Online news sites are some of the most useful and popular information retrieval systems in use today. Thousands of articles in different languages and on a variety of subjects are posted every day and updated every hour. Most articles are uninteresting and unimportant to a particular individual, and individuals may not want to review entire websites for stories of interest. Systems have been developed that provide summaries from online news websites but finding a means to rapidly scan stories of potential interest remains an open problem. In this thesis, we introduce a novel visualization system that uses geographical location combined with image collages and tag clouds to provide a tool for rapidly reviewing news stories. Tag clouds are arrangements of tags with the most important tags allocated a bigger font size or otherwise more prominent visual properties; and image collages provide a compact, effective and attractive representation for photos on one page. Bringing these media representations together over a geographic map offers a new style of interaction for online news browsing. The usability of our application was evaluated with two user studies. We aimed to determine how best to configure our visualization to communicate more information in less time to users than traditional feed-based news aggregators. We were particularly interested in knowing whether users interpret text/image size and placement as indications of a news item’s prominence. We also wanted to establish whether users understand the semantic relationship between zoom level on the map and the regional relevance (municipal, provincial, national) of news items displayed at that zoom level. The results of user feedback and data analysis (e.g., eye tracking logs) were examined to improve the usability of the system. Data analysis from the second user study suggests that, in general, the system is highly effective in helping users achieve an immediate and effortless bird’s-eye-view of news summaries within a large geographic region. However, users had varying opinions about the level of detail in the user interface (e.g., the number of images).

This paper describes the way to realization such an application, where a user chooses a photo database to working with and enters a photo into the system. The system using a visual vocabulary finds the most similar photos from the database and offers tags of the searched photo with a suitable form based on the tag statistical analysis of this photo.