Formal concept analysis and rough set theory for an effective representation of arabic short text

Abstract

With the increase use of mobile devices, such as smartphones and tablets, short text messages, tweets, comments and so on, have become a large portion of the online text data. Today, about one billion users interact daily on online social networks, where they share information and discuss a wide variety of topics. As in the rest of the world, users in Arab countries engage in social media applications. The representation of these short texts plays a vital role in language understanding. As a result, it may affect positively or negatively the performance of any Arabic text mining task. In this paper, we propose an efficient Arabic short text based on Formal Concept Analysis (FCA), which is a mathematical tool that offers conceptual data for knowledge representation, extraction and analysis with applications in different areas; combined with Rough Set Theory (RST) as a mathematical tool to deal with imprecise and vague data. The obtained results illustrate the interest of our contribution.