The Application Of Domain Knowledge In The Analysis Of Public Opinion In Tourism Networks

Growing of people's quality of life,the tourism industry has been risen rapidly and played as the important role in the national economy.For conforming the time of development,Yunnan has been caught this opportunity and made great efforts to develop the tourism industry.It has become a famous tourist destination place of both local and international.Information technology and economy development has been progressed,the speed of development of Internet technology and intelligent of mobile phone to use social app is more and more low threshold,the major social networking sites has become an important place on Yunnan tourism e-information center.The representative opinions of many Internet users on the topic of online tourism are expanding with the influence of the network public opinion on the tourism industry.In this case,Weibo quickly became interested in the platform with its simple and convenient advantages,gradually become one of the main ways to spread tourism network public opinion.In order to maintain the security,stability and healthy development of Yunnan's tourism industry for a long time,it is a great practical significance to discover the hot topics of tourism in Yunnan and to analyze and predict the evolution trend of the online public opinion on micro-blog.The main content of this paper is: how the Internet users focus on hot topic of tourism with complication,and scattered network data;how to analyze the information extracted from the hot topics of tourism,and to analyze the evolution trend of this topic.At present,we found that most of the hot topic via network technology research methods are getting details from interpretation information content,and found the relationship between those information,and then propose them to be the hot topic in the virtual network of Internet users that will concern about,but the effect is not very ideal,especially in different areas,at the same time the result of getting information method is not as good as satisfactory.Based on the shortcomings of current research,this paper constructs domain ontology for specific fields,and apply the domain ontology to data processing in public opinion analysis,In the courseof text modeling and topic clustering,the topic of high attention is found.Finally,the topic is sorted according to people's attention to the topic's heat,so they get the hot topic.On this basis,combining the related theories of other disciplines to analyze the formation mechanism and evolution characteristics of hot topics,to predict the evolution trend of hot topics.The innovative work done in this paper is as follows:(1)Construct the domain ontology based on the specific domain of Yunnan tourism.(2)Based on the further research of feature extraction algorithm,a feature extraction algorithm based on domain ontology is proposed.The method combines domain ontology and TF-IDF method,ontology reasoning,optimizing feature extraction,and using improved TF-IDF formula to calculate the level words.Using traditional algorithm and improved algorithm to do experimental.Experimental results show that the proposed algorithm improves the accuracy of feature extraction,and proves that it is an effective method for feature extraction.(3)Based on the number of people views on Weibo,likes,and shares;the harmonic number is used to assess the heat of the topic,and the results are sorted according to the evaluation value.The ranking results are compared with the official rankings published by Weibo,and the validity of the evaluation method is verified.