A Study On Hot Degree And Co-occurrence Of Different Spatial And Temporal Tourist Based On User-generated Content

With the rapid development of social networks,User-Generated Content(UGC)has become an important source of dissemination of information.The travel strategy channel of vertical UGC and integrated tourism website provide a platform for tourists to share and communicate personal experience.A large number of tourism destination data with rich spatiotemporal attributes will be produced in this process which provides a data support for geographers that research multi spatial and temporal scale tourism geography issues.This paper takes the Three Gorges of Yangtze River as a case and chooses Ctrip's travel data and Sina's location micro-blog data as data sources.Based on the previous work of the research group,we have enriched and improved the calculation method of the co-occurrence relationship and hot degree.The hot degree of tourism texts is calculated by the method of toponymy weight allocation.The micro-blog hot degree computational method is used for calculating the distribution density of location micro-blog based on coupling degree between the text content and location of micro-blog,and the final micro-blog hot degree is calculated combining word frequency of the text content.The general characteristics of the spatial structure of the tourist destination is reflected by comprehensive heat of the tourist site which is calculated by combining the heat of text and micro-blog.The co-occurrence relationship between the tourist places in tourism texts is expressed in co-occurrence matrix and transposed three tuple.The calculation method of micro-blog co-occurrence relationship is different from the previous method which only consider the co-occurrence of keywords.This method combines the toponymy with position relationship,and reflects co-occurrence network relationship of micro-blogs based on scenic spots.The hot degree and the co-occurrence relationship of scenery of the tourist places in Yangtze River are quantized and visualized by means of the hot degree of different UGC data and calculation method of co-occurrence.The hot degree analysis results show that:1)The characteristic of heat distribution curve of scenic spots in Three Gorges of the Yangtze River is the long tail shape which is analyzed based on tourism texts and micro-blogs,and the cold and hot phenomenon is obvious in the spatial distribution.2)The characteristic distributed in space of high heat scenic spots is “concentrated inside scenic spots and disperse among different scenic spots”.3)The spatial distribution of hot degree has the phenomenon of core guidance and agglomeration,which is indicated in three cores and two scenic spot gathering groups.4)The curve distribution of heat of sightseeing district accords with the law of people's daily routines in different time scales,and its distribution in space varies slightly with time.The analysis results of co-occurrence relationship show that: 1)The high-concurrence intensity of the scenic spots can form a network of high related levels.2)The distribution of network is extremely unbalance between different scenic area which represents the co-occurrence relationship of internal scenic spots in scenic area.The more complex the co-occurrence relationship network in the scenic area is,the more levels of relation are included.3)The co-occurrence relationship network of tourist sites has a distinct stratification phenomenon.The higher the correlation level,the less the number of related scenic spot groups.The research results show that: the calculation method of hot degree and co-occurrence of different spatial and temporal sightseeing district based on UGC can solve the problem of mining and analyzing the data of semantic texts and spatio-temporal attributes in tourism geography and related disciplines.The results of mining and analysis prove that the spatio-temporal information contained in research data has great significance for the study of cognitive space of tourist sites and the temporal and spatial variation of tourist behavior.