Examples are very important in design, but existing tools for design examples search still do not cover many cases. Long tail queries containing subtle and subjective design concepts, like "calm and quiet", "elegant", "dark background with a hint of color to make it less boring", are poorly supported. It is due to the inherent complexity of the task, which so far has been tackled only algorithmically using general image search techniques. We propose an approach for design examples search based on crowdsourcing. Out of many explored crowdsourcing configurations we found that (1) a design need should be represented via three query images, (2) crowd workers should assess the query-specific relevance of candidate examples from a pre-built design collection, and (3) a crowd task should contain verification questions about a design need to control quality. To test the utility of our approach, we compared it with Google Images in a queryby-example mode. Based on feedback from expert designers, the crowd selects more relevant and diverse design examples.
ABSTRACT:In this paper we present a pageintegrated tool for collecting feedback for online UC-WISE course content on the Moodle Virtual Learning Environment. First, we discuss previously employed methods that include a endof-semester in-browser survey and in-person student surveys, each of which has significant limitations. The feedback tool's defining advantage is: 1) its availability on all course elements within an online curriculum (yielding feedback data with greater granularity); and 2) a deep integration with the web portal to deliver analytical tools to instructors. Next, we present the design goals we set for this tool and the features that were developed to realize those goals. Following this is an explanation of the entire development cycle, the structure of the code base, and subsequent improvements on each iteration. Lastly, we map out steps for improving the tool further.
Movie recommendation systems are now becoming very popular both commercially and also in the research community, where many approaches have been proposed for providing recommendations. For more and more usage of any system, it is necessary to know about the efficiency of the system and for this reason performance evaluation of a Recommendation system is done. By doing the performance evaluation of a system, one can prove the potential of a recommendation system. The more high performance a system gives more is its worth as compared to others. And, on this basis we can get to know further research and improvement options for a system which gives rise to new advancements in the field. Indeed, movie recommendation systems have a number of properties that may affect user's experience, such as accuracy, quality, robustness, scalability, and so forth. In this paper, various important performance evaluation metrics are reviewed and discussed.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
customersupport@researchsolutions.com
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.