A Research Based on Weights of Words and Intentions Analysis to Enhance the Accuracy of Search Engines

• Main Authors: You-Hong SYU, 許佑鴻
• Other Authors: Jen-peng Huang
• Format: Others
• Language: zh-TW
• Published: 102
• Online Access: http://ndltd.ncl.edu.tw/handle/45992842858957414748

碩士 === 南台科技大學 === 資訊管理系 === 101 === Due to the vigorous development of the Internet, the amount of data around the world is rising every year. Although we use the search engines to search for information on the Internet, the search results may not be useful to users. People like to use keywords to search in traditional search engines, but the search results do not meet the needs of users. Therefore, in this thesis we propose a search engine platform to distinguish the intentions of the users in order to help users to find the information they need. We mainly develop a search engine platform which integrates with intentions analysis to improve accuracy of search results by using a web mining and a Chinese word segmentation technique. In this thesis a system with Chinese word segmentation is employed CKIP (Chinese Knowledge Information processing) system for conducting system design and research. In order to improve the accuracy of searching, we use the 5W1H to analyze searched strings to understand the intentions of users and use the TF-IDF weights values of keywords and similar questions as the two-stage weight ranking for each web page. The experimental results indicate that the proposed approach outperform a significant improvement on the accuracy of search engines.