Enhanced Recommendation System in Community–Question-Answering Websites using Splay-Tree Methodology
Jayashree R, Department of Computer Applications, Faculty of Science and Humanities, SRM Institute of Science and Technology, Chennai, India.
Manuscript received on October 01, 2019. | Revised Manuscript received on October 15, 2019. | Manuscript published on October 30, 2019. | PP: 1305-1310 | Volume-9 Issue-1, October 2019. | Retrieval Number: A9643109119/2019©BEIESP | DOI: 10.35940/ijeat.A9643.109119
Open Access | Ethics and Policies | Cite | Mendeley
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: In community-driven ranking systems participants with superior scores acquire strong reputation than low scored participants. The community-question-aswering websites, like stack exchange network, participants with unreciprocated or unnoticed questions for a long time get a badge called tumbleweed without taking into account of their earlier period performance. The user-driven question and answering website considers this reward as a consolation prize and discourages them instead of encouraging. Mostly, the users who ask unnoticed questions are either a new or less scored participants. The center of attention of this research work is to propose a recommendation system that prevents unnoticed questions from the participants who are about to receive a tumbleweed badge. A splay-tree is a tree with a self-balancing ability which brings the newly accessed node to the apex of the tree. In this paper, the splay-tree correspond to participants’ ranks and the highlight of the work is to raise average or beneath average scorer to apex without disturbing existing toppers.
Keywords: Community Question Answering, Ranking System, Splay and Semi-Splay-tree, Long Tail Problem, Collaborative Learning.