Authoritative sources in a hyperlinked environment
Journal of the ACM (JACM)
Extended Boolean information retrieval
Communications of the ACM
Introduction to Information Retrieval
Introduction to Information Retrieval
Mining city landmarks from blogs by graph modeling
MM '09 Proceedings of the 17th ACM international conference on Multimedia
Generating location overviews with images and tags by mining user-generated travelogues
MM '09 Proceedings of the 17th ACM international conference on Multimedia
TravelScope: standing on the shoulders of dedicated travelers
MM '09 Proceedings of the 17th ACM international conference on Multimedia
Equip tourists with knowledge mined from travelogues
Proceedings of the 19th international conference on World wide web
W2Go: a travel guidance system by automatic landmark ranking
Proceedings of the international conference on Multimedia
On theme location discovery for travelogue services
Proceedings of the 34th international ACM SIGIR conference on Research and development in Information Retrieval
Hi-index | 0.00 |
Recently, many local review websites such as Yelp are emerging, which have greatly facilitated people's daily life such as cuisine hunting. However they failed to meet travelers' demands because travelers are more concerned about a city's local specialties instead of the city's high ranked restaurants. To solve this problem, this paper presents a local specialty mining algorithm, which utilizes both the structured data from local review websites and the unstructured user-generated content (UGC) from community Q&A websites, and travelogues. The proposed algorithm extracts dish names from local review data to build a document for each city, and applies tfidf weighting algorithm on these documents to rank dishes. Dish-city correlations are calculated from unstructured UGC, and combined with the tfidf ranking score to discover local specialties. Finally, duplicates in the local specialty mining results are merged. A recommendation service is built to present local specialties to travelers, along with specialties' associated restaurants, Q&A threads, and travelogues. Experiments on a large data set show that the proposed algorithm can achieve a good performance, and compared to using local review data alone, leveraging unstructured UGC can boost the mining performance a lot, especially in large cities.