Název: | User profile detection based on text mining: technical report no. DCSE/TR-2004-09 |
Autoři: | Grolmus, Petr |
Datum vydání: | 2004 |
Nakladatel: | University of West Bohemia in Pilsen |
Typ dokumentu: | zpráva report |
URI: | http://www.kiv.zcu.cz/publications/ http://hdl.handle.net/11025/21604 |
Klíčová slova: | vyhledávání;uživatelský profil;algoritmus |
Klíčová slova v dalším jazyce: | searching;user profile;algorithm |
Abstrakt v dalším jazyce: | The old-fashioned search engine model based usually on Boole´s algebra has become outdated. Current systems tend to meet users (customers) needs more precisely and hence they have to improve their basis. The searching process has to be based on deeper knowledge of individual user preferences - i.e. on user profiles. This work presents an overview of recommender and expert finding systems. It also introduces the ProGen System rising at the University of West Bohemia. For the characteristic phrases selection from document collections is used the STC algorithm. Our system is able to work with multi-lingual document collections. A developed document language recognition is based on stop-word occurrence. We have developed a stemming algorithm combining both the dictionary-based and algorithm-based method. Finally, an outlook for the future work is sketched out. |
Práva: | © University of West Bohemia in Pilsen |
Vyskytuje se v kolekcích: | Zprávy / Reports (KIV) |
Soubory připojené k záznamu:
Soubor | Popis | Velikost | Formát | |
---|---|---|---|---|
Grolmus.pdf | Plný text | 506,16 kB | Adobe PDF | Zobrazit/otevřít |
Použijte tento identifikátor k citaci nebo jako odkaz na tento záznam:
http://hdl.handle.net/11025/21604
Všechny záznamy v DSpace jsou chráněny autorskými právy, všechna práva vyhrazena.