In this research paper,we propose a corpus for the task of detecting religious extremism in social networks and open sources and compare various machine learning algorithms for the binary classification problem using ...In this research paper,we propose a corpus for the task of detecting religious extremism in social networks and open sources and compare various machine learning algorithms for the binary classification problem using a previously created corpus,thereby checking whether it is possible to detect extremist messages in the Kazakh language.To do this,the authors trained models using six classic machine-learning algorithms such as Support Vector Machine,Decision Tree,Random Forest,K Nearest Neighbors,Naive Bayes,and Logistic Regression.To increase the accuracy of detecting extremist texts,we used various characteristics such as Statistical Features,TF-IDF,POS,LIWC,and applied oversampling and undersampling techniques to handle imbalanced data.As a result,we achieved 98%accuracy in detecting religious extremism in Kazakh texts for the collected dataset.Testing the developed machine learningmodels in various databases that are often found in everyday life“Jokes”,“News”,“Toxic content”,“Spam”,“Advertising”has also shown high rates of extremism detection.展开更多
For today＇s human rights protection, it is requisite to firmly oppose religious ex- tremism, no matter whether in China or worldwide. Religious extremism is a rather serious phenomenon in the political life of today...For today＇s human rights protection, it is requisite to firmly oppose religious ex- tremism, no matter whether in China or worldwide. Religious extremism is a rather serious phenomenon in the political life of today＇s world. In the form of religion （including banners, words, symbols and costumes, etc）, it agitates for the extreme claims and fanatical behavior of certain groups and damages social stability, so that it can serve its villainous purposes.展开更多
Since the first years of independence,Uzbekistan began to develop and implement a policy of countering religious extremism and addressing the ideological basis of terrorism.Taking into consideration the complexity of ...Since the first years of independence,Uzbekistan began to develop and implement a policy of countering religious extremism and addressing the ideological basis of terrorism.Taking into consideration the complexity of this problem,Uzbekistan is comprehensively combating expressions of extremism and terrorism.展开更多
Manglietia ventii is a wild plant species with extremely small populations endemic to Yunnan,mainly distributed in southeast Yunnan.Due to the continuous deterioration of natural habitats,excessive felling and utiliza...Manglietia ventii is a wild plant species with extremely small populations endemic to Yunnan,mainly distributed in southeast Yunnan.Due to the continuous deterioration of natural habitats,excessive felling and utilization of human beings,and the decline of breeding ability,the number of individuals in the population has decreased significantly.Through field investigation and literature review,the research status of M.ventii in systematics,conservation ecology,reproductive biology,genetic diversity,endangered mechanism and resource protection at home and abroad are systematically reviewed.And the future research direction is prospected.It is necessary to strengthen the research on the basic characteristics of M.ventii,explore the transmission route of M.ventii and deepen the development and utilization of resources,in order to provide a theoretical support for the protection and sustainable utilization of germplasm resources of M.ventii,and provide a reference for the protection of other wild plant species with extremely small populations.展开更多
An extreme （weather and climate） event does not only mean that an extreme occurs at a location, but more generally it can impact a certainarea and last a certain period of time, which is defined as a regional extrem...An extreme （weather and climate） event does not only mean that an extreme occurs at a location, but more generally it can impact a certainarea and last a certain period of time, which is defined as a regional extreme event （REE） with a certain impacted area and duration. The conceptof REE has been defined to allow mainly objective assessment of the events without a pre-determined boundary and duration. This paper reviewsthe studies on REEs published during the past 20 years, especially recent years. Mainly in view of methodology, these studies can be divided intothree types studies focusing on spatial simultaneity, studies focusing on temporal persistence, and studies identifying REEs. The methodsidentifying REEs include two kinds, e.g., type-I methods stressing REE＇s temporal persistence within a relatively certain area and type-IImethods focusing on catching a complete REE. Identification methods proposed in this paper could provide valuable information for variouspurposes, such as real-time monitoring, estimating long-term changes, mechanism diagnosis, forecasting study and even attribution analysis.Research on REEs is important for objectively defining extreme weather and climate events, which depends on the spatial and temporal scales ofinterest. Such an objective definition will support ongoing climate monitoring and improve the assessment of how regional extreme events havechanged over time.展开更多
基金This work was supported by the grant“Development of models,algorithms for semantic analysis to identify extremist content in web resources and creation the tool for cyber forensics”funded by the Ministry of Digital Development,Innovations and Aerospace industry of the Republic of Kazakhstan.Grant No.IRN AP06851248.Supervisor of the project is Shynar Mussiraliyeva,email:mussiraliyevash@gmail.com.
