Optimizing Seed Set for New User Cold Start

Wang, He-Da; Wu, Ji

doi:10.1109/ssci.2015.140

Search citation statements

Order By: Relevance

Paper Sections

Select...

Citation Types

Supporting

Mentioning

Contrasting

Year Published

2017

Publication Types

Select...

Book1

Article1

Relationship

Self Cite0

Independent2

Authors

Journals

Cited by 2 publications

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

A Review of Personal Profile Features in Personalized Learning Systems

Lapointe

Kondratova

Molyneaux

et al. 2017

Advances in Intelligent Systems and Computing

View full text Add to dashboard Cite

This paper reviews literature, market reports and commercial sites in order to identify features of personal profiles. This is a preparatory step in the development of a personalized learning environment. Results indicate that several features can be included as long as they relate to use cases. We also found that privacy concerns might arise when dealing with personal profiles and measures should be taken to ensure compliance with policies and legislation on the topic and to avoid the risk of alienating users.

show abstract

A Review of Personal Profile Features in Personalized Learning Systems

Lapointe

Kondratova

Molyneaux

et al. 2017

Advances in Intelligent Systems and Computing

View full text Add to dashboard Cite

show abstract

Multi-Criteria Recommender Systems

Hdioud

Frikh

Ouhbi

et al. 2017

International Journal of Mobile Computing and Multimedia Communications

View full text Add to dashboard Cite

A Recommender System (RS) works much better for users when it has more information. In Collaborative Filtering, where users' preferences are expressed as ratings, the more ratings elicited, the more accurate the recommendations. New users present a big challenge for a RS, which has to providing content fitting their preferences. Generally speaking, such problems are tackled by applying Active Learning (AL) strategies that consist on a brief interview with the new user, during which she is asked to give feedback about a set selected items. This article presents a comprehensive study of the most important techniques used to handle this issue focusing on AL techniques. The authors then propose a novel item selection approach, based on Multi-Criteria ratings and a method of computing weights of criteria inspired by a multi-criteria decision making approach. This selection method is deployed to learn new users' profiles, to identify the reasons behind which items are deemed to be relevant compared to the rest items in the dataset.

show abstract

Optimizing Seed Set for New User Cold Start

Cited by 2 publications

References 11 publications

A Review of Personal Profile Features in Personalized Learning Systems

A Review of Personal Profile Features in Personalized Learning Systems

Multi-Criteria Recommender Systems

Contact Info

Product

Resources

About