Method and Case Study of Hot-Toponym Extraction from Mass Amount of Internet Travel Blog Text
LI Zhao-han · Geography and Geo-Information Science · 2015
This paper discusses the characteristics of toponyms being used in text of Internet travel blog and the significance of this research.The toponyms in Internet travel blog refer to place names or landscape names in tourism.The quantitatively characteristics of toponyms used in travel blog can reflect the cognition structure and the common process of tourists.Depending on the existing Chinese Word Segmentation foundation and the characteristics of toponym in travel blog,this paper selects and uses the ATF*PDF method to calculate the joint weight of characteristic words in the whole travel blog collection.Design an automatic method of hot-toponym extraction from mass amount of text of Internet travel blog,laid the foundation of tourism geography research without manually defined gazetteer.The result of case study indicates that the method can extract tourism related toponym from text quickly.The hotter toponym has higher accuracy.The paper finds out the commonalities and differences in toponyms when being used in natural and cultural travel blog.This could help us find the meaning and potential value of toponyms in travel process by data interpretation.