Details

Project TitleConstrained Question Recommendation Algorithm
Track Code2014-222
Short DescriptionIn contrast to traditional product recommendation, question recommendation in discussion forums should simultaneously consider constraints on both students and questions. These considerations include
AbstractIn contrast to traditional product recommendation, question recommendation in discussion forums should simultaneously consider constraints on both students and questions. These considerations include (1) Load Balancing - students should not be over-burdened with too many requests; and (2) Expertise Matching - matching students' abilities to the difficulty of unanswered questions, which in turn positions students to contribute meaningfully to the forum. In this work, we have proposed, implemented, and evaluated a novel constrained question recommendation approach to address the above considerations. In particular, from a technical perspective, we designed a context-aware matrix factorization model to predict students' preferences over questions and then built a max cost flow model to manage the constraints. This package can be integrated with online discussion forums to ask as 'just in time' support for productive community interactions within those forums. https://libraries.io/github/DANCEcollaborative/social_recommendation
 
Tagsmatrix factorization, online discussion facilitation, recommender system
 
Posted DateJan 3, 2017 11:32 AM

Researcher

Name
Carolyn Rose
Diyi Yang

Manager

Name
Cindy Chepanoske