This workshop aims to introduce linguists to the powerful data analysis and manipulation tool, KNIME (Konstanz Information Miner), which offers an intuitive and versatile platform for conducting linguistic research. With its graphical interface and vast array of pre-built modules, KNIME allows researchers to streamline their workflows, facilitating the extraction of valuable insights from large and complex datasets.

The workshop will begin with an overview of KNIME and its potential role in the linguistic domain. Participants will learn how to set up and navigate the KNIME environment, as well as understand the key concepts and terminology associated with the platform. The session will then delve into the practical applications of KNIME for linguists, focusing on data ingestion, preprocessing, and transformation.

Through hands-on exercises, attendees will explore a range of text analytic tasks, such as corpus analysis, sentiment classification, and topic modelling. We will also discuss methods of data extraction from online sources such as Twitter and Youtube. By the end of this workshop, participants will be equipped with the knowledge and skills necessary to employ KNIME in their linguistic research, opening new avenues for data-driven discovery and innovative analysis.

CV

Jukka Tyrkkö is Professor of English Linguistics at Linnaeus University, Sweden. His research interests extend from the Middle Ages to the present day, focusing on a wide range of topics including corpus linguistic methodology, lexis and phraseology, the history of medical writing, multilingualism, historical lexicography, the language of politics and history of the book. He has compiled a number of historical corpora and he develops corpus linguistic software. His most recent edited volume is “Multilingualism from Manuscript to 3D: Intersections of Modalities from Medieval to Modern Times” (edited with Matylda Włodarczyk and Elżbieta Adamczyk, 2023). ORCID: 0000-0001-5251-5338.