{"title":"使用基于AI的社交媒体监控追踪反Vax社交运动","authors":"Fahim K. Sufi;Imran Razzak;Ibrahim Khalil","doi":"10.1109/TTS.2022.3192757","DOIUrl":null,"url":null,"abstract":"Anti-Vax social movement possesses a dire threat to governments’ aim of mass vaccination. Moreover, by propagating serious misconceptions and misinformation about COVID-19, Anti-Vaxxers directly and indirectly cause harm to the overall health and wellbeing of the society. In addition, the ongoing clashes between Anti-Vaxxers and Pro-Vaxxers have created great social conflicts in recent times. This article proposes an artificial intelligence (AI)-based solution to identify and monitor social groups, such as Anti-Vax and Pro-Vax, in ethical manner. The proposed solution uses AI-based sentiment analysis and named entity recognition (NER) to advice political scientist, social scientists, and policy makers to assess the influence and impact of social groups. The proposed solution was deployed via iOS, Android, and Windows App on a range of platforms integrating publicly available 40 857 Twitter data related to COVID-19 in 55 different languages from 15 June 2021 till 31 December 2021. Our system demonstrated that Anti-Vax and Pro-Vax social movements posted 72% and 65% more negative contents compared to average negative sentiments of global COVID-19 related posts during the monitored period. Moreover, Anti-Vax-related posts with “Hoax” keyword were found to have the highest level of social impact with 38 849 retweets and highest level of negativity (i.e., sentiment score of 0.87). We found out that Pro-Vax community engages in social conflict with Anti-Vaxxers referring them as ignorant (i.e., average sentiment score 0.91), stupid (i.e., average sentiment score 0.89), and confused (i.e., average sentiment score 0.88). Most importantly, the social conflict detection system reveals possible locations of conflict.","PeriodicalId":73324,"journal":{"name":"IEEE transactions on technology and society","volume":"3 4","pages":"290-299"},"PeriodicalIF":0.0000,"publicationDate":"2022-07-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"13","resultStr":"{\"title\":\"Tracking Anti-Vax Social Movement Using AI-Based Social Media Monitoring\",\"authors\":\"Fahim K. Sufi;Imran Razzak;Ibrahim Khalil\",\"doi\":\"10.1109/TTS.2022.3192757\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Anti-Vax social movement possesses a dire threat to governments’ aim of mass vaccination. Moreover, by propagating serious misconceptions and misinformation about COVID-19, Anti-Vaxxers directly and indirectly cause harm to the overall health and wellbeing of the society. In addition, the ongoing clashes between Anti-Vaxxers and Pro-Vaxxers have created great social conflicts in recent times. This article proposes an artificial intelligence (AI)-based solution to identify and monitor social groups, such as Anti-Vax and Pro-Vax, in ethical manner. The proposed solution uses AI-based sentiment analysis and named entity recognition (NER) to advice political scientist, social scientists, and policy makers to assess the influence and impact of social groups. The proposed solution was deployed via iOS, Android, and Windows App on a range of platforms integrating publicly available 40 857 Twitter data related to COVID-19 in 55 different languages from 15 June 2021 till 31 December 2021. Our system demonstrated that Anti-Vax and Pro-Vax social movements posted 72% and 65% more negative contents compared to average negative sentiments of global COVID-19 related posts during the monitored period. Moreover, Anti-Vax-related posts with “Hoax” keyword were found to have the highest level of social impact with 38 849 retweets and highest level of negativity (i.e., sentiment score of 0.87). We found out that Pro-Vax community engages in social conflict with Anti-Vaxxers referring them as ignorant (i.e., average sentiment score 0.91), stupid (i.e., average sentiment score 0.89), and confused (i.e., average sentiment score 0.88). Most importantly, the social conflict detection system reveals possible locations of conflict.\",\"PeriodicalId\":73324,\"journal\":{\"name\":\"IEEE transactions on technology and society\",\"volume\":\"3 4\",\"pages\":\"290-299\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2022-07-20\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"13\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"IEEE transactions on technology and society\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://ieeexplore.ieee.org/document/9834043/\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"IEEE transactions on technology and society","FirstCategoryId":"1085","ListUrlMain":"https://ieeexplore.ieee.org/document/9834043/","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Tracking Anti-Vax Social Movement Using AI-Based Social Media Monitoring
Anti-Vax social movement possesses a dire threat to governments’ aim of mass vaccination. Moreover, by propagating serious misconceptions and misinformation about COVID-19, Anti-Vaxxers directly and indirectly cause harm to the overall health and wellbeing of the society. In addition, the ongoing clashes between Anti-Vaxxers and Pro-Vaxxers have created great social conflicts in recent times. This article proposes an artificial intelligence (AI)-based solution to identify and monitor social groups, such as Anti-Vax and Pro-Vax, in ethical manner. The proposed solution uses AI-based sentiment analysis and named entity recognition (NER) to advice political scientist, social scientists, and policy makers to assess the influence and impact of social groups. The proposed solution was deployed via iOS, Android, and Windows App on a range of platforms integrating publicly available 40 857 Twitter data related to COVID-19 in 55 different languages from 15 June 2021 till 31 December 2021. Our system demonstrated that Anti-Vax and Pro-Vax social movements posted 72% and 65% more negative contents compared to average negative sentiments of global COVID-19 related posts during the monitored period. Moreover, Anti-Vax-related posts with “Hoax” keyword were found to have the highest level of social impact with 38 849 retweets and highest level of negativity (i.e., sentiment score of 0.87). We found out that Pro-Vax community engages in social conflict with Anti-Vaxxers referring them as ignorant (i.e., average sentiment score 0.91), stupid (i.e., average sentiment score 0.89), and confused (i.e., average sentiment score 0.88). Most importantly, the social conflict detection system reveals possible locations of conflict.