Exploring The Choice Under Conflict For Social Event Participation

Recent years have witnessed the booming of location based social network services(LBSNs),especially for the offline social evenits organization platforms,which allow cy-ber strangers to get connected in physical world.This new business model imposes new challenges for event organizers to draw the event plan and predict the attendance.Intu-itively,these services rely on the accurate estimation of users' preferences.However,due to the various motivation of historical participation,i.e.,attendance may not defi-nitely indicate interests,traditional recommender techniques which focus on analyzing users' behaviors records may fail to reveal the reliable user profiles.At the same time,motivated by the phenomenon that when someone is facing to the conflict of invitation,i.e.,only a part could be accepted while the rest should be absent,the choices may reflect users' real preference.Thus,we realize that precise modeling of these Conflict-Choice Triples will be beneficial to understand users.Along this line,in this paper,we develop a novel conflict-choice-based model to re-construct the decision-making process of users when facing to conflict.To be specific,in the perspective of utility in choice model,we formulate users' tendency with inte-grating content-based,social-based preferences and cost-based preferences,thus their topical interests as well as latent social interactions could be both captured.Further-more,we transfer the choice of conflict-choice triples into the pairwise ranking task,thus a learning-to-rank based optimization scheme is introduced to solve the problem.Comprehensive experiments on real-world data set show that our framework could out-perform the state-of-the-art baselines with significant margin,and related discussion on social network pruning based on social structure metrics could further ensure the computational efficiency,which validates the hypothesis that conflict and choice could better explain user's real preference,while confirm the potential of our framework on social event participation analysis.