Mining the blogosphere to generate local cuisine hotspots for mobile map service

Abstract

On-the-go consumers require dynamic information, particularly "word of mouth, " to make better purchase decisions. A popular genre of mobile map services is travel/cuisine, which is a popular topic for bloggers as well. This study attempts to generate local cuisine hotspot maps through blog content mining. The main obstacle in doing this involves recognizing and extracting restaurants and essential restaurant information (i.e., restaurant dishes) in unstructured content. In contrast to traditional Named Entity Recognition (NER) targets, dish name is a promising target that received little attention in previous studies. This study develops methods for recognizing and extracting restaurant names and dish names from Chinese blog posts and achieves satisfactory performance. The extraction results are arranged into hotspots and presented in map views. The extracted information can be fed back to POI (Point of Interest) databases, and thus a brand-new POI database comprising information extracted from User Generated Content (UGC) can be realized.