SSSulayman K. Sowe

Sulayman K. Sowe

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Sulayman K. Sowe has a total of 43 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    FAIR Data Assessment Using LLMs: The Fair-Way

    by Anmol Sharma, Sulayman K. Sowe, Soo-Yon Kim, Sayed Hoseini, Fidan Limani, Zeyd Boukhers, Christoph Lange, Stefan Decker

  • Top Cited Papers
    Open Access

    An LLM-Driven Chatbot in Higher Education for Databases and Information Systems

    by Alexander Tobias Neumann, Yue Yin, Sulayman Sowe, Stefan Decker, Matthias Jarke

    Contribution: This research explores the benefits and challenges of developing, deploying, and evaluating a large language models (LLMs) chatbot, MoodleBot, in computer science classroom settings. It highlights the potential of integrating LLMs into LMSs like Moodle to support self-regulated learning (SRL) and help-seeking behavior. Background: Computer science educators face immense challenges incorporating novel tools into LMSs to create a supportive and engaging learning environment. MoodleBot addresses this challenge by offering an interactive platform for both students and teachers. Research Questions: Despite issues like bias, hallucinations, and teachers’ and educators’ resistance to embracing new (AI) technologies, this research investigates two questions: (RQ1) To what extent do students accept MoodleBot as a valuable tool for learning support? (RQ2) How accurately does MoodleBot churn out responses, and how congruent are these with the established course content? Methodology: This study reviews pedagogical literature on AI-driven chatbots and adopts the retrieval-augmented generation (RAG) approach for MoodleBot’s design and data processing. The technology acceptance model (TAM) evaluates user acceptance through constructs like perceived usefulness (PU) and Ease of Use. Forty-six students participated, with 30 completing the TAM questionnaire. Findings: LLM-based chatbots like MoodleBot can significantly improve the teaching and learning process. This study revealed a high accuracy rate (88%) in providing course-related assistance. Positive responses from students attest to the efficacy and applicability of AI-driven educational tools. These findings indicate that educational chatbots are suitable for integration into courses to improve personalized learning and reduce teacher administrative burden, although improvements in automated fact-checking are needed.


  • Open Access

    RWTH-DBIS at LLMs4OL 2024 Tasks A and B

    by Yixin Peng, Yongli Mou, Bozhen Zhu, Sulayman Sowe, Stefan Decker

    The increasing capabilities of Large Language Models (LLMs) have opened new opportunities for enhancing Ontology Learning (OL), a process crucial for structuring domain knowledge in a machine-readable format. This paper reports on the participation of the RWTH-DBIS team in the LLMs4OL Challenge at ISWC 2024, addressing two primary tasks: term typing and taxonomy discovery. We used LLaMA-3-8B and GPT-3.5-Turbo models to find the performance gaps between open-source and commercial LLMs. For open-source LLMs, our methods included domain-specific continual training, fine-tuning, and knowledge-enhanced prompt-tuning. These approaches were evaluated on the benchmark datasets from the challenge, i.e., GeoNames, UMLS, Schema.org, and the Gene Ontology (GO), among others. The results indicate that domain-specific continual training followed by task-specific fine-tuning enhances the performance of open-source LLMs in these tasks. However, performance gaps remain when compared to commercial LLMs. Additionally, the developed prompting strategies demonstrate substantial utility. This research highlights the potential of LLMs to automate and improve the OL process, offering insights into effective methodologies for future developments in this field.


  • Open Access

    Managing North-South Research Collaboration Projects During the COVID-19 Pandemic

    by Sulayman K. Sowe, Mirco Schoenfeld, Cyrus Samimi, Petra Steiner, Anke Schürer-Ries

    Researchers from the Global North and South have collaborated for decades to conduct cutting-edge interdisciplinary research. The tools they used to manage their research projects remained virtually unchanged until the COVID-19 pandemic outbreak early in 2020. Since then, a lot has changed, including the nature and dynamics of research collaboration. How are researchers and project managers adapting to this change? Survey data, semi-structured interviews, and personal accounts from 102 respondents from 33 countries are used in this empirical study to investigate the impact of the pandemic on research collaboration projects. An independent non-parametric t-test revealed a significant difference in the research collaboration infrastructure and home environment between Global North and global South collaborators. The findings have practical implications for people involved in collaborative research projects, funding agencies, project management professionals, and universities interested in pursuing or sustaining North-South research collaboration during the pandemic.


  • Cyber-Physical-Human Systems: Putting People in the Loop

    by Sulayman K. Sowe, Eric Simmon, Koji Zettsu, Frederic de Vaulx, Irena Bojanova

    This article outlines the challenges of understanding how to integrate people into a new generation of cyber-physical-human systems (CPHSs) and proposes a human service capability description model to help.


  • Towards an Open Data Development Model for Linking Heterogeneous Data Sources

    by Sulayman K. Sowe, Koji Zettsu

    Open data is providing opportunities as well as challenges for research and development in the field of knowledge and systems engineering. The prospects for both researchers and application developers accessing and integrating publicly available data from various sources are unprecedented. However, many open data platforms are built in such a way that it is difficult or, sometimes, impossible to extract value from the data, integrate data from various sources, transform or improve the quality of the data through continuous use and reuse, track provenance, and share research findings. In this paper we present open data development model (ODDM) that addresses some these difficulties. The model shows how various stakeholders can check-out data from an open data repository, use and reuse the data, add new functionalities, appraise, transform, and publish or check-in the improved data for other researchers to benefit. We discuss how we intend to apply the model in practice to build a new generation of open data repository for interdisciplinary research, and highlight key issues for debate and discussion.


  • Designing a Cyber-Physical Cloud Computing Architecture

    by Eric Simmon, Sulayman K. Sowe, Koji Zettsu

    In this era of interconnectivity, where almost everybody, everything, and anything are networked, cyber-physical systems (CPS), also known as the Internet of Things (IoT), have emerged as vital systems that use information systems to observe and modify the physical world. Despite the proliferation of CPS in our lives, many such systems still use hardwired designs to accomplish a limited set of functions, such as sensing, actuating, or processing data or information. To achieve the vision of a platform for enabling the full potential of CPS that will encourage and drive innovation, CPS designers will need a new architectural design that can help connect everybody, everything, and anything together to achieve both our known and unknown goals. In this article, the authors present such a conceptual design and discuss its essential parts and key characteristics.


  • Managing Heterogeneous Sensor Data on a Big Data Platform: IoT Services for Data-Intensive Science

    by Sulayman K. Sowe, Takashi Kimata, Mianxiong Dong, Koji Zettsu

    Big data has emerged as a key connecting point between things and objects on the internet. In this cyber-physical space, different types of sensors interact over wireless networks, collecting data and delivering services ranging from environmental pollution monitoring, disaster management and recovery, improving the quality of life in homes, to enabling smart cities to function. However, despite the perceived benefits we are realizing from these sensors, the dawn of the Internet of Things (IoT) brings fresh challenges. Some of these have to do with designing the appropriate infrastructure to capture and store the huge amount of heterogeneous sensor data, finding practical use of the collected sensor data, and managing IoT communities in such a way that users can seamlessly search, find, and utilize their sensor data. In order to address these challenges, this paper describes an integrated IoT architecture that combines the functionalities of Service-Controlled Networking (SCN) with cloud computing. The resulting community-driven big data platform helps environmental scientists easily discover and manage data from various sensors, and share their knowledge and experience relating to air pollution impacts. Our experience in managing the platform and communities provides a proof of concept and best practice guidelines on how to manage IoT services in a data-intensive research environment.