Willingness optimization for social group activity

Abstract

Studies show that a person is willing to join a social group activity if the activity is interesting, and if some close friends also join the activity as companions. The literature has demonstrated that the interests of a person and the social tightness among friends can be effectively derived and mined from social networking websites. However, even with the above two kinds of information widely available, social group activities still need to be coordinated manually, and the process is tedious and time-consuming for users, especially for a large social group activity, due to complications of social connectivity and the diversity of possible interests among friends. To address the above important need, this paper proposes to automatically select and recommend potential attendees of a social group activity, which could be very useful for social networking websites as a value-added service. We first formulate a new problem, named Willingness mAximization for Social grOup (WASO). This paper points out that the solution obtained by a greedy algorithm is likely to be trapped in a local optimal solution. Thus, we design a new randomized algorithm to effectively and efficiently solve the problem. Given the available computational budgets, the proposed algorithm is able to optimally allocate the resources and find a solution with an approximation ratio. We implement the proposed algorithm in Facebook, and the user study demonstrates that social groups obtained by the proposed algorithm significantly outperform the solutions manually configured by users.

Maximizing Friend-Making Likelihood for Social Activity Organization

“…Each user, given 12 test cases of HMGF using her friends in Facebook as the input graph, is asked to solve the HMGF cases, and compare her results with the solutions obtained by MaxGF. In addition to the user study, we evaluate the performance of MaxGF on two real social network datasets, i.e., FB [15] MS dataset from KDD Cup 2013 8 . The FB dataset is extracted from Facebook with 90K vertices, and MS is a co-author network with 1.7M vertices.…”

“…Research on finding a set of attendees for activities based on the social tightness among existing friends [5,6,7,8,9] have been reported in the literature. Social-Temporal Group Query [5] checks the available times of attendees to find the social cohesive group with the most suitable activity time.…”

“…Geo-Social Group Query [6,7] extracts socially tight groups while considering certain spatial properties. The willingness optimization for social group problem in [8] selects a set of attendees for an activity while maximizing their willingness to participate. Finally, [9] finds a set of compatible members with tight social relationships in the collaboration network.…”

“…However, there is a gap between existing activity organization and friend recommendation services in OSNs for the scenarios under consideration. Existing activity organization approaches focus on extracting socially cohesive groups from OSNs based on certain cohesive measures, density, diameter, of social networks or other constraints, e.g., time, spatial distance, and interests, of participants [5,6,7,8]. On the other hand, friend recommendation services consider only the existing friendships to recommend potential new friends for an individual (rather than finding a group of people for engaging friend-making).…”

Scale-Adaptive Group Optimization for Social Activity Planning

“…3, the cumulative distribution function is shifted by C(k) when we incorporate the operation cost, and it thus still follows the same distribution. Assume that d j,l> c i,k , the probability that the solution generated from the start node v i with size k is better than the solution generated from the start node v j with size l, i.e., P (Q * i,k ≤ Q * j,l ), can be derived according to [15] as follows.…”