID-19 where the fake news is annotated and to provide a model for detecting Persian COVID-19 fake news. With the impressive advancement of multilingual pre-trained language models, the idea of cross-lingual transfer learning can be proposed to improve the generalization of models trained with low-resource language datasets. Accordingly, we use the state-of-the-art deep cross-lingual contextualized language model, XLM-RoBERTa, and the parallel convolutional neural networks to detect Persian COVID-19 fake news. Moreover, we use the idea of knowledge transferring across-domains to improve the results by using both the English COVID-19 dataset and the general domain Persian fake news dataset. The combination of both cross-lingual and cross-domain transfer learning has outperformed the models and it has beaten the baseline by 2.39% significantly.</p>","PeriodicalId":58,"journal":{"name":"The Journal of Physical Chemistry ","volume":"98 28","pages":"e13008"},"PeriodicalIF":3.0,"publicationDate":"2022-04-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9111484/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"41250129","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-03-01DOI: 10.1038/d41591-022-00026-y
Sofia Moutinho
{"title":"Health in the Amazon.","authors":"Sofia Moutinho","doi":"10.1038/d41591-022-00026-y","DOIUrl":"https://doi.org/10.1038/d41591-022-00026-y","url":null,"abstract":"","PeriodicalId":58,"journal":{"name":"The Journal of Physical Chemistry ","volume":" ","pages":"424-426"},"PeriodicalIF":82.9,"publicationDate":"2022-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"39787365","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-02-21DOI: 10.1038/d41591-022-00035-x
Karen O'Leary
{"title":"Cancer treatment toxicity affects women more than men.","authors":"Karen O'Leary","doi":"10.1038/d41591-022-00035-x","DOIUrl":"10.1038/d41591-022-00035-x","url":null,"abstract":"","PeriodicalId":58,"journal":{"name":"The Journal of Physical Chemistry ","volume":" ","pages":""},"PeriodicalIF":82.9,"publicationDate":"2022-02-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"39942216","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-02-18eCollection Date: 2022-01-01DOI: 10.3389/fendo.2022.835460
Yupu Liu, Juan Li, Yuchao Wu, Han Zhang, Qingguo Lv, Yuwei Zhang, Xiaofeng Zheng, Nanwei Tong
Background: The American Diabetes Association (ADA) 2003 diagnostic criteria divide impaired glucose tolerance (IGT) into isolated impaired glucose tolerance with normal fasting glucose (I-IGT, IGT+NFG) and impaired glucose tolerance combined with impaired fasting glucose (IGT+IFG), while the World Health Organization (WHO) 1999 criteria do not. The aim of this meta-analysis was to evaluate whether IGT should be divided into I-IGT (IGT+NFG) or IGT+IFG according to their risk of progression to type 2 diabetes.
Methods: The MEDLINE and EMBASE were searched to identify prospective cohort studies published in English prior to April 18, 2020. Review Manager 5.3 was used to calculate the pooled risk ratios (RRs) and 95% confidence intervals (CIs) as summary statistics for each included study.
Results: Sixteen eligible studies (n = 147,006) were included in the analysis. The subsequent incidence of type 2 diabetes was lower in the I-IGT (IGT+NFG) group than in the IGT+IFG group (0.45 [95% CI 0.37, 0.55] according to WHO 1999 criteria and 0.59 [95% CI 0.54, 0.66] according to ADA 2003 criteria). It was higher in the I-IFG, I-IGT (IGT+NFG), and IGT+IFG groups than in the normoglycemic group (95% CI of 5.53 [3.78, 8.08], 5.21 [3.70, 7.34], and 11.87 [7.33, 19.20] according to the WHO 1999 criteria and 95% CI of 2.66 [2.00, 3.54], 3.34 [2.81, 3.97], and 6.10 [4.72, 7.88] according to the ADA 2003 criteria). In general, the incidence of diabetes in the IGT+IFG group was the highest in the prediabetic population.
