[Paper Review] Social Computing for Mobile Big Data in Wireless Networks

Xing Zhang, Zhenglei Yi+5 more|arXiv (Cornell University)|Sep 30, 2016

Human Mobility and Location-Based AnalysisSocial Sciences3 references17 citations

TL;DR

This paper proposes a social computing framework for analyzing mobile big data in wireless networks by leveraging spatial, temporal, and social network features. It categorizes real-world cellular network data, identifies social characteristics such as user mobility patterns and social interactions, and outlines key research directions for optimizing network planning, operation, and marketing through social computing techniques.

ABSTRACT

Mobile big data contains vast statistical features in various dimensions, including spatial, temporal, and the underlying social domain. Understanding and exploiting the features of mobile data from a social network perspective will be extremely beneficial to wireless networks, from planning, operation, and maintenance to optimization and marketing. In this paper, we categorize and analyze the big data collected from real wireless cellular networks. Then, we study the social characteristics of mobile big data and highlight several research directions for mobile big data in the social computing areas.

Motivation & Objective

• To analyze mobile big data from real wireless cellular networks through a social computing lens.
• To identify and categorize the spatial, temporal, and social dimensions of mobile data.
• To highlight underexplored research opportunities in social computing for mobile big data.
• To bridge mobile network operations with social network analysis for improved optimization and service delivery.
• To provide a foundation for future research in social-aware mobile network management and analytics.

Proposed method

• Categorizes mobile big data based on spatial, temporal, and social network dimensions.
• Applies social network analysis techniques to extract user interaction patterns from mobile data.
• Uses real-world cellular network data to identify social characteristics such as user clustering and mobility trends.
• Integrates machine learning and statistical modeling to detect social features in mobile data.
• Proposes a framework that maps mobile data features to social computing applications in wireless networks.
• Leverages data from actual network operations to validate the relevance of social computing in mobile data analysis.

Experimental results

Research questions

• RQ1 How can social computing techniques be applied to extract meaningful patterns from mobile big data in wireless networks?
• RQ2 What are the key social characteristics embedded in mobile big data from cellular networks?
• RQ3 How can social network features such as user proximity and interaction frequency improve network planning and optimization?
• RQ4 What are the most promising research directions for integrating social computing into mobile network operations?
• RQ5 In what ways can social computing enhance mobile network maintenance, marketing, and service personalization?

Key findings

• Mobile big data exhibits rich social characteristics, including user mobility patterns and social interaction trends.
• Spatial and temporal features of mobile data correlate strongly with social network structures.
• Social computing enables improved network planning by identifying high-activity user clusters and mobility hotspots.
• The integration of social computing with mobile big data supports more effective network maintenance and optimization strategies.
• The study identifies several underexplored research directions in social-aware mobile network analytics.
• The framework demonstrates potential for enhancing marketing and service personalization through social feature extraction.