Dana Al-Ghadhban, Eman Alnkhilan, Lamma Tatwany, Muna Alrazgan
{"title":"Twitter中的阿拉伯语讽刺检测","authors":"Dana Al-Ghadhban, Eman Alnkhilan, Lamma Tatwany, Muna Alrazgan","doi":"10.1109/ICEMIS.2017.8272990","DOIUrl":null,"url":null,"abstract":"Sarcasm is a special form of irony or satirical wit in which people convey the opposite of what they mean. Sarcasm largely increases in social networks, especially in Twitter. Detecting sarcasm in tweets improves the automatic analysis tools that analyze the data to provide or enhance customer service and fabricate or enhance a product. Also, there are few studies that focus on detecting Arabic sarcasm in tweets. Consequently, we propose a classifier model that detects Arabic-sarcasm tweets by classifying them as sarcastic by setting some features that may declare a tweet as sarcastic using Weka. We evaluated our model through recall, precision, and f-score measurements that gave 0.659, 0.710, and 0.676 values, respectively, which these results are high especially when it comes to Arabic.","PeriodicalId":117908,"journal":{"name":"2017 International Conference on Engineering & MIS (ICEMIS)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2017-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"28","resultStr":"{\"title\":\"Arabic sarcasm detection in Twitter\",\"authors\":\"Dana Al-Ghadhban, Eman Alnkhilan, Lamma Tatwany, Muna Alrazgan\",\"doi\":\"10.1109/ICEMIS.2017.8272990\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Sarcasm is a special form of irony or satirical wit in which people convey the opposite of what they mean. Sarcasm largely increases in social networks, especially in Twitter. Detecting sarcasm in tweets improves the automatic analysis tools that analyze the data to provide or enhance customer service and fabricate or enhance a product. Also, there are few studies that focus on detecting Arabic sarcasm in tweets. Consequently, we propose a classifier model that detects Arabic-sarcasm tweets by classifying them as sarcastic by setting some features that may declare a tweet as sarcastic using Weka. We evaluated our model through recall, precision, and f-score measurements that gave 0.659, 0.710, and 0.676 values, respectively, which these results are high especially when it comes to Arabic.\",\"PeriodicalId\":117908,\"journal\":{\"name\":\"2017 International Conference on Engineering & MIS (ICEMIS)\",\"volume\":\"4 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2017-05-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"28\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2017 International Conference on Engineering & MIS (ICEMIS)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/ICEMIS.2017.8272990\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2017 International Conference on Engineering & MIS (ICEMIS)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICEMIS.2017.8272990","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Sarcasm is a special form of irony or satirical wit in which people convey the opposite of what they mean. Sarcasm largely increases in social networks, especially in Twitter. Detecting sarcasm in tweets improves the automatic analysis tools that analyze the data to provide or enhance customer service and fabricate or enhance a product. Also, there are few studies that focus on detecting Arabic sarcasm in tweets. Consequently, we propose a classifier model that detects Arabic-sarcasm tweets by classifying them as sarcastic by setting some features that may declare a tweet as sarcastic using Weka. We evaluated our model through recall, precision, and f-score measurements that gave 0.659, 0.710, and 0.676 values, respectively, which these results are high especially when it comes to Arabic.