CourseRank is a course planning tool aimed at helping students at Stanford. Recommendations comprise an integral part of the system. However, implementing existing recommendation methods leads to fixed, pre-specified recommendations that cannot adapt to each particular student's changing requirements and do not help exploit the full extent of the available learning opportunities at the university. In this paper, we describe the concept of a flexible recommendation workflow, i.e., a high-level description of a parameterized process for computing recommendations. The input parameters of a flexible recommendation process comprise the "knobs" that control the final output and hence support flexible recommendations. We describe how flexible recommendations can be expressed over a relational database and we present our prototype system that allows defining and executing different, fully-parameterized, recommendation workflows over relational data. Finally, we describe a user interface in CourseRank that allows students to make use of two flexible recommendation workflows.
Social sites such as FaceBook, Orkut, Flickr, MySpace and many others have become immensely popular. At these sites, users share their resources (e.g., photos, profiles, blogs) and learn from each other. On the other hand, higher education applications help students and administrators track and manage academic information such as grades, course evaluations and enrollments. Despite the importance of both these areas, there is relatively little research on the mechanisms that make them effective. Apart from being both a successful social site and an academic planning site, CourseRank provides a live testbed for studying fundamental questions related to social networking, academic planning, and the fusion of these areas. In this paper, we provide a system overview and our main research efforts through CourseRank.
Abstract-Most recommendation methods are 'hard-wired' into the system and they support only fixed recommendations. The purpose of this demo is to show the expressivity of flexible recommendation workflows, how flexible recommendations can be efficiently processed over relational data, and to show flexible recommendations in action through a real system used for course planning.
Recommendation systems have become very popular but most recommendation methods are 'hard-wired' into the system making experimentation with and implementation of new recommendation paradigms cumbersome. In this paper, we propose FlexRecs, a framework that decouples the definition of a recommendation process from its execution and supports flexible recommendations over structured data. In FlexRecs, a recommendation approach can be defined declaratively as a high-level parameterized workflow comprising traditional relational operators and new operators that generate or combine recommendations. We describe a prototype flexible recommendation engine that realizes the proposed framework and we present example workflows and experimental results that show its potential for capturing multiple, existing or novel, recommendations easily and having a flexible recommendation system that combines extensibility with reasonable performance.
No abstract
No abstract
Social sites are extremely popular among users but user interactions in most sites revolve around relatively simple tasks, such as uploading resources, tagging and poking friends. We believe that social sites can go beyond simple interactions among individuals and offer valuable services to well-defined, closed, communities (e.g., an academic, corporate or scientific community). In this paper, we present an example of a closed-community social system, CourseRank, an educational and social site where Stanford students can explore course offerings and plan their academic program. We perform an analysis of 12 months worth of CourseRank data including user contributed information, such as ratings and comments, as well as information extracted from the user logs, and we analyze several aspects of user interactions and user-contributed content in the site, such as activity levels, user behavior and user content quality. Our findings provide useful insights with respect to the potential of closed-community social sites.
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.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.