Maximizing acceptance probability for active friending in online social networks

Abstract

Friending recommendation has successfully contributed to the explosive growth of on-line social networks. Most friending recommendation services today aim to support passive friending, where a user passively selects friending targets from the recommended candidates. In this paper, we advocate recommendation support for active friending, where a user actively specifies a friending target. To the best of our knowledge, a recommendation designed to provide guidance for a user to systematically approach his friending target, has not been explored in existing on-line social networking services. To maximize the probability that the friending target would accept an invitation from the user, we formulate a new optimization problem, namely, Acceptance Probability Maximization (APM), and develop a polynomial time algorithm, called Selective Invitation with Tree and In-Node Aggregation (SITINA), to find the optimal solution. We implement an active friending service with SITINA in Facebook to validate our idea. Our user study and experimental results manifest that SITINA outperforms manual selection and the baseline approach in solution quality efficiently.

Privacy Analysis of Comment Using Text Mining in Osn Framework

“…Accordingly [15], by methods for a BL control, divider proprietors are for instance ready to restriction from their dividers, clients they don't straightforwardly know (i.e., with which they have just aberrant connections), or clients that are companion of a given individual as they may have a terrible supposition of this individual. This forbidding can be received for an undetermined day and age or for a particular time window.…”

“…as an example, a gadget mastering device inside the email Inbox can be utilized to examine and understand the messages got inside the inbox among unsolicited mail or nonjunk mail messages. [15] basically the machine studying here follows the posted messages for the brilliant and the illicit phrases applied as part of the divider by way of the general population customers. He can post any message there without the separating system.…”

Locally Adaptive Optimization: Adaptive Seeding for Monotone Submodular Functions

“…In these models the algorithm has access to the entire network but has the freedom to choose one node at a time (or group of nodes) and observe the realized value of these nodes. Yang et al [43] and Chen et al [9] also study "multi-level" models of the influence maximization problem, the latter partially inspired by the adaptive seeding model. However, their motivation, model and benchmark are substantially different from the adaptive seeding model, and apart from some special cases, their models do not have any constant factor approximations.…”

Friend recommendation with a target user in social networking services

“…Lo et al [10] developed a topology-based model to estimate relationship strength by exploiting real message interaction and Armentano et al [11] developed an unsupervised model in a Twitter environment to identify users who can be considered as good information sources. Yang et al [12] suggested an active friending concept and developed an algorithm to maximize acceptance probability.…”