Dr Jessica Witte

IASH Affiliate 2023-24
Dr Jessica Witte

Dr Jessica Witte is a postdoctoral research fellow in text and data mining affiliated with the School of Literatures, Languages & Cultures (LLC) and the Centre for Data, Culture & Society (CDCS). She received her PhD in nineteenth-century literature with a specialisation in digital humanities. Informed by this background, Dr Witte’s research takes an interdisciplinary approach to computational text analysis. Her research critically examines not only large textual datasets, but also the tools developed to analyse them. Currently, she is involved with several projects, including revising her PhD thesis into a monograph, exploring the metadata of the Internet Archive’s Text Collections, and applying NLP methods to social media data. As a “self-taught” digital humanist, Dr Witte is passionate about supporting current (and curious) computational researchers. She contributes to the CDCS digital skills training programme and has previously delivered workshops through the European DCODE Network and the Scottish Graduate School for the Arts & Humanities (SGSAH).

My current research is centred on developing natural language processing (NLP) tools tailored for the complexities of textual datasets frequently examined in the humanities. These datasets often contain historical language, literary and artistic allusions, sarcasm, and slang—linguistic nuances that pose challenges for computational algorithms and, consequently, for digital researchers. In recognition that effective computational text analysis demands the creation of specialised tools, my research underscores the importance of interdisciplinary in the field of text mining. Additionally, I am deeply committed to addressing ethical, accessibility, and open access issues in digital research. By tackling these challenges, I'm not only contributing to the cultivation of ethical and sustainable data-driven practices but also ensuring that valuable insights are made accessible to a wider audience. This dedication fosters inclusivity and transparency in an increasingly digitalized world.