Emerging Research Trends in Big Data: Big Data and Digital Humanities

CIRI Blog

Published: November 9, 2015 by Dr. Michelle Chen

In my information visualization and big data courses, some of my students express strong interest in applying big data analytical skills to address or solve humanities-related issues. Motivated by this noticeable trend, I am proposing a workshop for “Big Data and Digital Humanities” to be held in conjunction with the 2016 IEEE International Conference on Multimedia Big Data. While the workshop proposal is currently under review, I think it would be nice to share some of the thoughts and research ideas here.

In recent years, improvements in IT have allowed for the creation and wide availability of increasingly large data sets in the humanities field. These, for example, include the digitization of entire library and museum archives and the creation of gargantuan corpuses capable of amassing digital records from centuries of print culture. These new data sets are not limited to texts; they include images, music, videos, virtual environments, social media, and more. A globalizing digital culture means that large quantities of digital data will be generated on a daily basis, via blogs, comments, emails, Internet searches, music downloads, “shares,” and online purchases. These huge, ever-growing data sets (i.e., “big data”) require new analytic tools for identifying trends and patterns, extracting key information, and analyzing historical or cultural trajectories under the properties and challenges of big data.

The extent and scope of these giant data sets pose clear opportunities as well as challenges for new methods and applications, as opposed to the traditional (“analog”) humanities research that has relied on compiling only “small data,” e.g., the body of work of only a few authors or artists, a body of texts from a narrowly defined historical period, or a specific literacy or artistic movement only. Big data research intersects with the humanities in multiple ways, including ongoing research on the processing and interpretation of large cultural data sets, as characterized by large communities, widely used software, collective discourses, and global IT actors (Kaplan, 2015). The intersection of big data and digital humanities also focuses on the human experience of large data sets via various available interfaces. This new intersection demands a new and novel set of methods and approaches to make sense of these large data sets and present research or historical findings to scholars and practitioners in a meaningful way. Understanding the modern digital culture and how individuals interact and utilize it requires a clear and structured understanding of how large humanities data actually form, function, evolve, and communicate.

Some research topics in this area might include:

  • Text analysis and data mining of cultural and historical archives;
  • New media studies and multimedia objects in the humanities, such as digital paintings, digital music, and films;
  • Cultural analytics and social computing;
  • Language and sentiment analysis;
  • New infrastructure for the humanities, such as cyber- and cloud-based storage;
  • Linked data, hypertexts, and semantic webs;
  • Information and communication technologies that support cultural heritage;
  • Interfaces, applied augmented reality, and interactive gaming;
  • Geographic information systems and digital mapping;
  • Large-scale retrieval over digital humanities data sets;
  • Big digital humanities data collection, management, and analytics;
  • Cross-modal analytic model for multi-modal digital humanities data, and
  • Novel and incentive applications of digital humanities data in various fields, such as health care, advertising and marketing, and entertainment.

This expansion of technology will provide novel, groundbreaking critical insights into the cultural, artistic, and intellectual trends of the recently digitized past as well as an increasingly digital present and future, thus introducing advanced and broader humanities benefits to all of society.

Reference:

Kaplan, F. (2015). A map for big data research in digital humanities. Frontiers in Digital Humanities, May 06, 2015. Available at: http://dx.doi.org/10.3389/fdigh.2015.00001