{"title":"利用机器学习和深度学习技术进行虚假新闻检测","authors":"Sonal Garg, D. Sharma","doi":"10.1109/SMART50582.2020.9337120","DOIUrl":null,"url":null,"abstract":"The proliferation of misleading news stories on social-media raised a big challenge due to its potential to create an adverse impact on human-being. Existing lexico-syntactic features are unable to detect counterfeit news. Most of the state of art algorithms used small datasets containing a limited number of the training dataset. In this paper, we evaluate our framework on the LIAR dataset by applying machine learning and advanced deep learning techniques. LIAR is a predominant dataset consist of 12,836 short news collected from different sources, including social media. The proposed framework uses POS (part of speech) tagging information and Glove Embedding. The result shows the superiority in terms of accuracy in comparison to the existing state of the art algorithm.","PeriodicalId":129946,"journal":{"name":"2020 9th International Conference System Modeling and Advancement in Research Trends (SMART)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2020-12-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"9","resultStr":"{\"title\":\"Phony News Detection using Machine Learning and Deep-Learning Techniques\",\"authors\":\"Sonal Garg, D. Sharma\",\"doi\":\"10.1109/SMART50582.2020.9337120\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"The proliferation of misleading news stories on social-media raised a big challenge due to its potential to create an adverse impact on human-being. Existing lexico-syntactic features are unable to detect counterfeit news. Most of the state of art algorithms used small datasets containing a limited number of the training dataset. In this paper, we evaluate our framework on the LIAR dataset by applying machine learning and advanced deep learning techniques. LIAR is a predominant dataset consist of 12,836 short news collected from different sources, including social media. The proposed framework uses POS (part of speech) tagging information and Glove Embedding. The result shows the superiority in terms of accuracy in comparison to the existing state of the art algorithm.\",\"PeriodicalId\":129946,\"journal\":{\"name\":\"2020 9th International Conference System Modeling and Advancement in Research Trends (SMART)\",\"volume\":\"22 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2020-12-04\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"9\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2020 9th International Conference System Modeling and Advancement in Research Trends (SMART)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/SMART50582.2020.9337120\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2020 9th International Conference System Modeling and Advancement in Research Trends (SMART)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/SMART50582.2020.9337120","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Phony News Detection using Machine Learning and Deep-Learning Techniques
The proliferation of misleading news stories on social-media raised a big challenge due to its potential to create an adverse impact on human-being. Existing lexico-syntactic features are unable to detect counterfeit news. Most of the state of art algorithms used small datasets containing a limited number of the training dataset. In this paper, we evaluate our framework on the LIAR dataset by applying machine learning and advanced deep learning techniques. LIAR is a predominant dataset consist of 12,836 short news collected from different sources, including social media. The proposed framework uses POS (part of speech) tagging information and Glove Embedding. The result shows the superiority in terms of accuracy in comparison to the existing state of the art algorithm.