There has been an increasing shift away from traditions of individual based scientific research toward more collaborative models via scientific online communities. The internet/cyberinfrastructure techniques connect computers, data storage systems, data repositories and researchers together to improve research productivity and enable scientific breakthroughs. One famous example of scientific online communities is nanoHUB.org created by Network for Computational Nanotechnology (NCN). nanoHUB has been well received and has attracted more than 90,000 active users from 172 countries all over the world by providing thousands of resources such as simulation tools, teaching materials and publications. nanoHUB is powered by the HUBzero software developed by researchers at Purdue University. The HUBzero platform has been utilized to support more than a dozen of online communities in different scientific disciplines.
The rapid growth of information (i.e., resources) in scientific online communities demands intelligent information agents that can identify the most valuable to the users, which are very important for the success of the communities. Although valuable prior research of information recommendation has been conducted for applications such as collaborative filtering for movie recommendation and content-based filtering for research paper recommendation, existing solutions are not adequate for online scientific communities. For example, users in online scientific communities undertake different types of tasks (e.g., seeking teaching materials or conducting experiments for dissertation work) and require recommendation that distinguishes different tasks, which is not provided by existing recommendation solutions. Furthermore, a substantial amount of information from users of online scientific communities is implicit feedback (e.g., clickthrough data). However, most existing recommendation solutions focus on explicit feedback information (e.g., user ratings of movies).
Intellectual Merit: The proposed research seeks to overcome the limitations of existing recommendation solutions by proposing a new Integrated Information Recommendation Framework for online scientific communities. The proposed framework differs from existing solutions in several major aspects: (1) It analyzes the task undertaken by a user and recommends most relevant resources to the user for accomplishing the task; (2) It carefully models implicit feedback information from users without making too strong assumptions. In particular, The proposed research thrusts include: (1) Task-Specific Recommendation: estimate possible tasks undertaken and incorporate the estimation results into the process of making recommendation; (2) Intelligent Hybrid Recommendation: integrate collaborative filtering/recommendation and content-based filtering/recommendation techniques within a single model that intelligently tunes the weights of content based information and collaborative usage information; (3) Pairwise Comparison Approach for Implicit Feedback: model usersí implicit feedback information of recommended resources in a probabilistic model with a natural assumption of pairwise comparison; (4) System Development and Evaluation: build and integrate proposed algorithms into the HUBzero platform. The research results will be evaluated in carefully designed user studies as well as in real world operational environments (i.e., nanoHUB). The proposed research will be based on the PIsí extensive prior experience in designing recommendation systems and building software for online scientific communities.
Broader Impacts: The proposed research will yield substantial benefits in broad areas. (1) The information recommendation tool will be incorporated into nanoHUB to benefit a large number of users. The tool will be released with HUBzero platform and can be adapted and applied to many other important online scientific communities to foster research and discovery in different disciplines; (2) The source code of proposed algorithms will be released with the HUBzero platform to enable further advance and development in information recommendation; (3) The proposed information recommendation solutions can be adapted and used in other general purpose social network applications like facebook; (4) Some research topics will be integrated into the courses that the PIs teach. The PIs will also encourage the involvement of underrepresented students in the research project.