網路搜尋結果自動組織之研究

A Study on Organizing Web Search Results

蔡景祥(Ching-Hsiang Tsai)

指導教授 ： 簡立峰

國立臺灣大學/管理學院/資訊管理學研究所/碩士(2005年)

https://doi.org/10.6342/NTU.2005.00256

摘要

藉由搜尋引擎的幫助，人們已可輕易地從網路上獲得大量的資訊，然而這樣的搜尋結果經常缺乏適當的組織，使用者常須費心逐一檢視搜尋結果以找尋相關的資訊。過去的研究嘗試利用文件分群技術解決此問題，然而分群之後的結果往往缺乏語意上的解釋。
本論文提出一個新的搜尋結果組織技術，首先從搜尋結果摘錄中發掘出重要的主題術語，重要主題術語可以幫助使用者快速瀏覽整個搜尋結果中的重要概念，接著以使用者自訂的主題類別重新組織搜尋結果。在過去的搜尋結果組織技術中，都沒有考慮到使用者的偏好問題，本研究提出的作法不但可以以使用者比較熟悉的主題類別去標記所有出現在搜尋結果中的重要主題，幫助理解，還可以藉此瞭解重要主題之間的關係。這個技術可以提供使用者對於搜尋結果中重要主題的有較佳的整體概念，並且可以針對不同使用者的不同偏好加以重新組織，以個別使用者偏好的方式呈現。從初步實驗所獲致的結果發現，本研究所提方法可協助使用者快速瀏覽搜尋結果與重新闡述他的查詢。

關鍵字

全球資訊網 ； 搜尋結果組織 ； 分群技術 ； 分類技術

並列摘要

With the rapid growth of the amount of Web pages and the number of users, the demand for powerful search engines is high. Existing commercial search engines are still fraught with some disadvantages. The ranked list of search result pages returned from a search engine is often long and mixed with some concepts that are relevant to the user’s query but hard to be identified. Web search results are actually lack of a well organization, which require users to pay attention on examining the retrieved pages and identifying the correct ones. Conventional research to dealing with this problem relied on using document/term clustering algorithms to handle search results. However, the clustered results are still lack of comprehensive explanations.
In this thesis, we develop a new search result organizing approach which contains some characteristics outperformed from the conventional approaches. First, it extracts important topic terms from search result pages and tries to provide a comprehensive overview for the search result. Second, the extracted topic terms are organized with the manner the user prefers. In fact, users’ preferences were seldom taken into account in previous research. With the proposed approach, it is able to extract important topic terms from Web search result snippets and organizes them with the topic classes defined by users. A series of experiments has been conducted and the obtained results show that the proposed approach can help users effectively browse the concepts embedded in the search result pages and easier to locate relevant pages.

並列關鍵字

World Wide Web ； Search Result Organizing ； Clustering ； Classification

參考文獻

[11] Google search engine, (2005) http://www.google.com

[13] A. K. Jain, M. N. Murty and P. J. Flynn, “Data Clustering: A Review”, ACM Computing Surveys, Vol. 31, No. 3, September 1999.

[14] Z. Jiang, A. Joshi, R. Krishnapuram and L. Yi, “Retriever: Improving Web Search Engine Results Using Clustering”, Technical Report, CSEE Department, UMBC, 2000.

[16] Krishna Kummamuru, Rohit Lotlikar, Shourya Roy, Karan Singal and Raghu Krishnapuram, “A Hierarchical Monothetic Document Clustering Algorithm for Summarization and Browsing Search Results”, In Proceedings of the 13th international conference on World Wide Web, 2004, Pages 658-665.

[19] Stanley Loh, Leandro Krug Wives and José Palazzo M. de Oliveira, “Concept-Based Knowledge discovery in Texts Extracted from the Web”, In ACM SIGKDD Explorations Newsletter Vol. 2, No. 1, 2000, Pages 29-39.