Time-weighted Social Network: Predict when an item will meet a collector

Abstract

“For what else is this collection but a disorder to which habit has accommodated itself to such an extent that it can appear as order?”. Unpacking his library, Walter Benjamin describes how a collection is singular [2]. Collections are not unified wholes, but rather chains of undefined objects. Classify, search, arrange or browse collections are personal processes influenced by internal reflexions. Working on figural and non-figural collections, Piaget and Inhelder explain how space and time influence the way a collector looks to his collection [13]. As a result, representing collections is an issue for computer scientists. Here, we propose a time-based method, which consideres chronological events and draws a time-weighted graph defining patterns of items. We therefore show how this graph outputs different results depending on when it is requested. This work is based on an architecture, designed by Openrendezvous.com, a collaborative web-based application helping to make appointments. Our goal is to adapt a social graph used to define the perfect moment for two people to meet, to the collection case. We discuss how we can build a structure that helps to compute the ideal moment for an item to meet a collector.