Analysis of Arabic Bot Behaviors

Bayan Boreggah, Arwa Alrazooq, Muna S. Al-Razgan, Hana AlShabib
{"title":"Analysis of Arabic Bot Behaviors","authors":"Bayan Boreggah, Arwa Alrazooq, Muna S. Al-Razgan, Hana AlShabib","doi":"10.1109/NCG.2018.8592980","DOIUrl":null,"url":null,"abstract":"Nowadays, online social media became an essential communication platform that affects all our lives. However, it goes unnoticed that there are entities found in social media that affect and manipulate society and pose as a human to do so; these entities are called bots. Over the years, researchers have conducted tremendous work in developing bot detection applications, but unfortunately, most of them focus on analyzing and detecting English bots, whereas there is a noticeable lack in addressing Arabic bots. Therefore, in this paper, we have studied and analyzed Arabic Twitter bots’ behavior, and highlighted the most significant features of these bots. In addition, we addressed the language and cultural effect on these features and whether the bots’ behavior changes based on language and culture. The study started by collecting datasets using crowdturfing campaign and manual labeling. Then we extracted the features that were identified and proven to be useful by other researchers. After that, we built a classifier that tested the probability of an account being human or bot. Finally, the results were analyzed and discussed.","PeriodicalId":305464,"journal":{"name":"2018 21st Saudi Computer Society National Computer Conference (NCC)","volume":"44 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2018-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"6","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2018 21st Saudi Computer Society National Computer Conference (NCC)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/NCG.2018.8592980","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 6

Abstract

Nowadays, online social media became an essential communication platform that affects all our lives. However, it goes unnoticed that there are entities found in social media that affect and manipulate society and pose as a human to do so; these entities are called bots. Over the years, researchers have conducted tremendous work in developing bot detection applications, but unfortunately, most of them focus on analyzing and detecting English bots, whereas there is a noticeable lack in addressing Arabic bots. Therefore, in this paper, we have studied and analyzed Arabic Twitter bots’ behavior, and highlighted the most significant features of these bots. In addition, we addressed the language and cultural effect on these features and whether the bots’ behavior changes based on language and culture. The study started by collecting datasets using crowdturfing campaign and manual labeling. Then we extracted the features that were identified and proven to be useful by other researchers. After that, we built a classifier that tested the probability of an account being human or bot. Finally, the results were analyzed and discussed.
阿拉伯语机器人行为分析
如今,在线社交媒体成为影响我们生活的重要交流平台。然而,人们没有注意到的是,在社交媒体上发现了影响和操纵社会的实体,并假扮成人类这样做;这些实体被称为机器人。多年来,研究人员在开发机器人检测应用程序方面做了大量工作,但不幸的是,大多数研究都集中在分析和检测英语机器人上,而在解决阿拉伯语机器人方面明显缺乏。因此,在本文中,我们对阿拉伯语Twitter机器人的行为进行了研究和分析,并突出了这些机器人最显著的特征。此外,我们还研究了语言和文化对这些功能的影响,以及机器人的行为是否会根据语言和文化而变化。这项研究首先通过众筹活动和人工标签收集数据集。然后我们提取被其他研究人员识别并证明有用的特征。在那之后,我们建立了一个分类器来测试一个账户是人类还是机器人的概率。最后,对研究结果进行了分析和讨论。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信