Amina Chouigui

PhD Student
Higher School of Computer Sciences (ENSI)
La Manouba University
Research laboratory: 
Research Profile: 
Supervisors (s)

Ph.D Thesis description

Brief description

Arabic language presents many challenges because of its morphological richness and its semantic complexity. In return, the digital content of news websites in Arabic language is changing considerably; which makes the analysis of these texts interesting in order to detect the most influential events as well as their correlations..

Detailed description

The general problematic of the proposed thesis is part of the Text Mining and the Information Retrieval in Arabic. The temporal component will also be treated in this work as we are interested in news texts from online sources. The latter theme is referred to as Temporal Text Mining.

We started with collecting news texts from a Tunisian website. Our corpus, named ANT Corpus, is available online ( We aim to expand our corpus by collecting texts from other international websites. ANT Corpus is used for the text classification and will be used for other research topics such as terminology extraction and temporal data mining, Information Retrieval...