scholar papers recommender system based on context information using hadoop platform

scholar papers recommender system based on context information using hadoop platform

Nasrin Jokar1 Alireza Honarvar2 Khadija Esfandiari3

1) Iran University of Azad Email:
2) Iran University of Azad Email:
3) Iran University of Azad Email:

IOI Code : XYCZ-AAGAK
Publication : International Conference on Engineering and Applied Science(iceasconf.com)
Abstract :
    Recommender Systems have become popular for scholar papers. Over the past 14 years, more than 170 scholar papers, registered inventions, web pages and other things in this context have been published. Recommender system papers, by using context information, are trying to recommends users suggestions which are comply with the user personal desires and the systems do it based on performance, personal tastes and user behavior and depending on the context in which they are used. Since volume of articles is increasing day by day and recommender systems are not able to cover such a big volume for the processing papers according to user preferences. For this reason to cover and process this volume of papers, parallel processing [mapping-reduction programming] is needed. This research suggested systems at first create profile which is containing context information and the scope of the papers, then the systems will suggest the users some papers according to working range and range of papers. Since the range of data used is part of a big data and in this study time is an important factor, so A hadoop platform and parallel programming for system implementation has been used. The proposed system performance were evaluated based on criteria including user satisfaction and accuracy and that has yielded satisfactory results.

Keywords : recommender system big data hadoop context information