Hateful People or Hateful Bots?

Abstract

Arabic Twitter space is crawling with bots that fuel political feuds, spread misinformation, and proliferate sectarian rhetoric. While efforts have long existed to analyze and detect English bots, Arabic bot detection and characterization remains largely understudied. In this work, we contribute new insights into the role of bots in spreading religious hatred on Arabic Twitter and introduce a novel regression model that can accurately identify Arabic language bots. Our assessment shows that existing tools that are highly accurate in detecting English bots don't perform as well on Arabic bots. We identify the possible reasons for this poor performance, perform a thorough analysis of linguistic, content, behavioral and network features, and report on the most informative features that distinguish Arabic bots from humans as well as the differences between Arabic and English bots. Our results mark an important step toward understanding the behavior of malicious bots on Arabic Twitter and pave the way for a more effective Arabic bot detection tools.

Holy Tweets

“…When analyzing the tweets in our dataset, we found a trend of Quran tweets being tagged with the hashtag "# <du'a>" which translates to "#prayer'. We suspected that this trend might indicate bot activity, given that it was very consistent and frequent, which is also noted by [7]. After further investigation of these tweets metadata, we found that these tweets were automatically generated through an app.…”

“…The second strand of literature centers the different ways religious communities utilize new media forms like social media as platforms for expressing, discussing, and practicing their religious identities [6,7,9,12,19,21,26,38,51]. We reference this work to better situate our study at the intersection of both lines of research on religion and technology.…”

“…Albadi et al's. [7,8] study found that bots were responsible for about 11% of all religious hateful tweets on Arabic Twitter [7]. Their study revealed the use of 3rd party Islamic applications to post Islamic supplications and Quranic verses on their behalf.…”

“…this is more difficult to achieve in this dataset due to the large number of accounts with no profile picture for cultural reasons [2]6 We also checked for potential bot accounts, but none of the labeled accounts had a strong evidence of being a bot. The only noticed bot-like activity was the presence of automatically generated tweets using the applications mentioned earlier, but it was clear that these accounts still post other manually generated tweets 7. For the purpose of this study, we focused our analysis on identifiable religious content like Quran, Hadith, and Dua.…”

Hybrid Intelligence Strategies for Identifying, Classifying and Analyzing Political Bots

“…As such, we were able to detect and classify the political bots operating in Spain's 2019 elections, as well as to develop the country's first political bot classifier. Consequently, we were able to overcome the problems that arise upon using classifiers designed for texts written in English (Albadi et al 2019).…”