A recommendation system for scientific water data

Abstract

Thesis defense:

Recommendation systems have become a powerful feature for many online systems, including electronic commerce, video or music applications, news websites, etc. Most current recommendation systems are designed for increasing user satisfaction during use of media services. Recommendation systems for scientific data are targeted at data reuse and scientific progress. A recommendation system for scientific water data must handle scientific users’ multiple-interests behavior and objects with really large and complex sets of attributes. The context of this work is to establish a combination of the content-based filtering algorithm for hydrologic data and a Latent Dirichlet Allocation (LDA) topic modeling of user behavior on the HydroShare platform for water data sharing. The process for making scientific water data recommendations includes inferring users’ multiple-interests from the datasets with which they interact, and then calculating similarity between users’ interests set and datasets’ keywords. Evaluating such a system requires comparing objects’ keywords that are recommended with the datasets that users have already shown interest in using. Compared recommendations made by this approach with other well-known recommendation algorithms, we conclude that the combination of the content-based filtering and the LDA algorithm provides a workable solution for HydroShare.

Join the meeting in Sococo, VH 102, or Zoom.

Join Zoom Meeting: https://tufts.zoom.us/j/98610939077

PASSWORD: See colloquia email

Dial by your location: +1 646 558 8656 US (New York)

Meeting ID: 986 1093 9077

PASSCODE: See colloquia email