臺灣博碩士論文加值系統

在人們每天的生活中，進行搜索或者使用搜索引擎工具已經成為了獲取資訊的必要手段。通過Google，Bing以及Yahoo搜索等商用產品，人們可以快速定位到自己常去的網站與服務，了解最新聞事件與探索新知。不僅如此，在社群網站Facebook，圖片為主的線上社群Instgram，以及閱讀寫作分享平台Medium等以使用者產生內容(User Generated Content, UGC）為基礎的服務之中，資訊搜尋也已是不可或缺的一個功能。然而，如何有效地輔助使用者完成搜索，滿足使用者的需求依然是一待解難題。
如何幫助使用者在他們尚不知道如何用語言去表達搜索目標時的情況下去進行搜尋依然是一個非常具有挑戰性的設計難題。進一步來說，即使使用者知道如何表達，他們花費在思考以及建構搜尋關鍵詞的過程的認知成本也是相當可觀。在這篇論文中，我們提出了Click-Search。利用Click-Search，用戶可以通過選擇和截取畫面的部分內容表達搜索目的。系統將會自動轉換被選取的圖片區塊成為關鍵詞。這一轉換工作背後是由群眾外包所構建完成的資料庫作為基礎。透過一系列的用戶研究，我們發現Click-Search能夠有效支持不同類型的資訊搜尋行為。我們討論透過與圖片互動以進行搜索這一創新互動方法的設計啟示。

Information search is a common yet important task in everyday work and life. It remains a challenging design issue how to help users search for information or things they don’t necessarily know how to express with words. Also, even when people know how to express, the cognitive cost required to retrieve the concepts and formulate the queries can be excessive. In this paper, we present Click-Search, a search user interface that allows people to indicate their search intents by merely selecting and cropping segments of image contents. The system automatically converts selected image segments to keywords based on known associations between image pixels and semantic labels created by prior crowdsourced image tagging. Through a user study, we found that Click-Search can support a range of searching activities effectively. We discuss the implications of the new approach of searching through interactions with images.

Abstract i
Table of Contents iii
Acknowledgement v
List of Figures vi
List of Tables vii
Chapter 1 Introduction 1
Chapter 2 Background: Mental Model of Cognitive Search 5
2.1. Mental Processes of Information Search 5
2.2. Query Formulation and Reformulation 6
2.3. Information Foraging as Iterative Search 7
Chapter 3 Background: Images Searching and Labelling 9
3.1. Text-based Image Retrieval and Image Tagging 9
3.2. Content-based Image Retrieval 11
3.3. Interaction-based Information Search 11
Chapter 4 Click-Search System 13
4.1. User Interaction Model – Converting needs to query 13
4.1.1. Hovering over the images 13
4.1.2. Click and cycle segments from the image 13
4.1.3. Crop segments and save for later iteration 14
4.2. User Interaction Model – Refining queries to target 15
4.2.1. Save image segments to work space 15
4.2.2. Update Tag Clouds in Scent Space 16
4.3. Prototyping 17
4.2.1. Back-end Database 17
4.2.2. Image Retrieval 18
4.2.3. System Summary 19
4.4. Evaluation Preparation 20
4.3.1. Baseline - Regular Search Interface 20
4.3.2. Participants of the evaluation 21
Chapter 5 Part 1: Finding objects search 23
5.1. Introduction 23
5.2. Experimental Design 23
5.3. Procedure 24
5.4. Measures 24
5.5. Results 25
5.5.1. Time to find objects 26
5.5.2. Amount of text queries submitted 26
5.5.3. Amount of hovering over images 27
Chapter 6 Part 2: Search-based brainstorming 28
6.1. Introduction 28
6.2. Experimental Design 28
6.3. Procedure 29
6.4. Measures 29
6.5. Results 30
Chapter 7 System Efficiency and Satisfaction 31
7.1. Participants 31
7.2. Questionnaire Description 31
7.3. Evaluation Results 32
Chapter 7 Discussion 34
8.1. Verbalize the Unverbalized, Search the Unsearchable 34
8.2. Using Images as an External Search Memory 34
8.3. Interactions with Images as Relevance Feedback 35
8.4. Diversifying Information Search 36
8.5. Limitation and Future Work 37
Chapter 9 Conclusion 38
References 39

