Personalized multilingual Web content mining

Personalized multilingual Web content mining is particularly important for user who wants to keep track of global knowledge that is relevant to his/her personal domain of interest over the multilingual WWW. This paper presents a novel concept-based approach to personal multilingual Web content mining by constructing a personal multilingual Web space using self-organising maps. Multilingual linguistic knowledge required to define the multilingual Web space is made available by encoding all multilingual concept-term relationships using a multilingual concept map. With this map as the linguistic knowledge base, a concept-based multilingual text miner is developed to reveal the conceptual content of multilingual Web documents and to form concept categories of multilingual Web documents on a concept-based browsing interface. To construct the personal multilingual Web space, a concept-based user profile is generated from a user's bookmark file for highlighting the user's topics of information interests on the browsing interface. As such, personal multilingual Web mining activities ranging from explorative browsing to user-oriented concept-focused information filtering are facilitated.