A Weighted Semantic Similarity Technique for Document Clustering
Publish Year: 1391
نوع سند: مقاله کنفرانسی
زبان: English
View: 1,587
This Paper With 6 Page And PDF Format Ready To Download
- Certificate
- من نویسنده این مقاله هستم
استخراج به نرم افزارهای پژوهشی:
شناسه ملی سند علمی:
ICEEE04_181
تاریخ نمایه سازی: 6 مهر 1391
Abstract:
Document similarity has formed an important area in information retrieval and the document mining domains. In other words, having an accurate document similarity measure has a great influence on our performance in these areas. Although many proposed document similaritymethods suffer from several shortcomings. Therefore, this paper focuses on the problem of text document clusteringand has proposed a weighted graph algorithm to improve previous proposed methods. In this study, a weighted method which is based on the semantic relation of document's words is introduced. Using this relation helps us to capture the meaning of documents more accurately. Final results confirm that our method outperforms othercompared methods
Keywords:
Authors
Nasrin Malakooti
School of Electrical & Computer EngineeringShiraz UniversityShiraz, Iran
Ali Hamzeh
School of Electrical & Computer EngineeringShiraz UniversityShiraz, Iran