Field Of Computational Social Science Research Articles

No recognised ethical standards, no broad consent: navigating the quandary in computational social science research

Recital 33 GDPR has often been interpreted as referring to ‘broad consent’. This version of informed consent was intended to allow data subjects to provide their consent for certain areas of research, or parts of research projects, conditional to the research being in line with ‘recognised ethical standards’. In this article, we argue that broad consent is applicable in the emerging field of Computational Social Science (CSS), which lies at the intersection of data science and social science. However, the lack of recognised ethical standards specific to CSS poses a practical barrier to the use of broad consent in this field and other fields that lack recognised ethical standards. Upon examining existing research ethics standards in social science and data science, we argue that they are insufficient for CSS. We further contend that the fragmentation of European Union (EU) law and research ethics sources makes it challenging to establish universally recognised ethical standards for scientific research. As a result, CSS researchers and other researchers in emerging fields that lack recognised ethical standards are left without sufficient guidance on the use of broad consent as provided for in the GDPR. We conclude that responsible EU bodies should provide additional guidance to facilitate the use of broad consent in CSS research.

Predicting anxiety using Google and Youtube digital traces

Anxiety is a widespread and serious mental health issue that has been exacerbated by the COVID-19 pandemic and other stressors. In this study, we explore how online behavior data from Google and YouTube can be used to infer anxiety levels in individuals. We collected and processed digital traces from nearly 100 participants over eight weeks and applied various machine learning techniques to extract features and build predictive models. We found that combining data from multiple media modalities can yield highly accurate predictive models for anxiety as self-reported by a clinical GAD-7 scale (AUC > 0.86). We also found that the semantic categories of online engagement can affect the predictive performance of the models. This study contributes to the field of computational social science and digital mental health and demonstrates the potential of using online behavior data to monitor psychological well-being and design interventions for anxiety.

The rise of people analytics and the future of organizational research

Organizations are transforming as they adopt new technologies and use new sources of data, changing the experiences of employees and pushing organizational researchers to respond. As employees perform their daily activities, they generate vast digital data. These data, when combined with established methods and new analytic techniques, create unprecedented opportunities for studying human behavior at work and have fueled the rise of people analytics as a new institutional field of practice. In this chapter, I describe the emerging field of people analytics and new organizational phenomena that accompany the use of data and algorithms. These practices are affecting how individuals, groups, and organizations function, ranging from decision-making processes and work procedures, to communication and collaboration, to attempts to monitor and control employees. In each of these domains, I describe recent research and propose new research directions. Many of these domains intersect with the emerging field of Computational Social Science, in which disciplinary scholars are applying computational methods to an expanding array of digitized data, pursuing interests that extend far into the organizational domain. Organizational scholars are well-positioned to bridge organizational and disciplinary advances to stay at the forefront of research on the future of work.

An Online experiment during the 2020 US–Iran crisis shows that exposure to common enemies can increase political polarization

A longstanding theory indicates that the threat of a common enemy can mitigate conflict between members of rival groups. We tested this hypothesis in a pre-registered experiment where 1670 Republicans and Democrats in the United States were asked to complete an online social learning task with a bot that was labeled as a member of the opposing party. Prior to this task, we exposed respondents to primes about (a) a common enemy (involving Iran and Russia); (b) a patriotic event; or (c) a neutral, apolitical prime. Though we observed no significant differences in the behavior of Democrats as a result of priming, we found that Republicans—and particularly those with very strong conservative views—were significantly less likely to learn from Democrats when primed about a common enemy. Because our study was in the field during the 2020 Iran Crisis, we were able to further evaluate this finding via a natural experiment—Republicans who participated in our study after the crisis were even less influenced by the beliefs of Democrats than those Republicans who participated before this event. These findings indicate common enemies may not reduce inter-group conflict in highly polarized societies, and contribute to a growing number of studies that find evidence of asymmetric political polarization in the United States. We conclude by discussing the implications of these findings for research in social psychology, political conflict, and the rapidly expanding field of computational social science.

