9%)! Refined Threshold! Global Red Weight! Index Red Weight! (b) ,
9%)! Refined Threshold! Global Red Weight! Index Red Weight! (c) ,
9%)! Refined Threshold! Global Red Weight! Index Red Weight! (e) 0! 50! 100! 150! 200! 250! Average Response Time (ms)! ,
9%)! Refined Threshold! Global Red Weight! Index Red Weight! (f) 0! ,
9%)! Refined Threshold! Global Red Weight! Index Red Weight! (g) 0! 100 ,
9%)! Refined Threshold! Global Red Weight! Index Red Weight! (a), Average Response Time, vol.99 ,
Refined Threshold! Global Red Weight! Index Red Weight! (b) ,
9%)! Refined Threshold! Global Red Weight! Index Red Weight! (c) ,
9%)! Refined Threshold! Global Red Weight! Index Red Weight! (e), Average Response Time, vol.99 ,
Refined Threshold! Global Red Weight! Index Red Weight! (f), Average Response Time, vol.99 ,
9%)! Refined Threshold! Global Red Weight! Index Red Weight! (g) ,
Refined Threshold! Global Red Weight! Index Red Weight! (i) ,
Refined Threshold! Global Red Weight! Index Red Weight! (j) ,
9%)! Refined Threshold! Global Red Weight! Index Red Weight! (k) ,
Refined Threshold! Global Red Weight! Index Red Weight! References Amer-Yahia, It Takes Variety to Make a World: Diversification in Recommender Systems, pp.368-378, 2009. ,
Getting recommender systems to think outside the box, Proceedings of the third ACM conference on Recommender systems, RecSys '09, 2009. ,
DOI : 10.1145/1639714.1639769
Improving recommendation lists through topic diversifi- 570 cation, WWW '05, pp.22-32, 2005. ,
Amer-Yahia, Real-time recommendation of diverse related articles, pp.1-11, 2013. ,
Content-based recommendation systems, The adaptive web, pp.325-341, 2007. ,
Using collaborative filtering to weave an information tapestry, Communications of the ACM, vol.35, issue.12 ,
DOI : 10.1145/138859.138867
Introduction to Information Retrieval, 2008. ,
DOI : 10.1017/CBO9780511809071
A vector space model for automatic indexing, Communications of the ACM, vol.18, issue.11 ,
DOI : 10.1145/361219.361220
Diversifying search results, Proceedings of the Second ACM International Conference on Web Search and Data Mining, WSDM '09, pp.5-14, 2009. ,
DOI : 10.1145/1498759.1498766
Efficient Diversity-Aware Search Less is More: Probabilistic Models for Retrieving Fewer Relevant Documents, pp.781-792, 2006. ,
Improving Diversity in Ranking using Absorbing Random Walks, HLT-NAACL '05, pp.97-104, 2005. ,
An axiomatic approach for result diversification, Proceedings of the 18th international conference on World wide web, WWW '09, pp.381-390, 2009. ,
DOI : 10.1145/1526709.1526761
Socialscope: Enabling information discovery on social content sites, pp.1-1, 2009. ,
Efficient network aware search in collaborative tagging sites, VLDB Endowment, pp.710-721, 2008. ,
The influence of the sigmoid function parameters on the speed of backpropagation learning, From Natural to Artificial Neural Computation Lecture Notes in Computer Science, vol.930, pp.195-201, 1995. ,
DOI : 10.1007/3-540-59497-3_175
Sampling search-engine results, Proceedings of the 14th international conference on World Wide Web , WWW '05, pp.600-245, 2005. ,
DOI : 10.1145/1060745.1060784
Amer-Yahia, Efficient Computation of Diverse Query Results, ICDE '08, pp.228-236, 2008. ,
Addressing diverse user preferences in SQL-query-result navigation, Proceedings of the 2007 ACM SIGMOD international conference on Management of data , SIGMOD '07, pp.641-652, 2007. ,
DOI : 10.1145/1247480.1247551
Efficient Online Computation of Diverse Query Results ,
Turning down the noise in the blogosphere, Proceedings of the 15th ACM SIGKDD international conference on Knowledge discovery and data mining, KDD '09, pp.289-298, 2009. ,
DOI : 10.1145/1557019.1557056
New Stochastic Algorithms for Scheduling Ads in Sponsored Search, 2007 Latin American Web Conference (LA-WEB 2007), pp.22-31, 2007. ,
DOI : 10.1109/LA-Web.2007.26
DisC diversity, Proceedings of the VLDB Endowment, vol.6, issue.1, pp.13-25, 2013. ,
DOI : 10.14778/2428536.2428538
Adaptive Diversity Loss Analysis In this section, we analyze the quality and performance of the adaptive approach. Section AppendixA ,