1. André, P., Cutrell, E., Tan, D. S., & Smith, G. (2009). Designing novel image search interfaces by understanding unique characteristics and usage. InHuman-Computer Interaction–INTERACT 2009 (pp. 340-353). Springer Berlin Heidelberg.
2. Broder, A. (2002, September). A taxonomy of web search. In ACM Sigir forum (Vol. 36, No. 2, pp. 3-10). ACM.
3. Bilal, D. (2000). Children's use of the Yahooligans! Web search engine: I. Cognitive, physical, and affective behaviors on fact‐based search tasks. Journal of the American Society for information Science, 51(7), 646-665.
4. Barsalou, L. W. (1999). Perceptual symbol systems. Behavioral and brain sciences, 22(04), 577-660.
5. Bruza, P., McArthur, R., & Dennis, S. (2000, July). Interactive Internet search: keyword, directory and query reformulation mechanisms compared. In Proceedings of the 23rd annual international ACM SIGIR conference on Research and development in information retrieval (pp. 280-287). ACM.
6. Cousins, S. A. (1992). In their own words: an examination of catalogue users' subject queries. Journal of information science, 18(5), 329-341.
7. Cao, Y., Wang, H., Wang, C., Li, Z., Zhang, L., & Zhang, L. (2010, October). MindFinder: interactive sketch-based image search on millions of images. InProceedings of the international conference on Multimedia (pp. 1605-1608). ACM.
8. Datta, R., Joshi, D., Li, J., & Wang, J. Z. (2008). Image retrieval: Ideas, influences, and trends of the new age. ACM Computing Surveys (CSUR),40(2), 5.
9. Flickner, M., Sawhney, H., Niblack, W., Ashley, J., Huang, Q., Dom, B., ... & Steele, D. (1995). Query by image and video content: The QBIC system.Computer, 28(9), 23-32.
10. Fogarty, J., Tan, D., Kapoor, A., & Winder, S. (2008, April). CueFlik: interactive concept learning in image search. In Proceedings of the SIGCHI Conference on Human Factors in Computing Systems (pp. 29-38). ACM.
11. Hassan, A., White, R. W., Dumais, S. T., & Wang, Y. M. (2014, February). Struggling or exploring?: disambiguating long search sessions. InProceedings of the 7th ACM international conference on Web search and data mining (pp. 53-62). ACM.
12. Huang, A. H., Yen, D. C., & Zhang, X. (2008). Exploring the potential effects of emoticons. Information & Management, 45(7), 466-473.
13. He, K., Zhang, X., Ren, S., & Sun, J. (2015). Delving deep into rectifiers: Surpassing human-level performance on imagenet classification. arXiv preprint arXiv:1502.01852.
14. Hearst, M. (2009). Search user interfaces. Cambridge University Press.
15. Jansen, B. J., Spink, A., & Koshman, S. (2007). Web searcher interaction with the Dogpile. com metasearch engine. Journal of the American Society for Information Science and Technology, 58(5), 744-755.
16. Joachims, T. (2002, July). Optimizing search engines using clickthrough data. In Proceedings of the eighth ACM SIGKDD international conference on Knowledge discovery and data mining (pp. 133-142). ACM.
17. Kellar, M., Watters, C., & Shepherd, M. (2006). A goal‐based classification of web information tasks. Proceedings of the American Society for Information Science and Technology, 43(1), 1-22.
18. Lynch, C. A. (1992). The next generation of public access information retrieval systems for research libraries: lessons from ten years of the MELVYL system. Information technology and libraries, 11(4), 405.
19. Lin, J., DiCuccio, M., Grigoryan, V., & Wilbur, W. J. (2008). Navigating information spaces: A case study of related article search in PubMed.Information Processing & Management, 44(5), 1771-1783.
20. Mitra, M., Singhal, A., & Buckley, C. (1998, August). Improving automatic query expansion. In Proceedings of the 21st annual international ACM SIGIR conference on Research and development in information retrieval (pp. 206-214). ACM.
21. Perlman, G. A. R. Y. (2009). User interface usability evaluation with web-based questionnaires. Retrieved February, 20, 2010.
22. Pollock, A., & Hockley, A. (1997). What''s Wrong with Internet Searching.
23. Pirolli, P., & Card, S. K. (1998, May). Information foraging models of browsers for very large document spaces. In Proceedings of the working conference on Advanced visual interfaces (pp. 83-93). ACM.
24. Pirolli, P., & Card, S. (1999). Information foraging. Psychological review,106(4), 643.
25. Rui, Y., Huang, T. S., & Mehrotra, S. (1997, October). Content-based image retrieval with relevance feedback in MARS. In Image Processing, 1997. Proceedings., International Conference on (Vol. 2, pp. 815-818). IEEE.
26. Srinagesh, A., Varma, G. S., Thota, L., & Govardhan, A. User-Based Interaction for Content-Based Image Retrieval by Mining User Navigation Patterns.
27. Shneiderman, B., Byrd, D., & Croft, W. B. (1997). Clarifying search: A user-interface framework for text searches. D-lib magazine, 3(1), 18-20.
28. Salton, G., Wong, A., & Yang, C. S. (1975). A vector space model for automatic indexing. Communications of the ACM, 18(11), 613-620.
29. Salton, G., & Buckley, C. (1997). Improving retrieval performance by relevance feedback. Readings in information retrieval, 24(5), 355-363.
30. Taylor, R. S. (1962). The process of asking questions. American documentation, 13(4), 391-396.
31. Taylor, R. S. (1968). Question-negotiation and information seeking in libraries. College & research libraries, 29(3), 178-194.
32. Von Ahn, L., & Dabbish, L. (2004, April). Labeling images with a computer game. In Proceedings of the SIGCHI conference on Human factors in computing systems (pp. 319-326). ACM.
33. Von Ahn, L., Liu, R., & Blum, M. (2006, April). Peekaboom: a game for locating objects in images. In Proceedings of the SIGCHI conference on Human Factors in computing systems (pp. 55-64). ACM.
34. Xia, D., Fu, P., Huang, C., & Wang, Y. (2009, September). Trend of Content-Based Image Retrieval on the Internet. In Image and Graphics, 2009. ICIG'09. Fifth International Conference on (pp. 733-738). IEEE.