Premium
Key analysis of smart tourism project setting and tourists' satisfaction degree based on data mining
Author(s) -
Gu Tao,
Song Lijun,
Wang Hua,
Jin Maozhu
Publication year - 2018
Publication title -
concurrency and computation: practice and experience
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.309
H-Index - 67
eISSN - 1532-0634
pISSN - 1532-0626
DOI - 10.1002/cpe.4755
Subject(s) - computer science , collaborative filtering , scalability , tourism , key (lock) , data mining , big data , recommender system , cloud computing , tourist attraction , database , machine learning , computer security , political science , law , operating system
Summary By improving the mining efficiency and enhancing the scalability of the algorithm, it solves the problem that the traditional recommendation algorithm has a long response time and low recommendation efficiency in the recommendation of tourist spots, and cannot adapt to the needs of big data mining. An in‐depth analysis of the existing collaborative filtering recommendation algorithm was conducted, and the Slope One algorithm and the Item‐based algorithm recommended for the tourist attractions were selected. Combine these two algorithms efficiently, parallelize the algorithm based on MapReduce programming on the Hadoop cloud platform, and verify the validity of the algorithm by collecting the “tourism evaluation network” real tourist attraction scoring data. By testing the real tourist attraction score data, it shows that the algorithm not only improves the accuracy of the recommendation but also has higher running speed than the traditional collaborative filtering algorithm. The experimental results show that the algorithm has higher mining performance and scalability and can be better adapted to the characteristics of large tourist sites, sparse data matrix, and meet the high hit rate and personalized requirements of tourist attractions.