Social Interactions, Resilience, and Access to Economic Opportunity: A Research Agenda for the Field of Computational Social Science

Social Interactions, Resilience, and Access to Economic Opportunity: A Research Agenda for the Field of Computational Social Science

The (real) need for a human touch: testing a human–machine hybrid topic classification workflow on a New York Times corpus

The classification of the items of ever-increasing textual databases has become an important goal for a number of research groups active in the field of computational social science. Due to the increased amount of text data there is a growing number of use-cases where the initial effort of human classifiers was successfully augmented using supervised machine learning (SML). In this paper, we investigate such a hybrid workflow solution classifying the lead paragraphs of New York Times front-page articles from 1996 to 2006 according to policy topic categories (such as education or defense) of the Comparative Agendas Project (CAP). The SML classification is conducted in multiple rounds and, within each round, we run the SML algorithm on n samples and n times if the given algorithm is non-deterministic (e.g., SVM). If all the SML predictions point towards a single label for a document, then it is classified as such (this approach is also called a “voting ensemble"). In the second step, we explore several scenarios, ranging from using the SML ensemble without human validation to incorporating active learning. Using these scenarios, we can quantify the gains from the various workflow versions. We find that using human coding and validation combined with an ensemble SML hybrid approach can reduce the need for human coding while maintaining very high precision rates and offering a modest to a good level of recall. The modularity of this hybrid workflow allows for various setups to address the idiosyncratic resource bottlenecks that a large-scale text classification project might face.

MD-MBPLS: A novel explanatory model in computational social science

The newly emerged field of computational social science has witnessed unprecedented opportunities in the past decade with the explosion of data collection. However, these data are of different types, usually consisting of constant attributes (scalar data), temporal dynamics at the individual level (functional data) and group summaries at the collective level (compositional data). Consequently, existing models are substantially challenged by difficulties encountered in data aggregation. Moreover, previous studies excessively focus on the predictive power rather than interpretative power of models, while the latter is genuinely more crucial for developing profound theories and disclosing in-depth mechanisms in social science. This paper proposes a novel model named mixed data multi-block partial least squares (MD-MBPLS) to overcome these difficulties. Four real-world datasets are considered to evaluate the model. These datasets arise from large-scale collections of smart-card sensors, high-frequency trading systems and online social media, representing trending topics of student campus behaviour, stock market volatility, fake news circulation and personality in tweeting. The empirical results congruously reveal the prominent advantages of the model with respect to data fusion and explanatory power. Specifically, interesting patterns are reliably revealed which supplement new insights and help decision makers to obtain guidelines for interventions, such as student academic performance enhancement or precautions against fake news propagation. Our model will enhance the interpretative ability of computational social science studies by fully leveraging mixed types of data.

Twitter Explorer

We present an open-source interface for scientists to explore Twitter data through interactive network visualizations. Combining data collection, transformation and visualization in one easily accessible framework, the twitter explorer connects distant and close reading of Twitter data through the interactive exploration of interaction networks and semantic networks. By lowering the technological barriers of data-driven research, it aims to attract researchers from various disciplinary backgrounds and facilitates new perspectives in the thriving field of computational social science.

New Formats, New Methods: Computational Approaches as a Way Forward for Media Entertainment Research

The rise of new technologies and platforms, such as mobile devices and streaming services, has substantially changed the media entertainment landscape and continues to do so. Since its subject of study is changing constantly and rapidly, research on media entertainment has to be quick to adapt. This need to quickly react and adapt not only relates to the questions researchers need to ask but also to the methods they need to employ to answer those questions. Over the last few years, the field of computational social science has been developing and using methods for the collection and analysis of data that can be used to study the use, content, and effects of entertainment media. These methods provide ample opportunities for this area of research and can help in overcoming some of the limitations of self-report data and manual content analyses that most of the research on media entertainment is based on. However, they also have their own set of challenges that researchers need to be aware of and address to make (full) use of them. This thematic issue brings together studies employing computational methods to investigate different types and facets of media entertainment. These studies cover a wide range of entertainment media, data types, and analysis methods, and clearly highlight the potential of computational approaches to media entertainment research. At the same time, the articles also include a critical perspective, openly discuss the challenges and limitations of computational methods, and provide useful suggestions for moving this nascent field forward.

Behavioral attributes and financial churn prediction

Customer retention is crucial in a variety of businesses as acquiring new customers is often more costly than keeping the current ones. As a consequence, churn prediction has attracted great attention from both the business and academic worlds. Traditional efforts in the financial domain mainly focus on domain specific variables such as product ownership or service usage aggregation, however, without considering dynamic behavioral patterns of customers’ financial transactions. In this paper, we attempt to fill in this gap by investigating the spatio-temporal patterns and entropy of choices underlying the customers’ financial decisions, and their relations to customer churning activities. Inspired by previous works in the emerging field of computational social science, we built a prediction model based on spatio-temporal and choice behavioral traits using individual transaction records. Our results show that proposed dynamic behavioral models could predict churn decisions significantly better than traditionally considered factors such as demographic-based features, and that this effect remains consistent across multiple data sets and various churn definitions. We further study the relative importance of the various behavioral features in churn prediction, and how the predictive power varies across different demographic groups. More generally, the proposed features can also be applied to churn prediction in other domains where spatio-temporal behavioral data are available.

