本論文以標籤資源為研究資料，考慮使用者在以查詢字於社群標籤資源中進行搜尋，探討如何從搜尋結果物件的標籤找出有效篩選物件的標籤字，並自動組織成概念階層架構，以方便使用者進行進一步選取所需物件。我們從包含查詢字為標籤的物件中，以這些物件包含的標籤當作候選標籤字，從中挑選出與查詢字相關度較高的前k個標籤作為代表標籤。我們以人為給定有上下概念包含關係的標籤配對組合為訓練資料，根據個別標籤字在資料物件的多種出現特徵，利用Rank-SVM模型學習判別語意概念高低排序模型。此外，同樣以人為給定具語意包含關係及不具語意包含關係的兩類標籤配對為訓練資料，根據標籤配對中兩個標籤在資料庫中出現情況所計算出的多種特徵，運用SVM模型學習出判斷兩個標籤是否有語意包含關係的分類模型。我們將查詢結果代表標籤字及其特徵輸入排序模型中進行語意概念廣度的排序。依照其排序結果之順序一一加入概念架構中，再由分類模型判斷每一個新加入概念架構的代表標籤可作為在概念架構中那些標籤下的子概念，建立出標籤概念階層式架構。實驗結果顯示，本論文方法所挑選的代表標籤字並進行建立語意階層式架構，能夠有好的查詢效果；同時本論文提出的階層式架構建立方法也能找出具語意包含關係的標籤架構。

This thesis considers the scenario that users give short queries to search the resources with tags. In order to help users find the required resources efficiently, our goal is to study how to find the tags used for further filtering the objects in the query results and construct a concept hierarchy for these tags automatically. At first, we find out the query results which consist of all the objects with tag sets containing the query terms. All the tags of these objects are called the candidate tags. Among these candidate tags, we select the top-k tags whose relatedness with the query is the highest, which are called the representative tags. In the offline-processing, according the various features of tags, a collection of tag pairs that have relationships of semantic containment is used as training data to learn the concept-abstraction sorting model by using Rank-SVM. In addition, based on the co-occurring features between a pair of tags got from the corpus, we use SVM to construct a classification model for deciding whether a tag represents a sub-concept of another tag. Then the representative tags and their features are inputted to the concept sorting model to get a sorted list according to their degrees of concept abstraction. Each tag in the sorted list is added into the concept hierarchy of tags one by one. The constructed classification model is used to decide whether a newly added representative tag can serve as a sub-concept of the other tags existing in the concept hierarchy. The experimental results show that performing the proposed representative tag selection method before constructing the concept hierarchy of tags can improve the effectiveness of searching. Furthermore, the proposed method of constructing concept hierarchical of tags can find a good result with level-wise sematic relationships among the representative tags.

[1] R. Binzabiah and S. Wade, “Proposed Method to Build an Ontology Based on Folksonomy,” in Proceedings of the 2012 International Conference on Information Society (i-Society), 441 - 446 , June 2012.
[2] S. Lohmann and P. Diaz, ”Representing and Visualizing Folksonomies as Graph- A Reference Model,” in Proceedings of International Working Conference on Advanced Visual Interfaces(AVI), 2012.
[3] D. Skoutas and M. Alrifai, “Tag Clouds Revisited,” in Proceedings of the 20th international conference on Information and knowledge management(CIKM), 2011.
[4] P. Venetis, G. Koutrika and H. Garcia-Molina, “On the Selection of Tags for Tag Clouds,” in Proceedings of the fourth ACM international conference on Web search and data mining(WSDM), 2011.
[5] L. Adeyanju, D. Song, M-D. Albakour, U. Kruschwitz, A.D. Roeck and M. Fasil, ”Adaptation of the Concept Hierarchy Model with Search Logs for Query Recommendation on Intranets” in Proceedings of 35th international conference on Research and development in information retrieval(SIGIR), 2012.
[6] Y. Song, B. Qiu and U. Farooq, “Hierarchical Tag Visualization and Application for Tag Recommendations,”in Proceedings of the 20th international conference on Information and knowledge management(CIKM), 2011.
[7] D. Helic and M. Strohmaier,”Building Directories for Social Tagging Systems,” in Proceedings of the 20th ACM international conference on Information and knowledge management(CIKM), 2011.
[8] D. Dash, J. Rao, N. Megiddo, A. Ailamaki and G. Lohman, ”Dynamic Faceted Search for Discovery-driven Analysis,” in Proceedings of the 17th conference on Information and knowledge management(CIKM), 2008.
[9] X. Ling, Q. Mei, C. X. Zhai and B. Schatz, ”Mining Multi-Faceted Overviews of Arbitrary Topics in a Text Collection,” in Proceedings of the 14th international conference on Knowledge discovery and data mining(SIGKDD), 2008.
[10] B. Zhao, X. Lin, B. Ding and J. Han, “TEXplorer: Keyword-based Object Search and Exploration in Multidimensional Text Databases,” in Proceedings of the 20th ACM international conference on Information and knowledge management(CIKM), 2011.
[11] J. Koren, Y. Zhang and X. Liu, “Personalized Interactive Faceted Search,” in Proceedings of the 17th international conference on World Wide Web(WWW), 2008.
[12] D.C. Anastasiu, B.J. Gao and D. Buttler, “A Framework for Personalized and Collaborative Clustering of Search Results” in Proceedings of the 20th ACM international conference on Information and knowledge management(CIKM), 2011.
[13] S. Overall, B. Sigurbjornsson and R. van Zwol, “Classifying Tag Using Open Content Resources,” in Proceedings of the Second ACM International Conference on Web Search and Data Mining(WSDM), 2009.
[14] C.S. Firan, M. Georgescu, W. Nejdl and R. Paiu, ”Bring Order to Your Photos: Event-Driven Classification of Flickr Images Based on Social Knowledge,” in Proceedings of the 19th ACM international conference on Information and knowledge management(CIKM), 2010.
[15] V. Dang and R.W. Croft, ” Query Reformulation Using Anchor Text,” in Proceedings of the third ACM international conference on Web search and data mining(WSDM), 2010.
[16] M. Sanderson and B. Croft, “Deriving concept hierarchies from text,” in Proceedings of the 22nd annual international ACM conference on Research and development in information retrieval(SIGIR), 1999.
[17] R. Baeza-Yates and A. Tiberi, “Extracting Semantic Relations from Query Logs, ” in Proceedings of the 13th ACM international conference on Knowledge discovery and data mining(KDD), 2007.
[18] R. Baraglia, F. Cacheda, V. Carneiro, D. Fernandez, V. Formoso, R. Perego and F. Silvestri, “Search Shortcuts: a New Approach to the Recommendation of Queries,” in Proceedings of the third ACM conference on Recommender systems(RecSys), 2009.