Web Science and Digital Libraries Research Group

Introduction: There is a significant amount of research papers and tools for Named-entity recognition (NER); however, only a small potion of it addresses Arabic text and even less tools for extracting named entities from documents written in Arabic. In August 2020, I proposed an approach for  extracting named entities from Arabic text using a combination of tools, Google Translate and Stanford NERC , and produced comparable results to Arabic Linguistic Pipeline (ALP) . The implementation of my approach,  GTS, is available on GitHub . In December 2020, I wrote a  blog post outlining tools and libraries for matching Arabic names written in English , which is important for Entity Linking, a subtask of Natural Language Processing (NLP). While discussing the importance of Entity linking is beyond the scope of this post, merging Arabic named entities written in English is the first step for Entity Linking when processing English documents. This is because discrepancie...

Internet Archive & Libyan newspapers logos Colonel Gaddafi ruled Libya for 42 years after taking power from King Idris in a 1969 military coup . In August 2011, his regime was toppled in the so-called Arab Spring. For more than four decades, media in Libya was highly politicized to support Gaddafi’s regime and secure his power. After the Libyan revolution (in 2011), media became freed from the tight control of the government, and we have seen the establishment of tens if not hundreds of new media organizations. Here is an overview of one side, newspapers, of Gaddafi’s propaganda machine: 71 newspapers and magazines  All monitored and published by the Libyan General Press Corporation (LGPC)  The Jamahiriya News Agency (JANA) was the main source of domestic news  No real political function other than to polish the regime’s image  Publish information provided by the regime  The following are the Libyan most well-known newspapers which are all publ...

In this work, I collected the top 20 Arabic websites that I like and browse, and in my personal judgment consider as popular (shown in Table 1). For each, I checked its ranking globally and locally based on Alexa Ranking . Then I used MemGator tool to check if it is archived, and got the estimated creation date based on the first memento date. After that, I checked who archived the webpage first (shown in Table 2). Arabic websites in general were evaluated based on how well they were archived and indexed in my previous work, How Well Are Arabic Websites Archived? . We sampled 300,646 Arabic language pages, and found that 46% are not archived and 31% are not indexed by Google . Table 1: List of my favorite Arabic Websites and its description Website Site Description maktoob.yahoo.com Yahoo! مكتوب A major internet portal and email service provider in Arabic language. aljazeera.net الجزيرة نت News channel, political, economic, and thoughts. 6a...