Campuslab "Digitization and computer-assisted analysis in the humanities and social sciences" (DCAGG)Campuslabs_Struktur.jpg

The CampusLab "Digitisation and Computational Analysis in the Humanities and Social Sciences" is a cross-institutional and inter-departmental unit which is concerned with the development of innovative digital methods for the Humanities and Social Sciences with a focus on data analytics. It aims to bridge the gap between the Humanities/Social Sciences on the one hand and Computer Science/the Natural Sciences on the other hand. The DCA currently comprises four research areas (Text, 3D, GIS, and Visualisation) and is coordinated by the GCDH.


Speaker: Prof. Caroline Sporleder

Coordinator: Dr. Piroska Lendvai

Administrative Support: Bettina Brandt


For more Information subscribe the Campuslabs mailing list at:

ed.negnitteog-inu.stsil@gnureisilatigid-robalsupmac




List and chart of supported Projects:


pilot-pies.svg


 

Lab Nr.Project TitleInstitutionPeopleAbstract
1Digitales TextlaborSeminar für dt. Philologie
FB neuere dt. Literatur
Prof.Dr. Heike Sahm
Dr. Berenike Herrmann

Digital Text Lab
DCA method fieldText analysis

Text Lab implements methods for literature scientific markup for text corpora und digital historical editions. It involves gamification as acquisition and quality control for literary markup method in research-oriented university teaching.
It conducts grammatical and fine-grained narratological and figurative analysis, identification of speech and thought representation types,  and the investigation of metaphor.
2IT-AFKProfessur für Anwendungssysteme
und E-Business
Prof. Dr. Matthias Schumann
Janne Kleinhans (M.A.)
 "IT-gestützte Analyse von Freitextaufgaben für die Lehre"
 
Automatizing essay scoring via text classification in the Business Education domain via text analysis approaches.
The project targeted corpus collection, interfacing existing tools and
reusing labeled data for running machine learning experiments.
 
33D-DigitalisierungslaborArchäologisches InstitutProf. Dr. Martin Langner 
The lab addresses digitization of physical objects and the digital reconstruction of collection items. Its method field is visualization, the targetd DH domains are Cultural Heritage and Image Science.
Methods envisioned:
-Scanning workflow 
-Methods for pattern recognition 
-Shape Comparison of artifacts (Ancient portraiture, Greek terracotta figurines, Medieval seals, plaster casts)
-Shape Analysis of artifacts. 
-A method for object mining is envisioned.
-Creating a 3D repository for all collections on campus
4"TrAiN"Institut für Informatik /
GCDH
Dr. Marco Büchler TrAIN aims to conduct research pertaining to two essential Digital Transformation processes, namely Optical Character Recognition (OCR) and Handwritten Text Recognition (HTR), applied to historical data. The project focuses on the  letter collection from the Grimm Brothers. TrAIN compares the outputs produced by the HTR of the original letters and by the OCR of the printed edition, and investigates two common scholarly tasks: text reuse detection and authorship attribution. Text reuse algorithms are employed to align the OCR output with the HTR output, and author attribution techniques to identify the stylistic markers of the Grimm Brothers.
5"KOLIMO"Seminar dt. Philologie
FB neuere dt. Literatur
GCDH
Prof. Dr. Gerhard Lauer
Dr. Berenike Herrmann
 KoLiMo is developing a large literary collection to verify hypotheses of textual scholarship, Identify and assess quantitative indicators of style, to enable synchronic and diachronic comparison of  epochs, movements, and authorship. The main tasks in creating this new benchmark resource consist of corpus cleanup, preprocessing, grammatical analysis and labeling, standardized metadata creation, acquisition, mapping and labeling, standardized markup, quality control, and online presentation.
6"Datarama"Max-Planck-Institut zur Erforschung multireligiöser und multiethnischer
Gesellschaften
Dr. Norbert Winnige
Prof. Dr. Steven Vertovec
 
The DATARAMA is a research and presentation tool which provides a novel solution to presentation challenges for a wide field of disciplines.
Datarama is an immersive projection environment with interactive selection, management and handling of multiple types and sources of data.
 
•Two introduction videos presenting the DATARAMA and its set of distinctive visual data solutions for a range of scientific applications, in order to deal with complexities and challenges of modern data workflows.
7"Digital Publishing of the Liber Ordinarius"Musikwissenschaftliches SeminarProf. Dr. Andreas Waczkat
Karen Thöle
 
The project explores digital means for the transcription, presentation and evaluation of the text and its sources. Its focus is on the testing the usability of existing software for this purposes
We experiment with a combination of different specialized tools for the different stages of preparing a source text edition, and also try to adapt tools designed for non-research-purposes, especially plagiarism detectors. We make use of highly specialist software such as Transkribus
8"PoliLab"Institut für PolitikwissenschaftProf. Dr. Andreas Busch PoliLab targets computer-assisted analysis of political discourse such as Chancellor’s speeches and party programs. Its methods include text categorization, topic and sentiment analysis and tracking of content changes over time.
9"Die Erschließung des Staatsgebietes"Institut für historische LandesforschungProf. Dr. Arndt Reitemeier
Dr Niels Petersen
 
Die Erschließung des Staatsgebiets: Chausseebau in Nordwestdeutschland 1764-1843
 
The project’s goal was to clarify how the administration of road construction has functioned in the focus area, by means of providing geographical contextualization for enhanced historico-cultural interpretation. The method developed converted road and landmark objects from historical maps and archived texts to digital contemporary maps. A corpus of GIS maps is developed and presented online.
10"LingLab"Seminar dt. Philologie
mit linguistisch ausgerichteten Abteilungen
Prof. Dr. Anke Holler
Prof. Dr. Marco Coniglio
Dr. Annika Herrmann
 The idea of project LingLab is to create an innovative collaboration platform to concentrate the workflow of empirically working linguists into one system and provide a tool to ease research data management and data publication. With LingLab research projects can be publically accessed at a very early stage in the research process. By giving access to an automatically created data paper and the relevant material, linguistic data can be easily replicated and reused by other interested researchers. This ensures the sustainability of research materials and invites researchers to intensify networking and collaboration.