Research On The Query And Visual Analysis Technology Of Tourism Data

In recent years, with the popularity and the development of online social media, more and more tourists are declined to release tourism information on the social media anyplace and anytime, but also has produced the huge volume, multi-dimensional, travel unstructured data at the same time. The research of this complex data has attracted attention of researches from the he majority of colleges and universities and the business community. This paper introduces main research work of tourism data on social media as the following three aspects: this first is tourism data collection and data preprocessing,and the second is data analysis methods based on tourism data, including Top-k dominating query algorithm, technology of text sentiment mining and keywords extraction and so on, the last is the network opinion visualization research based on the tourism data.1, For collection and preprocessing of tourism data on social media, this paper first discusses the process for obtaining tourism data from the tourism social network site,secondly, analyses two different ways: packet capture and simulation of different browser,which both are able to collect the micro-blog data, and then this paper introduces how to collect micro-blog data by search capabilities, the last is the research on the data preprocessing of data cleansing and data integration.2, In order to meet demand for subspace Top-k dominating query, the paper do some research on Top-k dominating query algorithm based on tourism data. Firstly, the ordered lists for each data attribute is constructed by the B+-Tree. Secondly, round-robin scheduling algorithm is used to scan ordered attribute lists satisfied skyline criterion.Some candidates are generated and k end tuples are obtained. Thirdly, the dominated scores of end tuples were calculated by using the probability distribution model according to the generated candidate tuples and end tuples. Through iterating the above process, the optimal query results were obtained. In this paper, SVM model is adopted for the short document sentiment classification based on features selection. Features selection includepunctuations &tags, sentiment words, modal adverbs, comment attributes and travelrelevant keywords. The result demonstrates that the methods used in this paper has some practical values.3, Based on the network opinion from the tourism data, an object-oriented visual analysis Web framework is proposed in this paper, which is improving the speech of the team collaboration development. This paper studies and designs a visual analytic system for tourism network opinion. The system supports place tourist information, comments emotional information, social network information display and interaction analysis, it is convenient for the user to multi angle to understand the public opinion of the tourist information and found comments implied characteristics, relationships and trends.Experimental results show that the proposed the system can effectively analyze tourists' regional tendency and emotional changes. It can also help tourism management department more thoroughly understand the tourism network opinion in time.