Call for papers: Automatic understanding of texts in social and computer sciences

Abstract

Over the last 20 years, the use of automated and semi-automated techniques for extracting meanings from text have been widely debated in the social sciences. Automated and semi-automated techniques can be employed in all research phases: data collection (e.g. scraping), data cleaning (e.g. lemmatization of words), analysis (e.g. Named Entity Recognition, Part-of-speech Tagging, Topic Modeling, Keyword Analysis, Semantic Network Analysis, Sentiment Analysis), and visualization. Far from forcing epistemological choices, these techniques can be inductively used to deal with big corpora of data, impossible to work with for a human being. The debate produced great expectations, but substantive research results and the development of actual user friendly tools are still relatively scarce. Social researchers usually lack the technical skills to develop and integrate new research tools as instruments able to radically change the way the research is devised and conducted. Computer scientists, on the other hand, often lack regular opportunities to interact with social scientists in ways that would enable greater understanding and more widespread use to be derived from the introduction of new tools. Moreover, in social and organizational sciences, different researchers use different techniques, but both a broader reflection on the advantages and disadvantages of each technique, and an integration/comparison of different tools, are lacking. A critical review of how these techniques are used in social sciences is a valuable and welcome contribution that would enable researchers working in these areas to disentangle the technicalities of these numerous and diverse techniques and showcase the research approaches they are used for. This call for papers follows an initial stream of research developed by the CATARSI project at the University of Bologna. CATARSI (Comprensione Automatica di Testi e ARticoli nelle scienze Sociali e Informatiche – automatic understanding of texts and articles in social sciences and computer sciences) aims at tackling the interface between social sciences and information science and improving both the knowledge and the development of computer-based techniques for analyzing texts and extracting meanings. The issue tackled by CATARSI, thus, is cultural and practical, and its results will impact both on information science, which deals more with ontological aspects, and on the social sciences, which stand to benefit from the use of new instruments to improve the way knowledge is analyzed and created. This Call for Papers (CfP) aims thus at collecting contributions able to shed light on the current use of semi-automatic and computer-aided techniques for understanding texts and extracting meanings from them, especially within the social sciences. Topics include, but are not limited to: application of one or more semi-automated techniques to organizational studies; critical reviews on how semi-automated techniques are used to elicit meanings from texts in organization science; comparison of qualitative and computer-aided techniques in conducting research; analysis of the ways different techniques are used to grasp meaning from texts; cross-field and interdisciplinary applications of automatic analysis techniques; description of new tools and systems for the use and application of these methods; critical reviews on the evolution of automatic reading within social and organization science. We welcome different theoretical and empirical methodologies. Qualitative, quantitative, and experimental methodologies are welcome. Full paper submission deadline: 31st October 2019