Data Intensive Digital Humanities

The research area Data Intensive Digital Humanities within Linnaeus University Centre for Data Intensive Sciences and Applications (DISA) is a network that brings together those interested in intersecting computing and the disciplines of the humanities.

Digital humanities, the application and use of new ICT tools and systems, have led to a range of novel methods profoundly transforming the humanities and the social sciences.

Data Intensive Digital Humanities is a research network that brings together those interested in intersecting computing and the disciplines of the humanities. We conceptualize digital humanities as a social undertaking, meaning that the key component is collaboration that starts from research questions in the humanities. Solving these questions involves technical experts, such as computer scientists, specialists in virtual reality (VR), multimodal analysis and visualization experts. This intersection often leads to new answers to familiar questions not only in the humanities, but also new openings in the accompanying technical fields. Another important objective is to involve various cultural heritage institutions and organizations and collaborate in finding ways to present their materials.

New answers to familiar questions

We welcome new initiatives that are either related to our ongoing activities or are new openings in intersecting computing and humanities. We strongly feel the use and application of new computational methods can provide new answers to familiar questions in humanities and also help modeling humanities and social science phenomena in new ways in the future.

Our current work centers around three broad topic areas:

  • Variable natural language: the researchers in this area are scholars in English linguistics, and our research focuses on understanding language contact and emerging variability in the digital age. In a nutshell, we combine traditional philological data with real-time empirical evidence and develop and apply new methods to enrich and (visually) analyze natural language data streams that are large in scope and rich in metadata to gain novel insights on language variability in social context. We are currently using a continuous data stream of freely available data of Twitter messages and their metadata for sociolinguistic research tackling the influx of English in the Nordic region.
  • Regulated vs. open social media: develops new ways of tackling the transformation of media. It is based on the revolution of social and alternative media, which have challenged professionally regulated media. To understand the processes that shape today's media, the researchers will process and visually analyze large amounts of social and alternative media data.
  • Automated subject indexing and classification: aims to provide solutions to automated subject indexing and classification for improved retrieval across heterogeneous academic resources in distributed collections such as repositories, research data collections, catalogues of libraries, archives, museums. Furthermore, differences in terminology between different research communities (and even individual researchers) mean that literal string search cannot deliver effective cross-search for scholarly purposes. To address these issues, cross-disciplinary expertise involving linguistics, library and information science, computer science and information visualization will be combined.

Data Intensive Digital Humanities is an application area within the Linnaeus University Centre of Excellence (LNUC) for Data Intensive Sciences and Applications.

Ongoing work

  • Developing the Nordic Tweet Stream (NTS), a real-time tweet stream with material from five Nordic countries
  • Using big social media data in sociolinguistic research
  • Visualizing stance in tweets
  • Developing a pilot version of a VR application based on the NTS data