HTHoucemeddine Turki

Houcemeddine Turki

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

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Houcemeddine Turki has a total of 130 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    European Network for FAIR Academic Metrics – ENFAIRAM COST Action proposal 2021

    by Dragan Ivanovic, Grischa Fraumann, Jennifer Dusdal, Kim Holmberg, Vladimir Trajkovik, Houcemeddine Turki, Colin Layfield, Stevo Popovic, Haris Memisevic, Lidija Ivanovic, et al.

    The open science paradigm, digitalisation, interdisciplinarity and internationalisation have significantly changed the research process, collaboration, dissemination and impact of scholarly work in the 21 st century. Research impact assessment should include new metrics based on Web 2.0 channels suffering from the following issues: data quality (i.e. accuracy, coverage, comprehensiveness), heterogeneity of data sources and APIs and potential manipulation (i.e. metrics gaming). Although the Findable, Accessible, Interoperable and Reusable (FAIR) principles were designed for research data, they can also be applied to research impact metrics to increase their discoverability and reusability. The main aim of this European Cooperation in Science and Technology (COST) Action is to remove barriers for the wider adoption and reusability of metrics, based on Web 2.0 technologies, which are a significant and vital part of research ecosystems. These metrics can serve as the basis for enhanced research impact assessment and, thus, improve recognition of excellence and foster the further development of science and society. Although Scientometrics, based on Web 2.0, is a paradigm that is over 10 years old, it has not yet been widely adopted. Therefore, a plan or roadmap for transition to Scientometrics 2.0 is needed. This should include recommendations for overcoming the challenges associated with new research impact metrics, as well as frameworks for the evaluation of new metrics and data sources. These challenges include the heterogeneity and comprehensiveness of metrics data sources, the varying quality of metrics data, metrics data gaming etc. Due to the multifaceted nature of these challenges, the Action proposes to create synergies between all interested actors: researchers, research software engineers, librarians, representatives of metrics data providers and policy-makers. This article presents an edited version of the original funding proposal submitted to the COST Open Call 2021.

  • Open Access

    Research Topics and Trends in MIMIC ‐ IV: A Large ICU Database Relevant for Critical Care Nursing

    by Yuh‐Shan Ho, Ahmed Ben Salem, Mahdi Kchaou, Abdulhameed Dere, Yosra Mzid, Houcemeddine Turki

    Background: The Medical Information Mart for Intensive Care‐IV (MIMIC‐IV) clinical database has become a central resource for data‐driven critical care research, enabling advances in clinical informatics, machine learning and nursing science. Despite its rapid uptake, no prior study has provided a transparent, methodologically grounded, bibliometrics‐based overview of MIMIC‐IV‐related research output. Aim: This paper aims to map the major research themes associated with the MIMIC‐IV database (2021–2024) and to evaluate their relevance to critical care nursing research and practice. Study Design: A study of 1150 publications retrieved from the Web of Science Core Collection (SCI‐Expanded). Explicit search strategies, front‐page filtering and publication counts were used to identify and analyse keyword‐based research themes. Results: Keyword analyses identified mortality prediction, sepsis, acute kidney injury, intensive care workflows and machine learning as dominant research areas, many of which are directly relevant to nursing‐sensitive outcomes and bedside clinical decision‐making. Conclusions: This review provides the first focused mapping of research themes within MIMIC‐IV publications. These findings clarify the thematic landscape of current MIMIC‐IV‐based research and underscore topics of particular importance to critical care nursing. Relevance to Clinical Practice: MIMIC‐IV supports the generation of evidence on essential nursing concerns. Recognising global research patterns enables nurses, clinicians and informatics teams to identify emerging tools, prioritise data‐driven competencies and translate large‐scale analytics into improved ICU care and patient outcomes.


