TY - JOUR A2 - Wu, Lei AU - Jiang, Kai AU - Liu, Like AU - Xiao, Rong AU - Yu, Nenghai PY - 2012 DA - 2012/08/26 TI - Mining Local Specialties for Travelers by Leveraging Structured and Unstructured Data SP - 987124 VL - 2012 AB - 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. SN - 1687-5680 UR - https://doi.org/10.1155/2012/987124 DO - 10.1155/2012/987124 JF - Advances in Multimedia PB - Hindawi Publishing Corporation KW - ER -