CLS INFRA D4.1 Skills Gap Analysis

The main task of this deliverable was to explore current gaps in teaching of research skills for computational literary studies to inform the CLS INFRA project’s own approach to training schools and chart the territory to gain broader insight into current CLS teaching practices.

We approached the task through an explicit mapping of 1) existing training opportunities (“supply”) and 2) opinions of the practitioner community (“demand”) to a single grid of skills, where it would be possible to identify the gaps through comparison. 

From four broadly defined stages in a research cycle: 1) Theory and research setup, 2) Collection, 3) Analysis, 4) Delivery we derived 26 skills. To understand supply we have manually annotated current offers in a sample of European university courses in Digital Humanities and summer school workshops. To index demand we set up an online survey to ask the community to evaluate each skill from the grid based on its perceived future prospects in the field and teaching (1-5 scale response, 118 participants).

After value normalization, areas of Analysis and Collection, especially advanced text modeling, classification, statistics, corpus building, and access to existing collections look undersaturated. Across Research setup the focus is on research design principles, while Delivery shows underrepresentation of knowledge on reproducibility. 

The survey also offered a chance to observe the demographic structure of the CLS community. Most of the responses came from early career researchers, indicating a new generational wave within computational literary studies. Participant gender was balanced, although more late career men than women were represented, and men were more represented in disciplines with technical backgrounds. Self-reported involvement in CLS and experience in computational skills was likewise on average lower for female participants. Researchers who work in the field of CLS also report more proficiency in computational methods, which suggests that these go hand in hand in current practice.

Open questions built into the survey showed further nuance in community lines of thinking about opportunities and pitfalls for training in CLS. Among the topics most frequently mentioned were a quantitative lack of (centralized) training, concern about the discipline’s positioning, and the lagging behind in institutionalization of computational research skills.

To a lesser degree, participants addressed the lack of resources to learn. Several participants reported missing the opportunities to pursue a career in CLS. Others felt overwhelmed by the unorganized offer in CLS training and material, or described a qualitative lack in schooling beyond introductory modules.

When asked about missed areas in the survey, participants suggested more focus on the heterogeneity of the current textual landscape in CLS and the discipline’s connections outside of academia. The reported core issues for training overlap thematically with the outlined areas of improvement of this survey, showing that this survey was not all-encompassing. It underlines the importance of foregrounding community voices in taking steps to support skill advancement in CLS research.