Micro-blog Based Personalized Search System

Today, the rapid development of Internet technology, whenever and wherever people can publish and share their feelings become the new demand. Micro-blog as a new type of social media, it has been widespread concern. Currently thousands of micro-blogs are emerged on the Internet every day, and it brings challenges to quickly find the desired information for users. The search engine based on micro-blog can solute part of the problem. However, most search engines are based on only the content, it can not meet the needs of accessing to personalized information for users from the mass of micro-blogs. Therefore, how to realize the personalized demand in the micro-blog search engine is a hot topic. this paper establishes user model and integrate into the information retrieval process. The paper also designed a personalized search system based on micro-blog. The research work of this paper mainly include the following aspects:The first is to build user model. This paper mainly around the user model data acquisition, the modeling method and representation, model updating methods of these four aspects has carried on the key discussion and research work. In the personalized technology,system mainly through the analysis of the user original micro-blog and retweeted micro-blog to build user interest model,it statistics the their frequency,and selected the top 50 words as the user interest keywords, and on this basis to achieve the personalized search.After that, this paper uses Lucene framework and successfully research a personalized search function based on the micro-blog platform. Besides, the paper carefully analyze the registration module, the establish index module, the interest model construction module, and the personalized search module. Finally analyzes the advantages and disadvantages of the system.In summary, this paper captures the micro-blog platform, combined with information retrieval and personalized domain related theory and technology, and design a personalized search system based on the micro-blog platform.