Bitte klicken Sie auf die einzelnen Programmblöcke um nähere Informationen (Abstracts, CfP, Programmabläufe, Links) über den jeweiligen Programmpunkt zu bekommen. Über die Listenansicht haben Sie die Möglichkeit nach Workshopkategorien zu filtern.
Raum C 201
09:00 - 18:00
Donnerstag, 26.09.2024
In the pursuit of regaining digital sovereignty, a critical political and societal goal in our contemporary landscape marked by pandemics, geopolitical tensions, and virtual security risks, the nexus of computing education and digital literacy emerges as central. This integrated call for workshops addresses the transformative power of computational methods, including AI, not only in education, but also in society and labor markets. Expanding on skills and qualifications for the design of digitalized futures, this call seeks interdisciplinary insights into computer science, computational studies in the social sciences, economics, and humanities, and the profound impact of computational methods on digital sovereignty, societal structures, and the evolving demands of labor markets.
This workshop aims to comprehensively explore the intersection of computer science, computational methods, education research, sociological research, their respective methods and societal implications, with a special focus on digitalization and AI for and in education and educational research. It delves into interdisciplinary perspectives on the design of digitalized futures, examining aspects such as general education, labor markets, qualifications, vocational education and training, and adult education. In addition, the workshop encourages submissions that critically reflect on the application of digital methods in these research areas. The overarching goal is to understand how computational methods, especially AI, can be sensible applied in the development of digital and sustainable societies and economies. Emphasis is placed on both quantitative and qualitative research, including data science methods and AI approaches applicable to recommender systems, digitized learning, and effective linking of digital resources. Topics of interest include, but are not limited to:
• Quantitative and qualitative research
• Data science methods to analyse (vocational) education and labour market data
• Digital methods and systems in education (e-learning, adult education, general, VET and academic education, etc.)
• AI approaches for recommender systems and digitalized learning
• Linking of digital resources, a discussion of data sets, their quality and reliability, combining quantitative and qualitative data, anonymization and data protection.
• We also welcome submissions focusing on a critical reflection of digital methods in labour market research, education and other research areas.
Abstract: This paper introduces a novel algorithm specifically designed to address the unique complexities of icon-based tables in digital documents. Our algorithm leverages a combination of computer vision techniques to accurately detect table grids, identify symbols, and insert them into their relative positions.
Keywords: table extraction, education data, higher education
Abstract: The digitization of historical documents has gained particular interest in recent years. The majority of research endeavors aim at digitizing historical documents by extracting text from scanned images. A pipeline that transcribes scanned documents into fully structured texts was utilized to digitize over 900 German VET and CVET regulations. As a preliminary investigation, a basic corpus analysis was conducted to assess the usability of the digitized documents and the necessity for
document digitization methods that can generate transcripts that maintain the logical text structure and hierarchy. This paper focuses on the processing of the transcripts created from German VET and CVET regulation images to demonstrate the advantages of fully structured text over plain OCR results and to illustrate that even simple analyses require more information for more comprehensive document understanding.
Keywords: Document digitization, OCR, Legal texts, Corpus analysis
Abstract: The overall aim of this paper is to increase the comprehensiveness of the German Labour Market Ontology (GLMO). The GLMO provides entities for qualifications, such as occupations and training programs, as well as tools and skills. However, like most knowledge graphs, the GLMO provides only partially complete relationships between entities. This, for instance, affects the mappings of related tools, skills, and qualifications. To enrich the GLMO, publicly available data from the platforms of the Federal Employment Agency are extracted and combined with the GLMO. This integration process has led to the creation of additional entity classes for occupational metadata, including activity fields or activity areas. Moreover, additional links between skills and occupations, and between related qualifications have been established.
Keywords: Labor Market research, Ontology Completion, Web Mining
Abstract: The overall aim of this paper is to increase the comprehensiveness of the German Labour Market Ontology (GLMO). The GLMO provides entities for qualifications, such as occupations and training programs, as well as tools and skills. However, like most knowledge graphs, the GLMO provides only partially complete relationships between entities. This, for instance, affects the mappings of related tools, skills, and qualifications. To enrich the GLMO, publicly available data from the
platforms of the Federal Employment Agency are extracted and combined with the GLMO. This integration process has led to the creation of additional entity classes for occupational metadata, including activity fields or activity areas. Moreover, additional links between skills and occupations, and between related qualifications have been established.
Keywords: Labor Market research, Ontology Completion, Web Mining
Abstract: This research examines the impact of node and edge removal strategies on centrality measures within complex networks. Investigating random, scale-free, and small-world networks, various removal approaches, including targeted and random removal, are evaluated. The study assesses their influence on centrality metrics such as degree, betweenness, closeness, and eigenvector centrality on random networks and networks from educational research describing longitudinal data in labor
market-related topics in social networks. The findings contribute insights applicable across domains. In social network analysis, an understanding of key actors is beneficial for the development of targeted interventions or marketing strategies. Historical network analyses benefit from the discernment of pivotal nodes or connections, which elucidate information flow or influential figures across different periods. Such applications underscore the significance of the research in optimizing network performance in diverse contexts.
Keywords: Centrality Measures, Complex networks, Labor Market Networks, Social Network Analysis
Abstract: The increasing globalization of the Internet has led to a growing need for the processing of data in multiple languages. This has resulted in a significant increase in the amount of multilingual data available on the web, which presents a significant challenge for accessing, processing, and integrating data from different language sources. An ontology provides a shared and precise source for system interoperability and the reuse of knowledge bases. The objective of this study is to develop an efficient approach for mapping and enriching cross-domain, dual-lingual ontologies. In this case, we will combine the Computer Science Ontology (CSO) and DBpedia. The resulting taxonomy will be analyzed using a German online job advertisement (OJA) dataset of 3,567,240 records to identify trends in the development and/or requirement of tools in the Computer Science domain. In order to achieve this, we employ a comparative analysis of two distinct approaches: a holistic, hierarchical approach and a precision-driven approach. The former considers the child-parent relation of the ontology, whereas the latter solely identifies those tools directly associated with a topic in the CSO.
Keywords: Ontology Mapping, dual-lingual ontologies, Labor Market Research, digitalization, online job advertisements
Abstract: In 2018, BIBB introduced a legacy tools taxonomy for labor market research which is enhanced utilizing the Computer Science Ontology (CSO) and dual-language translation to incorporate additional information. The main research question is if it is feasible to enrich or rebuild an existing taxonomy on the basis of CSO. This poster presents a novel approach to enrich the CSO with data from DBpedia, creating a dual-language ontology enriched with tools and entities. This includes an ML-based approach to identify tools and compares the results with the legacy work tools taxonomy to identify the gaps.
Keywords: Ontology Mapping, dual-lingual ontologies, Labor Market Research, digitalization, tools