检索结果-南通市图书馆

Applying Machine Learning Techniques for Religious Extremism Detection on Online User Contents

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2022年第1期70卷 915-934页

作者： shynar Mussiraliyeva Batyrkhan Omarov Paul Yoo Milana Bolatbek Al-Farabi Kazakh National University AlmatyKazakhstan CSIS Birkbeck CollegeUniversity of LondonLondonUK

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 *** 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 *** 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 *** a result,we achieved 98%accuracy in detecting religious extremism in Kazakh texts for the collected *** 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.

关键词： Extremism religious extremism machine learning social media social network natural language processing NLP

Cyberbullying-related Hate Speech Detection Using Shallow-to-deep Learning

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2023年第1期74卷 2115-2131页

作者： Daniyar Sultan Aigerim Toktarova Ainur Zhumadillayeva Sapargali Aldeshov shynar Mussiraliyeva Gulbakhram Beissenova Abay Tursynbayev Gulmira Baenova Aigul Imanbayeva Al-Farabi Kazakh National University AlmatyKazakhstan International Information Technology University AlmatyKazakhstan Akhmet Yassawi International Kazakh-Turkish University TurkistanKazakhstan L.N.Gumilyov Eurasian National University AstanaKazakhstan South Kazakhstan State Pedagogical University ShymkentKazakhstan M.Auezov South Kazakhstan University ShymkentKazakhstan University of Friendship of People’s Academician A.Kuatbekov ShymkentKazakhstan National Academy of Education named after Y.Altynsarin AstanaKazakhstan

Communication in society had developed within cultural and geographical boundaries prior to the invention of digital *** latest advancements in communication technology have significantly surpassed the conventional constraints for communication with regards to time and *** new platforms have ushered in a new age of user-generated content,online chats,social network and comprehensive data on individual ***,the abuse of communication software such as social media websites,online communities,and chats has resulted in a new kind of online hostility and aggressive *** to widespread use of the social networking platforms and technological gadgets,conventional bullying has migrated from physical form to online,where it is termed as ***,recently the digital technologies as machine learning and deep learning have been showing their efficiency in identifying linguistic patterns used by cyberbullies and cyberbullying detection *** this research paper,we aimed to evaluate shallow machine learning and deep learning methods in cyberbullying detection *** deployed three deep and six shallow learning algorithms for cyberbullying detection *** results show that bidirectional long-short-term memory is the most efficient method for cyberbullying detection,in terms of accuracy and recall.

关键词： Cyberbullying machine learning deep learning classification NLP

The Creation Mechanisms of the Halide Defects in Alkali Halide Crystals in the Field of Dipole Complex

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

材料科学与工程（中英文A版） 2012年第9期2卷 636-641页

作者： Kuanyshbek Shunkeyev Daulet Sergeyev Zuchra Aimaganbetova Aleksandra Barmina Karlygash Bizhanova shynar Sagimbaeva Department of Experimental and Theoretical Physics Aktobe State Pedagogical Institute Aktobe 030012 Kazakhstan

Using the absorption spectroscopy methods the work researches the efficiency of the X3 --centers by X-ray radiation in alkali halide crystals in the field of cation-homologs, plastic and elastic stress. For the first time the absorption band in absorption spectrum is registered; it is typical for interstitial halogen ion (Cli -), which forms a part of (Cl3 -)acaLii +Cli -, (Cl3 -)acaNai +Cli - and (Cl3 -)0 acaSrc +Cli --centers in KCl-Li, KCl-Na and KCl-Sr crystals. The creation mechanisms are determined for KCl-Li and KCl-Sr crystals in the field of cation vacancy (Liic +υc -, υc -Src +) of V4A = (Cl3 -)acaLii +Cli - and V2A = (Cl3 -)0 acaSrc +Cli --centers, in plastic stressed KCl crystals in the divacancy field (υc -υa +) of V2 = (Cl3 -)aca-centers, and in the field of quartets [2(υc -υa +)] vacancy of V3 = [(Cl2)2]aca.

关键词：碱金属卤化物晶体机制偶极子阳离子空位弗吉尼亚州缺陷吸收光谱

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

改性固化淤泥的水力特性及水分迁移特征

山西建筑 2015年第29期41卷 49-51页

作者：况彦西娜张俊峰谌柳明戴小松徐顺平武汉理工大学土木工程与建筑学院湖北武汉430070 武汉大学土木建筑工程学院湖北武汉430072 中建三局投资发展有限公司湖北武汉430070

东湖固化淤泥土不能直接用于路基填筑,因此使用水泥对其进行改性,形成了改性固化淤泥,通过对改性固化淤泥的水力特性试验,获得了其土水特征曲线和水力传导函数曲线,在此基础上,使用Richards方程作为控制方程的瞬态流理论进行了东湖改性... 详细信息

东湖固化淤泥土不能直接用于路基填筑,因此使用水泥对其进行改性,形成了改性固化淤泥,通过对改性固化淤泥的水力特性试验,获得了其土水特征曲线和水力传导函数曲线,在此基础上,使用Richards方程作为控制方程的瞬态流理论进行了东湖改性固化淤泥路基在不同外部环境作用下水分迁移的数值模拟分析,得出了一些有意义的结论。

关键词：淤泥改性路基水力特征水分迁移