  • Open Access

    Previous Nobel prize winners cite newer laureates

    by Houcemeddine Turki, Mohamed Ali Hadj Taieb, Mohamed Ben Aouicha

  • Evaluating the Behavior of Small Language Models in Answering Binary Questions

    by Houcemeddine Turki, Bonaventure F. P. Dossou, Ahmed Nebli, Ilario Valdelli


  • Tunisian Normalized Pronunciation

    by Houcemeddine Turki, Maik Gibson, Rafik Zribi, Imed Adel, Mohamed Ali Hadj Taieb, Mohamed Ben Aouicha, Kawthar Ellouze, Hager Ben Ammar, Abderrezak Bennour

  • Normalized Orthography for Tunisian Arabic

    by Houcemeddine Turki, Kawthar Ellouze, Hager Ben Ammar, Mohamed Ali Hadj Taieb, Imed Adel, Mohamed Ben Aouicha, Pier Luigi Farri, Abderrezak Bennour


  • Text Categorization Can Enhance Domain-Agnostic Stopword Extraction

    by Houcemeddine Turki, Naome A. Etori, Mohamed Ali Hadj Taieb, Abdul-Hakeem Omotayo, Chris Chinenye Emezue, Mohamed Ben Aouicha, Ayodele Awokoya, Falalu Ibrahim Lawan, Doreen Nixdorf


  • Open Access

    Publication Performance and Trends in Ontology Research in Computer Science Areas: A Bibliometric Analysis

    by Yuh-Shan Ho, Houcemeddine Turki, Mohamed Frikha, Ajith Abraham, Mohamed Ali Hadj Taieb, Mohamed Ben Aouicha

    Ontologies play a significant role in knowledge structure as they enable the exchange of information among various elements of AI. When fostering standardized data representations, ontologies contribute to knowledge organization and system interoperability. The current research investigates the evolution of the influence of ontology-based research from 1991 to 2022, using data from the Science Citation Index Expanded (SCIEXPANDED) database. It sheds light on the dynamic ontology research landscape and its contributions to the broader field of artificial intelligence. The study identified a total of 12,500 ontology-related articles, with the highest number of contributions from the United States, China, the United Kingdom, and Spain. Some of these papers are considered citation classics, serving as foundational pillars in the field or introducing valuable FAIR resources for ontology research. These citation classics are mainly developed by the United States, the United Kingdom, Germany, and Belgium. The article explores various aspects of ontology research, including document types, publication outputs, Web of Science categories, journals, reviews, countries, and research trends and surveys. The illustrative findings give insights into the ever-evolving nature of ontologies, research foci, and influential contributors, as the field of ontology research can help guide researchers, practitioners, and stakeholders, enabling them to harness the full potential of ontologies for advancing intelligent systems and knowledge management.


  • Open Access

    MeSH2Matrix: combining MeSH keywords and machine learning for biomedical relation classification based on PubMed

    by Houcemeddine Turki, Bonaventure F. P. Dossou, Chris Chinenye Emezue, Abraham Toluwase Owodunni, Mohamed Ali Hadj Taieb, Mohamed Ben Aouicha, Hanen Ben Hassen, Afif Masmoudi

    Biomedical relation classification has been significantly improved by the application of advanced machine learning techniques on the raw texts of scholarly publications. Despite this improvement, the reliance on large chunks of raw text makes these algorithms suffer in terms of generalization, precision, and reliability. The use of the distinctive characteristics of bibliographic metadata can prove effective in achieving better performance for this challenging task. In this research paper, we introduce an approach for biomedical relation classification using the qualifiers of co-occurring Medical Subject Headings (MeSH). First of all, we introduce MeSH2Matrix, our dataset consisting of 46,469 biomedical relations curated from PubMed publications using our approach. Our dataset includes a matrix that maps associations between the qualifiers of subject MeSH keywords and those of object MeSH keywords. It also specifies the corresponding Wikidata relation type and the superclass of semantic relations for each relation. Using MeSH2Matrix, we build and train three machine learning models (Support Vector Machine [SVM], a dense model [D-Model], and a convolutional neural network [C-Net]) to evaluate the efficiency of our approach for biomedical relation classification. Our best model achieves an accuracy of 70.78% for 195 classes and 83.09% for five superclasses. Finally, we provide confusion matrix and extensive feature analyses to better examine the relationship between the MeSH qualifiers and the biomedical relations being classified. Our results will hopefully shed light on developing better algorithms for biomedical ontology classification based on the MeSH keywords of PubMed publications. For reproducibility purposes, MeSH2Matrix, as well as all our source codes, are made publicly accessible at https://github.com/SisonkeBiotik-Africa/MeSH2Matrix .


  • Open Access

    A framework for integrating biomedical knowledge in Wikidata with open biological and biomedical ontologies and MeSH keywords

    by Houcemeddine Turki, Khalil Chebil, Bonaventure F.P. Dossou, Chris Chinenye Emezue, Abraham Toluwase Owodunni, Mohamed Ali Hadj Taieb, Mohamed Ben Aouicha