TY - GEN
T1 - 20 Years of Analyzing Multilingual Propaganda Content on the Web.
AU - Last, Mark
N1 - DBLP License: DBLP's bibliographic metadata records provided through http://dblp.org/ are distributed under a Creative Commons CC0 1.0 Universal Public Domain Dedication. Although the bibliographic metadata records are provided consistent with CC0 1.0 Dedication, the content described by the metadata records is not. Content may be subject to copyright, rights of privacy, rights of publicity and other restrictions.
PY - 2023
Y1 - 2023
N2 - From the early years of the Internet as a global information infrastructure, multilingual propaganda content has been circulating on the web. For example, the WWW played a critical role in the planning of the 9/11 attacks, both as a source of inspirational information and as a safe means of covert communication between the plotters. Shortly after the tragic events of 2001, our binational team of US and Israeli researchers started to explore the online activities of various hate groups. Initially, we developed a prototype of a monitoring system aimed at detecting the frequent visitors of terrorist websites, which could be influenced by terrorist propaganda and eventually develop into what we call today “the lone wolf attackers”. Shortly after, we focused on another, closely related question: what makes terrorist-generated propaganda content in various languages different from unbiased news reports discussing similar topics? Over the years, we developed prototypes of several additional text analysis tools such as text-summarization algorithms, which can automatically summarize large amounts of untranslated content in any language, as well as AI tools for automated detection of metaphoric language. After presenting the motivational and ethical foundations of our research, I plan to describe some of the methods developed during the last two decades and finally, discuss past and future challenges in this important and fascinating domain.
AB - From the early years of the Internet as a global information infrastructure, multilingual propaganda content has been circulating on the web. For example, the WWW played a critical role in the planning of the 9/11 attacks, both as a source of inspirational information and as a safe means of covert communication between the plotters. Shortly after the tragic events of 2001, our binational team of US and Israeli researchers started to explore the online activities of various hate groups. Initially, we developed a prototype of a monitoring system aimed at detecting the frequent visitors of terrorist websites, which could be influenced by terrorist propaganda and eventually develop into what we call today “the lone wolf attackers”. Shortly after, we focused on another, closely related question: what makes terrorist-generated propaganda content in various languages different from unbiased news reports discussing similar topics? Over the years, we developed prototypes of several additional text analysis tools such as text-summarization algorithms, which can automatically summarize large amounts of untranslated content in any language, as well as AI tools for automated detection of metaphoric language. After presenting the motivational and ethical foundations of our research, I plan to describe some of the methods developed during the last two decades and finally, discuss past and future challenges in this important and fascinating domain.
M3 - Conference contribution
SP - 1
EP - 2
BT - Proceeding of the IACT'23 Workshop
ER -