ILCM - A Virtual Research Infrastructure for Large-Scale Qualitative Data

iLCM - A Virtual Research Infrastructure for Large-Scale Qualitative Data Andreas Niekler1, Arnim Bleier2, Christian Kahmann1, Lisa Posch2,3, Gregor Wiedemann1, Kenan Erdogan2, Gerhard Heyer1, Markus Strohmaier4, 2 , 1Faculty of Mathematics and Computer Science, University Leipzig, Augustusplatz 10, 04109 Leipzig, Germany {aniekler, kahmann, wiedemann, heyer}@informatik.uni-leipzig.de 2Department of Computational Social Science, GESIS – Leibniz Institute for the Social Sciences Unter Sachsenhausen 6-8 50667 Cologne, Germany {firstname.lastname}@gesis.org 3Institute of Interactive Systems and Data Science, Graz University of Technology, Inffeldgasse 16c, 8010 Graz, Austria 4HumTec Institute, RWTH Aachen University Theaterplatz 14, 52062 Aachen, Germany markus.strohmaier@humtec.rwth-aachen.de Abstract The iLCM project pursues the development of an integrated research environment for the analysis of structured and unstructured data in a “Software as a Service” architecture (SaaS). The research environment addresses requirements for the quantitative evaluation of large amounts of qualitative data with text mining methods as well as requirements for the reproducibility of data-driven research designs in the social sciences. For this, the iLCM research environment comprises two central components. First, the Leipzig Corpus Miner (LCM), a decentralized SaaS application for the analysis of large amounts of news texts developed in a previous Digital Humanities project. Second, the text mining tools implemented in the LCM are extended by an “Open Research Computing” (ORC) environment for executable script documents, so-called “notebooks”. This novel integration allows to combine generic, high-performance methods to process large amounts of unstructured text data and with individual program scripts to address specific research requirements in computational social science and digital humanities. ilcm.informatik.uni-leipzig.de Keywords: infrastructure, text mining, computational social science, digital humanities, reproducible research 1. Introduction Computational social science (CSS) is the interdisciplinary study of socio-cultural phenomena through new kinds of data and technologies. One of its central objectives is the extraction of useful and interpretable knowledge from po- tentially large behavioral digital datasets. The availability of these datasets has witnessed a fast increase in the past decades through the progressing digitization of social pro- cesses. Similar potentials, as well as challenges due to this development, can be observed in fields such as the digital humanities (DH) and communication science (CS). In CSS, unstructured data (usually text) and structured data (e.g. metadata, survey data or log/sensor data) are both im- portant sources of information. Through the digitization of social processes, they are available in large quantities. With the iLCM infrastructure, we plan to offer analysis ca- pabilities for reusable and reproducible research with both data types. The manual analysis of qualitative text data is an integral part of the method repertoire of empirical re- search in various disciplines. The increasing availability of large amounts of digital or retro-digitized text has lead to a growing interest in computer-assisted evaluation methods. Different research methods such as quantitative or qualita- tive content analysis, discourse analysis or grounded the- ory methodology can be fruitfully combined with text min- ing methods (Wiedemann, 2016). Lexicometric methods such as keyword extraction, frequency- and co-occurrence analysis are already established and widely used in social science text analysis. Machine learning methods such as …

Content truncated to 500 words