A Particle Swarm Optimization Based Approach for Finding Similar Users on Facebook

@article{Kabara2016APS,
  title={A Particle Swarm Optimization Based Approach for Finding Similar Users on Facebook},
  author={Pratik S. Kabara and Vishal Kaushal and Akshay Divekar and Mohit Kamdar and Devvrat Ganeriwal},
  journal={J. Comput.},
  year={2016},
  volume={11},
  pages={18-25}
}
With ever increasing size and use of social networks, there is a large amount of information which users implicitly or explicitly leave behind on social media. This information can be used to identify their personal traits and preferences. In this work, we have proposed a Particle Swarm Optimization (PSO) based approach for clustering users on Facebook (FB) data to identify similar users. Proposed method can be used to recommend people having similar interests. Our results indicate a lesser… 

Figures and Tables from this paper

Study on Application of PSO with Time Window for User Recommendation in Research Social Networks

TLDR
The empirical experiment indicated that this integrated algorithm could identify the similar user accurately, and it's valuable in practice.

A Scientometric Analysis of Transient Patterns in Recommender System with Soft Computing Techniques

TLDR
First of its kind scientometric analysis on “recommender system with soft computing techniques” is presented, providing useful parameters for establishing relationships between quantifiable data and intangible contributions in the field of recommender systems.

References

SHOWING 1-10 OF 23 REFERENCES

Finding Similar Users in Facebook

TLDR
This chapter proposes an approach in order to estimate the similarity of two users based on the knowledge of social ties existing among users, and the analysis of activities in which users are involved, by applying the Katz coefficient.

Social Networks : Finding Highly Similar Users and Their Inherent Patterns

TLDR
A means for finding “clones” within a large, sparse social graph is explored, and the findings that concern patterns of shared interests are presented, and how this correlates with connectivity and degrees of separation is explored.

Data clustering using particle swarm optimization

TLDR
This paper proposes two new approaches to using PSO to cluster data, one which basically usesPSO to refine the clusters formed by K-means, and the other which uses PSO in a different way to seed the initial swarm.

Editorial survey: swarm intelligence for data mining

TLDR
This paper surveys the intersection of two fascinating and increasingly popular domains: swarm intelligence and data mining, and provides a unifying framework that categorizes the swarm intelligence based data mining algorithms into two approaches: effective search and data organizing.

Characterizing user behavior in online social networks

TLDR
A first of a kind analysis of user workloads in online social networks, based on detailed clickstream data collected over a 12-day period, shows that browsing, which cannot be inferred from crawling publicly available data, accounts for 92% of all user activities.

Particle swarm optimizer for variable weighting in clustering high-dimensional data

TLDR
A particle swarm optimizer (PSO) to solve the variable weighting problem in projected clustering of high-dimensional data and shows that the proposed algorithm greatly improves cluster quality and is much less dependent on the initial cluster centroids.

Finding similar users using category-based location history

TLDR
The approach first models a user's GPS trajectories with a semantic location history (SLH) and measures the similarity between different users' SLHs by using the maximal travel match (MTM) algorithm, which outperforms the related works.

Measurement and analysis of online social networks

TLDR
This paper examines data gathered from four popular online social networks: Flickr, YouTube, LiveJournal, and Orkut, and reports that the indegree of user nodes tends to match the outdegree; the networks contain a densely connected core of high-degree nodes; and that this core links small groups of strongly clustered, low-degree node at the fringes of the network.

Social Networking and Community Behavior Modeling: Qualitative and Quantitative Measures

TLDR
Critical security issues confronting social networking, the emergence of new mobile social networking devices and applications, network robustness, and how social networks impact the business aspects of organizations are studied.

An experiential, social network‐based approach to direct marketing

Purpose – Direct marketing faces challenges and opportunities associated with the emergence of social network media. Companies need to address target audiences both directly and also indirectly