Concerning the Application of Big Data-Based Techniques to Social Sciences

Dear Colleagues,

Can Big Data and its analytic tools help research in the social sciences? If so, how can we properly apply Big Data analytics to address social problems? These are the questions that social scientists asked when Big Data was first introduced, but there is no clear answer to them yet.

Ironically, in 2015, a report from Gartner announced that the term “Big Data” had been dropped from its Hype Cycle for Emerging Technologies, suggesting that the concept is no longer considered new and lustered, but rather simply another part of the general technological landscape (Chung, Rhee & Cha, 2020). Despite the acceptance of the term, it remains challenging to determine what should be done with the Big Data available on the Internet, which aspects of the data are critical, and what kinds of consequences are brought into online and offline worlds in relation to the application of Big-Data-based techniques to social sciences.

Big Data can be seen as a mine with a massive amount of information underneath. To discover what is meaningful and significant, it is necessary to apply the proper tools and techniques. Advancements in computing hardware and software significantly aid how we process and analyze Big Data. Research methods and analytic tools continuously evolve as Big Data gain importance. Computer science and engineering are the leaders in this development, and different fields (e.g., medicine and business) have deepened their engagement with Big Data analytics. However, the field of social sciences is still very limited in excavating significant information from available Big Data.

Many researchers in social sciences study nodes (e.g., people, groups, or countries) and their interactions. They continuously examine how these interactions influence societies and the world. The Internet and social network services have vastly altered people’s relationships within societies, and this change is still in progress. Is classical data enough to understand how we live today? Every day, people leave their behavioral traces online. There is an uncountable amount of social data available, which endlessly reproduces in scale (Ruth & Pfeffer, 2014). More and more researchers are acknowledging the potential and importance of Big Data in the social sciences, and are attempting to incorporate Big Data in the study of social problems.

However, the pace of expansion of Big Data in social sciences does not match the rapid pace of change worldwide. This is because Big Data analytics requires an understanding that is significantly different from the existing research methods. It has particular methods for the collection, processing, and analysis of data (Shah, Cappella, & Neuman, 2015). For example, previous quantitative research in social sciences found causal relationships through statistical models using survey data. However, as people and societies have evolved due to online hyperconnectivity, it is inevitable for social scientists to embrace Big Data.

Big Data require an approach to processing and interpretation that is exceedingly different from current statistical analysis methods. Big Data are mainly unstructured and require thorough data preprocessing. For example, researchers may have to spend a great amount of time handling empty cells and decoding texts. Analyzing Big Data can be very difficult due to the high complexity of applied algorithms. It can be like interpreting a regression model with many interaction terms in lesser degrees. Big Data analysis is not always about finding causality, but rather about understanding correlation and making proper predictions and classifications.

It is challenging for social scientists to adapt to this new trend without relevant examples (Gonzalez-Bailon, 2013). Works from fellow researchers in multidisciplinary areas can significantly mitigate these hurdles. This Special Issue aims to provide bundles of Big Data research that can provide meaningful insights and guidelines to interested scholars through exploring the Big-Data-based techniques and their practical application in social sciences.

List of Topics    

Multidisciplinary contributions from scholars with a background in information systems, communications, politics, business, technology, e-research, digital humanities, knowledge management, and data-oriented fields are encouraged to submit a paper to this Special Issue.

Potential research topics that may be addressed include (but are not limited to):

• Practical applications of Big Data in communication, online information systems, new media and technology, digital humanities, knowledge management, and broader social sciences;
• Data collection and processing techniques for unstructured data;
• Machine learning for Big Data analytics;
• Analyzing social media in the social sciences;
• Testing theories or models using Big Data;
• Techniques to handle Big Data for e-research (e-politics, e-education, e-government, e-science, etc.);
• Measuring and monitoring data-driven research on the Internet;
• Developing a Big Data formula for online activities;
• Data-centric storytelling and scenarios;
• Case studies relating to the application of data science in interdisciplinary areas.

References

Chung, C., Rhee, Y., & Cha, H. (2020). Big Data analyses of Korea's nation branding on Google and Facebook. Korea Observer, 51(1), 151-174.

Gonzalez-Bailon, S. (2013). Social science in the era of Big Data. Policy & Internet, 5(2), 147-160.

Ruths, D., & Pfeffer, J. (2014). Social media for large studies of behavior. Science, 346(6213), 1063-1064.

Shah, D. V., Cappella, J. N., & Neuman, W. R. (2015). Big Data, digital media, and computational social science: Possibilities and perils. The ANNALS of the American Academy of Political and Social Science, 659(1), 6-13.

Dr. Chung Joo Chung
Guest Editor

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Sustainability is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2400 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

• big data
• social sciences
• practical application