检索规则说明:AND代表“并且”;OR代表“或者”;NOT代表“不包含”;(注意必须大写,运算符两边需空一格)
检 索 范 例 :范例一: (K=图书馆学 OR K=情报学) AND A=范并思 范例二:J=计算机应用与软件 AND (U=C++ OR U=Basic) NOT M=Visual
作 者:史达 黄子璇 李飞 SHI Da;HUANG Zixuan;LI Fei(Surrey International Institute,Dongbei University of Finance and Economics,Dalian 116025;School of Tourism and Hotel Management,Dongbei University of Finance and Economics,Dalian 116025;School of Big Data and Artificial Intelligence,Dalian University of Finance and Economics,Dalian 116622,China)
机构地区:[1]东北财经大学萨里国际学院,大连116025 [2]东北财经大学旅游与酒店管理学院,大连116025 [3]大连财经学院大数据与人工智能学院,大连116622
出 处:《干旱区资源与环境》2022年第11期175-182,共8页Journal of Arid Land Resources and Environment
基 金:辽宁省社会科学基金项目(L20BGL025)资助。
摘 要:旅游规模预测研究亟待应用旅游大数据及其适应性方法,以提升预测的准确度。文章基于多来源搜索引擎指数和UGC数据,以ARIMA模型为基准,综合运用灰色关联度分析、TF-IDF自然语言处理技术、机器学习领域中适用范围最广的RF与SVR模型,对重庆市月度旅游规模展开预测。研究发现:融合多来源搜索引擎指数与包含旅游者丰富心理信息的UGC数据进行的旅游规模预测,在三种模型中的预测精度均呈提升态势,说明多源旅游大数据对目的地潜在客流具有前兆作用。在相同数据集约束下,ARIMAX、RF、SVR三种模型的预测精度递增,表明机器学习算法对于旅游大数据具有更强的分析与处理能力。文中提供了集成多源异构旅游大数据与高效的机器学习算法以回应城市旅游规模预测问题的新思路。It is urgently needed to apply tourism big data and its adaptive methods to forecasting tourism scale for improving the accuracy of forecasting.Based on multi-source search engine index and user generated content data(UGC),the ARIMA model is taken as a benchmark,gray correlation analysis,TF-IDF technology,and both of support vector regression and random forest method which are the most widely applicable in the field of machine learning,are comprehensively used to forecast the monthly tourism scale in Chongqing.The following two main results are obtained.Firstly,the forecasting accuracy using multi-source search engine index data and UGC data containing tourists’rich psychological information shows a trend of improvement in each of three models(i.e.,ARIMAX,RF,SVR models).The multi-source tourism big data has a precursory effect on the potential scale of the destination.Secondly,under the same dataset constraints,the forecasting accuracy of ARIMAX,RF,and SVR models are gradually improved,indicating that machine learning algorithms have stronger analyzing and processing capabilities for tourism big data.This paper attempts to forecast the scale of urban tourism by a new research path,which integrates multi-source heterogeneous tourism big data and efficient machine learning algorithms.
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在链接到云南高校图书馆文献保障联盟下载...
云南高校图书馆联盟文献共享服务平台 版权所有©
您的IP:216.73.216.20