2015/03/12 by Zeon Trevor Fernando, Fernando, Zeon Trevor
Computer Science · #Video Analysis and Summarization #Advanced Image and Video Retrieval Techniques #Image Retrieval and Classification Techniques
paper · pdf · doi:10.48550/arxiv.1503.03660
In Social Science research, multimedia documents are often collected to\nanswer particular research questions like: "Which of the aesthetic properties\nof a photo are considered important on the web" or "How has Street Art\ndeveloped over the past 50 years". Therefore, a researcher generally issues\nmultiple queries to a number of search engines. This activity may span over\nlong time intervals and results in a collection which can be further analyzed.\nDocumenting the collection building process which includes the context of the\ncarried out searches is imperative for social scientists to reproduce their\nresearch. Such context documentation consists of several user actions and\nsearch attributes like: the issued queries; the results clicked and saved;\nduration a particular result was viewed for; the set of results that was\ndisplayed but neither clicked, nor saved; as well as user annotations like\ncomments or tags. In this work we will describe a search process tracking\nmodule and a search history visualization module. These modules can be\nintegrated into keyword based search systems through a REST API which was\ndeveloped to help capture, document and revisit past search contexts while\nbuilding a web corpora. Finally, we detail the implementation of how the module\nwas integrated into the LearnWeb2.0 platform - a multimedia web2.0 search and\nsharing application which can obtain resources from various web2.0 tools such\nas Youtube, Bing, Flickr, etc using keyword search.\n