文摘In this research paper,we propose a corpus for the task of detecting religious extremism in social networks and open sources and compare various machine learning algorithms for the binary classification problem using a previously created corpus,thereby checking whether it is possible to detect extremist messages in the Kazakh language.To do this,the authors trained models using six classic machine-learning algorithms such as Support Vector Machine,Decision Tree,Random Forest,K Nearest Neighbors,Naive Bayes,and Logistic Regression.To increase the accuracy of detecting extremist texts,we used various characteristics such as Statistical Features,TF-IDF,POS,LIWC,and applied oversampling and undersampling techniques to handle imbalanced data.As a result,we achieved 98%accuracy in detecting religious extremism in Kazakh texts for the collected dataset.Testing the developed machine learningmodels in various databases that are often found in everyday life“Jokes”,“News”,“Toxic content”,“Spam”,“Advertising”has also shown high rates of extremism detection.
文摘For today＇s human rights protection, it is requisite to firmly oppose religious ex- tremism, no matter whether in China or worldwide. Religious extremism is a rather serious phenomenon in the political life of today＇s world. In the form of religion （including banners, words, symbols and costumes, etc）, it agitates for the extreme claims and fanatical behavior of certain groups and damages social stability, so that it can serve its villainous purposes.
文摘Since the first years of independence,Uzbekistan began to develop and implement a policy of countering religious extremism and addressing the ideological basis of terrorism.Taking into consideration the complexity of this problem,Uzbekistan is comprehensively combating expressions of extremism and terrorism.
基金Supported by National Natural Science Foundation of China(31960069).
文摘Manglietia ventii is a wild plant species with extremely small populations endemic to Yunnan,mainly distributed in southeast Yunnan.Due to the continuous deterioration of natural habitats,excessive felling and utilization of human beings,and the decline of breeding ability,the number of individuals in the population has decreased significantly.Through field investigation and literature review,the research status of M.ventii in systematics,conservation ecology,reproductive biology,genetic diversity,endangered mechanism and resource protection at home and abroad are systematically reviewed.And the future research direction is prospected.It is necessary to strengthen the research on the basic characteristics of M.ventii,explore the transmission route of M.ventii and deepen the development and utilization of resources,in order to provide a theoretical support for the protection and sustainable utilization of germplasm resources of M.ventii,and provide a reference for the protection of other wild plant species with extremely small populations.
文摘An extreme （weather and climate） event does not only mean that an extreme occurs at a location, but more generally it can impact a certainarea and last a certain period of time, which is defined as a regional extreme event （REE） with a certain impacted area and duration. The conceptof REE has been defined to allow mainly objective assessment of the events without a pre-determined boundary and duration. This paper reviewsthe studies on REEs published during the past 20 years, especially recent years. Mainly in view of methodology, these studies can be divided intothree types studies focusing on spatial simultaneity, studies focusing on temporal persistence, and studies identifying REEs. The methodsidentifying REEs include two kinds, e.g., type-I methods stressing REE＇s temporal persistence within a relatively certain area and type-IImethods focusing on catching a complete REE. Identification methods proposed in this paper could provide valuable information for variouspurposes, such as real-time monitoring, estimating long-term changes, mechanism diagnosis, forecasting study and even attribution analysis.Research on REEs is important for objectively defining extreme weather and climate events, which depends on the spatial and temporal scales ofinterest. Such an objective definition will support ongoing climate monitoring and improve the assessment of how regional extreme events havechanged over time.
