Personalized Optimal Search in Local Query Expansion

Personalized Optimal Search in Local Query Expansion Shan-Mu Lin1 and Chuen-Min Huang2 1Dept. of Information Management, National Yunlin University of Technology and Science, Douliou, Taiwan 2 Dept. of Information Management, National Yunlin University of Technology and Science, Douliou, Taiwan Abstract Query Expansion was designed to overcome the barren query words issued by user and has been applied in many commercial products. This treatment tries to expand query words to identify users’ real requirement based on semantic computation. It may be critical to deal with the problem of information overloading and diminish the using threshold, however the modern retrieval systems usually lack user modeling and are not adaptive to individual users, resulting in inherently non-optimal retrieval performance. In this study, we propose the LLSF method based on each individual search history to automatically generate specific personalized profile matrix. By which to generate context-based expanded query words. Considering the accuracy of retrieving performance, we process query words re-weighting algorithm to achieve this goal. Finally, the documents list is ranked by the way of stressed density distribution modeling. And the experimental result shows that our framework corresponds to personalization and the performance is very promising. Keywords: Personalization, Latent Semantic Indexing, Query Expansion, Relevance Feedback, Maximum Entropy Density Function. 1. Introduction 1.1 Research Background and Motivation The widespread usage of search engines has grown for many years, The searching technique can be used to apply in various aspects, either in World Wide Web or in particular Information Retrieval (IR) database. People can find what they want through it in the world of information overloading. For all of these reasons, search engine now becomes indispensable in the modern lives. Traditional search engine presents search result based on keyword matching of users’ query. It is the simplest method to gather documents associated with specific keywords. However, it’s possible for users to acquire undesired results due to inadequate acquisition.. One of these problems is most common users of IR systems type short queries. (Shen et al., 2005) From a single query, however, the retrieval system can only have very limited clue about the user’s information need. Mostly, it’s hard for users to realize what actual searching requirement is when proceeding searching activities, so there are certain of measure to solve the problem about vague queries issued from users in the past years. 1.2 Research Objective In this article, we try to provide users more selective query keywords which are related to original query not only for the suggestion but also to help users realizing the real requirement in searching behaviors when users submit too brief query to find out more wanted documents. In addition, we also decide to deliver the decision making authority to users of which documents seem to be more preferred by them for achieving user center approach. Otherwise, in order to provide each user with more personal searching environment and contents, we endeavor to propose several approaches to adapt search results according to each user’s information need. 2. Related Work 2.1 Review of Refining …

Content truncated to 500 words