This chapter provides the reader with three reflections about the Policy Priority Inference research programme and its potential to make a difference in the real world. First, we synthesise the results found throughout the book and their implications for sustainable development. Second, we elaborate on systematic guidelines for deriving policies from the various analyses presented throughout the book. Third, we discuss the technical capabilities needed to adopt this toolkit and advocate for the training of computational social scientists.

The frontiers of network analysis keep expanding with new data sources and new ways to see structure and model relations. Traces of interactions and relations are now constantly streaming and being recorded through social network platforms. New technologies are affording new ways to visualize and analyze massive online data sets, as well as flowing interactions using video and sensor data. These new data sources are being met with new data mining approaches, giving us a deeper and wider view of social structure. Moreover, these new technologies are undoubtedly changing aspects of social structure itself, as people form ties and influence one another in ways that were unimaginable a generation ago. What is missing, we contend, is a systematic way of linking these projects to a theory of social structure (as outlined in Chapter 2). We conclude by proposing three strategies for addressing open problems and moving forward in modeling social structure.

Increasing digitalization means that many of our daily interactions happen within digital environments where they leave digital footprints in the form of trace data. Such digital trace data is often thought to generate insights by virtue of its immense scale. This focus on ‘big data’ tends to overlook the richness and complex characteristics of digital traces that opens new vistas for a multitude of computational analyses that generate new and high-resolution insights to digital environments. As such, paying attention to the characteristics of trace data allows for deep investigations of social-technical interactions in unprecedented detail.

This chapter describes the process of digital trace analysis through four analytical activities aimed at identifying units of analysis, extracting categories, validating patterns and conceptualizing findings from digital trace data. It then shows how analytical activities can be applied to a given digital trace dataset to derive three ‘facets’ that each provide rich conceptualizations of social interaction with technology. It explains each facet and outlines ways to implement digital trace analyses that focus on facets relating to relations (network analysis), processes (sequence analysis) or semantics (text analysis).

We set out the case for computational social science as opposed to traditional “pencil and paper” formal methods. The substantive theme of this book is the governance cycle in parliamentary democracies, but the ideas we put forward can be applied to many other areas of study.

While heavy-duty computational methods have revolutionized much empirical work in political science, computational analysis has yet to have much any impact on theoretical accounts of politics – in contrast to the situation in many of the natural sciences. We set here out to map a path forward in computational social science. Analyzing the complex and deductively intractable “governance cycle” that plays out in the high-dimensional issue spaces of parliamentary systems, we use two different computational approaches. One models functionally rational politicians who deploy rules of thumb to navigate their complex environment. The other deploys an artificial intelligence algorithm which systematic learns, from massively repeated self-play, to find near-optimal strategies. Future work made possible by greater computational firepower would enable better AI, more realistic ABMs, and the modeling of logrolling under the conditions of incomplete information which characterize most real-world bargaining and negotiation.

We outline the core argument of the book and steps taken to establish this. We begin by sketching component parts of the governance cycle: election, government formation, and government survival. Noting that the analysis of this complex system is intractable for traditions deductive methods of formal modeling, we preview two different computational methods for analyzing it. First, we model “functionally rational” artificial agents who use simple but effective rules of thumbs to navigate their high stakes but complex environment (ABM). Second, we specify an artificial intelligence (AI) algorithm which, by massively repeated self-play, teaches itself to find near-optimal strategies for playing what is in effect a traditional, but intractable, noncooperative game. We conclude by sketching the empirical approach we use to first calibrate and exercise the models on training data and then test them on out-of-sample test data.

Reciprocity is a mechanism for the evolution of cooperation. This mechanism explains cooperation among unrelated individuals by an assortment in which individuals restrict their interaction partners to avoid being exploited by defectors. Three types of reciprocal mechanisms have been proposed: direct reciprocity, indirect reciprocity, and network (spatial) reciprocity. Direct reciprocity is a behavior whereby an individual acts in a manner that temporarily reduces his or her fitness while increasing another individual’s fitness with the expectation that the other individual will behave similarly at a later time. If individuals who use direct reciprocity both regard each other as cooperative, they will establish reciprocal relationships. Indirect reciprocity is a mechanism that enables individuals to establish cooperative relationships, e.g., by evaluating others’ behavior, without having direct interactions, which are required by direct reciprocity. If an individual cooperates with individuals with good reputations and that individual establishes a good reputation, cooperation via indirect reciprocity can occur. Network reciprocity explains reciprocal relationships via restriction of interaction, e.g., network and spatial restrictions, namely, individuals interact with fixed individuals in a network. If cooperative clusters arise, cooperators realize high fitness by cooperating with each other. Theoretical studies have explored the evolutionary stability of the cooperation that facilitates these reciprocities. Experimental studies have examined the evidence for these reciprocities according to the theoretical studies. These theoretical and experimental studies assume a simple interaction among individuals for cooperative and reciprocal behavior, such as in evolutionary game theory. By examining such theoretical and experimental evidence in a less restrictive environment, these pieces of evidence can be generalized to natural environments and real life. Human behavior logs on the Internet, e.g., online games, can be utilized in such studies. In this chapter we review the theory and evidence for the three types of reciprocities. First, we introduce evolutionary game theory as a framework for the evolution of cooperation, such as reciprocal altruism. Second, we explain the three types of reciprocity by reviewing results of theoretical studies. Third, we present experimental evidence for human reciprocity, which supports these evolutionary theories of reciprocity. Finally, we present empirical evidence for human reciprocity in practice using an online game dataset, which represents a less restrictive environment.