Social scientists address some of the most pressing issues of society such as health and wellness, government processes and citizen reactions, individual and collective knowledge, working conditions and socio-economic processes, and societal peace and violence. In an effort to understand these and many other consequential issues, social scientists invest substantial resources to collect large quantities of data, much of which are not fully explored. This chapter proffers the argument that privacy protection and responsible use are not the only ethical considerations related to data mining social data. Given (1) the substantial resources allocated and (2) the leverage these “big data” give on such weighty issues, this chapter suggests social scientists are ethically obligated to conduct comprehensive analysis of their data. Data mining techniques provide pertinent tools that are valuable for identifying attributes in large data sets that may be useful for addressing important issues in the social sciences. By using these comprehensive analytical processes, a researcher may discover a set of attributes that is useful for making behavioral predictions, validating social science theories, and creating rules for understanding behavior in social domains. Taken together, these attributes and values often present previously unknown knowledge that may have important applied and theoretical consequences for a domain, social scientific or otherwise. This chapter concludes with examples of important social problems studied using various data mining methodologies including ethical concerns.
TopBackground
Social scientists allocate substantial resources to data collection. At colleges and universities in the United States more than $4.4 billion was spent on social science research and development in fiscal year 2009 (National Science Board, 2012). Governments and non-government organizations spend billions of dollars more collecting data on society. This investment represents not only a financial expenditure but also the expenditure of countless days, weeks, and months of researcher, participant, and administrator time and effort. The results of this immense investment are often embodied in extensive data sets. Minimal efficiency demands reasonable output from this substantial input in data collection. This is not a new concept. Rosenthal (1994, p. 130) contends there is a larger obligation:
[D]ata are expensive in terms of time, effort, money, and other resources… If the research was worth doing, the data are worth a thorough analysis, being held up to the light in many different ways so that our research participants, our funding agencies, our science, and society will all get their time and their money’s worth.
Further, these data sets may contain answers to some of society’s pressing issues. Very broadly, the challenge to social investigators as stated in the National Science Foundation’s mission statement is lofty: “to promote the progress of science; to advance the national health, prosperity, and welfare; [and] to secure the national defense” (National Science Foundation, 2009). In this endeavor, the large quantities of data collected may contain the keys to resolving important social issues.
More specifically, though, these extensive data sets offer substantial leverage on the issues they address. For example, Oatley and Ewart (2003) worked with the West Midlands Police, UK, to develop a decision support system designed to reduce burglary and other crimes. The system used neural networks and a Bayesian belief network based on details of victims, offenders, locations, and the specific victimizations.