Exposure to opposing views on social media can increase political polarization

There is mounting concern that social media sites contribute to political polarization by creating "echo chambers" that insulate people from opposing views about current events. We surveyed a large sample of Democrats and Republicans who visit Twitter at least three times each week about a range of social policy issues. One week later, we randomly assigned respondents to a treatment condition in which they were offered financial incentives to follow a Twitter bot for 1 month that exposed them to messages from those with opposing political ideologies (e.g., elected officials, opinion leaders, media organizations, and nonprofit groups). Respondents were resurveyed at the end of the month to measure the effect of this treatment, and at regular intervals throughout the study period to monitor treatment compliance. We find that Republicans who followed a liberal Twitter bot became substantially more conservative posttreatment. Democrats exhibited slight increases in liberal attitudes after following a conservative Twitter bot, although these effects are not statistically significant. Notwithstanding important limitations of our study, these findings have significant implications for the interdisciplinary literature on political polarization and the emerging field of computational social science.

Analytical sociology and computational social science

Analytical sociology focuses on social interactions among individuals and the hard-to-predict aggregate outcomes they bring about. It seeks to identify generalizable mechanisms giving rise to emergent properties of social systems which, in turn, feed back on individual decision-making. This research program benefits from computational tools such as agent-based simulations, machine learning, and large-scale web experiments, and has considerable overlap with the nascent field of computational social science. By providing relevant analytical tools to rigorously address sociology’s core questions, computational social science has the potential to advance sociology in a similar way that the introduction of econometrics advanced economics during the last half century. Computational social scientists from computer science and physics often see as their main task to establish empirical regularities which they view as “social laws.” From the perspective of the social sciences, references to social laws appear unfounded and misplaced, however, and in this article we outline how analytical sociology, with its theory-grounded approach to computational social science, can help to move the field forward from mere descriptions and predictions to the explanation of social phenomena.

Channeling Hearts and Minds: Advocacy Organizations, Cognitive-Emotional Currents, and Public Conversation

Do advocacy organizations stimulate public conversation about social problems by engaging in rational debate, or by appealing to emotions? We argue that rational and emotional styles of communication ebb and flow within public discussions about social problems due to the alternating influence of social contagion and saturation effects. These “cognitive-emotional currents” create an opportunity structure whereby advocacy organizations stimulate more conversation if they produce emotional messages after prolonged rational debate or vice versa. We test this hypothesis using automated text-analysis techniques that measure the frequency of cognitive and emotional language within two advocacy fields on Facebook over 1.5 years, and a web-based application that offered these organizations a complimentary audit of their social media outreach in return for sharing nonpublic data about themselves, their social media audiences, and the broader social context in which they interact. Time-series models reveal strong support for our hypothesis, controlling for 33 confounding factors measured by our Facebook application. We conclude by discussing the implications of our findings for future research on public deliberation, how social contagions relate to each other, and the emerging field of computational social science.

The Data Science of Politics

This article engages with the methods content in Dowding’s book, examining the underlying assumptions regarding political science methodology and data and arguing that these issues deserve a more central role. In particular, the new possibilities for generation and analysis of large-scale data sources from political activity is driving methodological change, requiring a variety of multi-disciplinary expertise, and presenting new ethical challenges. Expansion of the toolkit of political science methodologies to incorporate the growing field of computational social science, or social data science, draws new scientists into the analysis of politics – such as mathematicians, computer scientists and physicists – who bring their own philosophy and practice of theory building, explanation and approach, which may shape the discipline in the future.

Combining natural language processing and network analysis to examine how advocacy organizations stimulate conversation on social media

Social media sites are rapidly becoming one of the most important forums for public deliberation about advocacy issues. However, social scientists have not explained why some advocacy organizations produce social media messages that inspire far-ranging conversation among social media users, whereas the vast majority of them receive little or no attention. I argue that advocacy organizations are more likely to inspire comments from new social media audiences if they create "cultural bridges," or produce messages that combine conversational themes within an advocacy field that are seldom discussed together. I use natural language processing, network analysis, and a social media application to analyze how cultural bridges shaped public discourse about autism spectrum disorders on Facebook over the course of 1.5 years, controlling for various characteristics of advocacy organizations, their social media audiences, and the broader social context in which they interact. I show that organizations that create substantial cultural bridges provoke 2.52 times more comments about their messages from new social media users than those that do not, controlling for these factors. This study thus offers a theory of cultural messaging and public deliberation and computational techniques for text analysis and application-based survey research.

