Social Media Analysis

With merely more than a decade since its birth, social media has become a huge area of our socialization. With more social interaction shifting to social media, it becomes an important source for research in different social sciences. This chapter looks at typical pipelines for social media analysis and introduces specialized R packages for these tasks, such as Twitter.

Network Visualization

Visual inspection of networks is a powerful tool in exploratory analysis of social networks. However, visualization of graphs has inherent problems that may result in misleading visualizations. This chapter first introduces basic theory behind these inherent problems. Then it introduces features of common layout algorithms used in visualization. Through applied examples, the chapter explores the use of layout parameters to obtain visualizations appropriate for the research focus.

Macro-Level Analyses and Dynamics

There are few studies on the macro-level dynamics of networks. These dynamics affect the whole network and concern non-local changes. Macro-level changes almost always stem from reasons outside the network. We observe this in its most typical form when the network population increases or decreases in an unusual manner. We cannot correlate such a population change with the relations of actors or the dyad, triad, or intergroup behaviors within the scope of these relations as it was the case in microo r meso-level dynamics. Sudden changes in population in a social network may“disturb” the established order and, therefore, may affect individual communicative relations. Population growth, on the other hand, might result in a revival in terms of other aspects. This chapter these macro-level dynamics.

Introduction

The traditional research approaches common in different disciplines of social sciences centered around one half of the social realm: the actors. The other half are the relations established by these actors and forming the basis of “social.” The social structure shaped by these relations, the position of the actor within this structure, and the impact of this position on the actor are mostly excluded by the traditional research methods. In this chapter, the authors introduce social network analysis and how it complements the other methods.

Modeling Network Dynamics

Social relationships and the social networks over these relationships do not occur arbitrarily. However, the random networks dealt with in this chapter are important tools for modeling the networks of these systems. The authors use random networks to understand and to model dynamics regarding the whole social structure. Random network models became the topic of several studies independently from social network analysis in the 1950s. These models were used in the analysis of a wide range of social and non-social phenomena, from electrical and communication networks to the speed and manner of disease propagation. This chapter explores the modeling network dynamics of random networks.

Social Capital and Social Embeddedness

The term social capital embodies a concept that emphasizes recent acknowledgement of how important social structure is to business life and how economic and business activity is embedded within the social structure. This rather theoretical chapter summarizes and exemplifies these concepts. This theory proves important in interpreting structural features whose analysis are covered in other chapters.

Structural Analysis With Graphs

Graphs are mathematical formalisms that represent social networks very well. Analysis methods using graph theory have started to develop substantially along with the advancement of mathematics and computer sciences in recent years, with contributions from several disciplines including social network analysis. Learning how to use graphs to represent social networks is important not only for employing theoretical insights of this advanced field in social research, but also for the practical purposes of utilizing its mature and abundant tools. This chapter explores structural analysis with graphs.

Varieties of Networks and Their Characteristics

Contemporary social network analysis deals with network data of varying nature. An important source of this variety comes from availability of continuous, temporal data from online and digitalized interactions between actors. E-mail exchanges or Twitter activity are some examples of such data. This chapter introduces terminology to classify network data according to its content. In addition, it exemplifies research on temporal data and methods used in analysis of such data.

Non-Local Centrality

The previous chapter focused more on assessment of the local and immediate structure surrounding a social actor. In this chapter, the authors look at the actor's relative importance by considering his/her position in the whole network. Some actors fill critical gaps in the broader social structure (e.g., by brokering between two otherwise detached social groups). Hence, their importance emerges from their structural qualities at the whole network level rather than local level. In this chapter, the authors develop the concepts and metrics to assess the broader structural features of individuals.

Neighborhood and Position

An important contribution of studying social structure is that it allows us to analyze the inequalities and differences in a complex web of social relations with concrete metrics. The ‘centrality' of individuals is an important metric used in this respect. The concept of ‘center' is borrowed from geometry, and there are several centrality metrics of social structure. This chapter looks into a particular centrality that gives information about the position of individual within his/her local structural neighbourhood. The concepts in this chapter also lay the foundation for understanding further variants of centrality in the following chapters.