The Study of Bi-Gram combines Vector Weighting for Text Categorization Based on Community Forestry Plans

• Main Authors: Yuan-ming Tai, 戴元銘
• Other Authors: Lai-His Lee
• Format: Others
• Language: zh-TW
• Published: 2007
• Online Access: http://ndltd.ncl.edu.tw/handle/64970571103833930599

碩士 === 國立屏東商業技術學院 === 資訊管理系 === 95 === Projects of community forestry proposed by Forestry Bureau had been a popular policy for community development. However, the difficulty for project categorization causes communities unable to learn experiences from other communities. This study aims to propose a method to categorize projects automatically. Keywords from categorized projects are collected previously so as to build a keyword data base for keyword comparisons. Then the weighted bigram technique is employed as the main categorization method to compare keywords of new projects with keywords in the data base. The resulting precision rate is 93.55%, which shows well performance of project categorization. A system prototype is also demonstrated to show the procedure of project categorization. The results are expected to let communities who are newly participate the project can learn experiences from other communities in the same project categorization.