This paper presents a method to discover possible terminological relationships from tweets. We match the histories of terms (frequency patterns). Similar history indicates a possible relationship between terms. For example, if two terms (t1, t2) appeared frequently in Twitter at particular days, and there is a ‘similarity’ in the frequencies over a period of time, then t1 and t2 can be related. Maintaining standard terminological repository with updated relationships can be difficult; especially in a dynamic domain such as social media where thousands of new terms (neology) are coined every day. So we propose to construct a raw repository of lexical units with unconfirmed relationships. We have experimented our method on time-sensitive Arabic terms used by the online Arabic community of Twitter. We draw relationships between these terms by matching their similar frequency patterns (timelines). We use dynamic time warping as a similarity measure. For evaluation, we have selected 630 possible terms (we call them preterms) and we matched the similarity of these terms over a period of 30 days. Around 270 correct relationships were discovered with a precision of 0.61. These relationships were extracted without considering the textual context of the term.

Cet article décrit deux expériences sur la construction de ressources terminologiques multilingues (preterminologies) préliminaires, mais grandes, grâce à des communautés Internet, et s’appuie sur ces expériences pour cibler des données terminologiques plus raffinées venant de communautés Internet et d’applications Web 2.0. La première expérience est une passerelle de contribution pour le site Web de la Route de la Soie numérique (DSR). Les visiteurs contribuent en effet à un référentiel lexical multilingue dédié, pendant qu’ils visitent et lisent les livres archivés, parce qu’ils sont intéressés par le domaine et ont tendance à être polygottes. Nous avons recueilli 1400 contributions lexicales en 4 mois. La seconde expérience est basée sur le JeuxDeMots arabe, où les joueurs en ligne contribuent à un réseau lexical arabe. L’expérience a entraîné une croissance régulière du nombre de joueurs et de contributions, ces dernières contenant des termes absents et des mots de dialectes oraux.

In this paper, we present a new approach to disambiguation Arabic using a joint rule-based model which is conceptualized using Dependency Grammar. This approach helps in highly accurate analysis of sentences. The analysis produces a semantic net like structure expressed by means of Universal Networking Language (UNL) - a recently proposed interlingua. Extremely varied and complex phenomena of Arabic language have been addressed.