Harvesting Big Data in social science: A methodological approach for collecting online user-generated content

Online user-generated content is playing a progressively important role as information source for social scientists seeking for digging out value. Advances procedures and technologies to enable the capture, storage, management, and analysis of the data make possible to exploit increasing amounts of data generated directly by users. In that regard, Big Data is gaining meaning into social science from quantitative datasets side, which differs from traditional social science where collecting data has always been hard, time consuming, and resource intensive. Hence, the emergent field of computational social science is broadening researchers' perspectives. However, it also requires a multidisciplinary approach involving several and different knowledge areas. This paper outlines an architectural framework and methodology to collect Big Data from an electronic Word-of-Mouth (eWOM) website containing user-generated content. Although the paper is written from the social science perspective, it must be also considered together with other complementary disciplines such as data accessing and computing.

Cultural carrying capacity: Organ donation advocacy, discursive framing, and social media engagement

Social media sites such as Facebook have become a powerful tool for public health outreach because they enable advocacy organizations to influence the rapidly increasing number of people who frequent these forums. Yet the very open-ness of social media sites creates fierce competition for public attention. The vast majority of social media messages provoke little or no reaction because of the sheer volume of information that confronts the typical social media user each day. In this article, I present a theory of the “cultural carrying capacity” of social media messaging campaigns. I argue that advocacy organizations inspire more endorsements, comments, and shares by social media users if they diversify the discursive content of their messages. Yet too much diversification creates large, disconnected audiences that lack the sense of shared purpose necessary to sustain an online movement. To evaluate this theory, I created a Facebook application that collects social media posts produced by forty-two organ donation advocacy organizations over 1.5 years, as well as supplemental information about the organization, its audience, and the broader social context in which they interact. Time series models provide strong evidence for my theory net of demographic characteristics of social media users, the resources and tactics of each organization, and broader external factors. I conclude by discussing the implications of these findings for public health, cultural sociology, and the nascent field of computational social science.

Why interdisciplinary research enriches the study of crime: Comment on “Statistical physics of crime: A review” by M.R. D'Orsogna and M. Perc

The past several years have seen a rapidly growing interest in the use of advanced quantitative methodologies and formalisms adapted from the natural sciences to study a broad range of social phenomena. The research field of computational social science [1,2], for example, uses digital artifacts of human online activity to cast a new light on social dynamics. Similarly, the studies reviewed by D’Orsogna and Perc showcase a diverse set of advanced quantitative techniques to study the dynamics of crime. Methods used range from partial differential equations and self-exciting point processes to agent-based models, evolutionary game theory and network science [3]. The research reviewed should be seen within the larger context of and complimentary to a growing trend in the social sciences towards the use of ever more advanced and refined quantitative methodologies. Much of this is driven by a generation of researchers that in addition to their substantive subject interest, embrace interdisciplinary work and possess advanced technical skills. These three key themes – subject relevance, interdisciplinarity, advanced methodologies – reappear throughout the studies reviewed by D’Orsogna and Perc. The review, for example, repeatedly highlights that research in this emerging field is inherently interdisciplinary: studies use methodologies adapted from other disciplines but explicitly engage with existing work on the mechanisms and dynamics of criminal behavior. This is an important and critical prerequisite for generating results that are relevant for a wider, social science audience. At the same time, the studies demonstrate that the methodologies used may, in fact, shed new light on a number of relevant aspects of criminal activity. The review further emphasizes the importance of systemic dynamics for the understanding of emerging patterns of crime. Historically, much of the research on crime has focused on the structural conditions for crime or on the motivations of individuals to engage in criminal activity. A more systemic perspective additionally emphasizes the relevance of the dynamics that arise from complex interactions – among individuals and with the environment – for the understanding of patterns of crime. This is nicely illustrated by a number of studies reviewed by D’Orsogna and Perc. The research discussed in Section 4, for example, shows that very simple mechanisms paired with complex systemic interactions may help elucidate the effect of policing on levels of crime. Similarly, a number of studies explicitly highlight the relevance of endogenous “feedback” effects for our understanding of criminal activity – this is

Visualizing Computational Social Science

Parallel advances in communication and visualization technologies have enabled the study and visualization of human behavior at a scale and level of detail never before possible. Nowhere are these advances more evident than within the emerging field of computational social science. Using Adamic and Glance’s image of the political blogosphere as an example and social representations theory as a guiding framework, we explore how computational social science visualizations may aid and complicate public understanding of this new science. We conclude with a discussion of best practices for the production and reuse of computational social science images for public consumption.

Computational Social Science for the World Wide Web

In this article, we want to introduce the field of computational social science to the intelligent systems community and discuss how this field can help to advance the current state of understanding and engineering social-computational systems on the World Wide Web. Overall, this article makes an argument that computational social science offers a unique range of challenges as well as methods and techniques that can help understand and engineer systems on the World Wide Web.