Conclusions: The present meta-analysis suggested that the established WHO diagnostic criteria for IGT should be revised to separately identify individuals with IGT+NFG or IGT+IFG.
{"title":"Evidence From a Systematic Review and Meta-Analysis: Classical Impaired Glucose Tolerance Should Be Divided Into Subgroups of Isolated Impaired Glucose Tolerance and Impaired Glucose Tolerance Combined With Impaired Fasting Glucose, According to the Risk of Progression to Diabetes.","authors":"Yupu Liu, Juan Li, Yuchao Wu, Han Zhang, Qingguo Lv, Yuwei Zhang, Xiaofeng Zheng, Nanwei Tong","doi":"10.3389/fendo.2022.835460","DOIUrl":"10.3389/fendo.2022.835460","url":null,"abstract":"<p><strong>Background: </strong>The American Diabetes Association (ADA) 2003 diagnostic criteria divide impaired glucose tolerance (IGT) into isolated impaired glucose tolerance with normal fasting glucose (I-IGT, IGT+NFG) and impaired glucose tolerance combined with impaired fasting glucose (IGT+IFG), while the World Health Organization (WHO) 1999 criteria do not. The aim of this meta-analysis was to evaluate whether IGT should be divided into I-IGT (IGT+NFG) or IGT+IFG according to their risk of progression to type 2 diabetes.</p><p><strong>Methods: </strong>The MEDLINE and EMBASE were searched to identify prospective cohort studies published in English prior to April 18, 2020. Review Manager 5.3 was used to calculate the pooled risk ratios (RRs) and 95% confidence intervals (CIs) as summary statistics for each included study.</p><p><strong>Results: </strong>Sixteen eligible studies (<i>n</i> = 147,006) were included in the analysis. The subsequent incidence of type 2 diabetes was lower in the I-IGT (IGT+NFG) group than in the IGT+IFG group (0.45 [95% CI 0.37, 0.55] according to WHO 1999 criteria and 0.59 [95% CI 0.54, 0.66] according to ADA 2003 criteria). It was higher in the I-IFG, I-IGT (IGT+NFG), and IGT+IFG groups than in the normoglycemic group (95% CI of 5.53 [3.78, 8.08], 5.21 [3.70, 7.34], and 11.87 [7.33, 19.20] according to the WHO 1999 criteria and 95% CI of 2.66 [2.00, 3.54], 3.34 [2.81, 3.97], and 6.10 [4.72, 7.88] according to the ADA 2003 criteria). In general, the incidence of diabetes in the IGT+IFG group was the highest in the prediabetic population.</p><p><strong>Conclusions: </strong>The present meta-analysis suggested that the established WHO diagnostic criteria for IGT should be revised to separately identify individuals with IGT+NFG or IGT+IFG.</p>","PeriodicalId":58,"journal":{"name":"The Journal of Physical Chemistry ","volume":"69 10","pages":"835460"},"PeriodicalIF":3.9,"publicationDate":"2022-02-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8894674/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"41250096","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-02-08DOI: 10.1038/d41591-022-00033-z
Karen O'Leary
{"title":"The global burden of antimicrobial resistance.","authors":"Karen O'Leary","doi":"10.1038/d41591-022-00033-z","DOIUrl":"10.1038/d41591-022-00033-z","url":null,"abstract":"","PeriodicalId":58,"journal":{"name":"The Journal of Physical Chemistry ","volume":" ","pages":""},"PeriodicalIF":82.9,"publicationDate":"2022-02-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"39901554","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-01-31DOI: 10.1038/d41591-022-00030-2
Karen O'Leary
{"title":"A Cytosponge to support cancer screening.","authors":"Karen O'Leary","doi":"10.1038/d41591-022-00030-2","DOIUrl":"10.1038/d41591-022-00030-2","url":null,"abstract":"","PeriodicalId":58,"journal":{"name":"The Journal of Physical Chemistry ","volume":" ","pages":""},"PeriodicalIF":82.9,"publicationDate":"2022-01-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"39739171","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
扫码关注我们
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号