Startseite Mathematik 14 Implementation and evaluation of an eXplainable artificial intelligence to explain the evaluation of an assessment analytics algorithm for freetext exams in psychology courses in higher education to attest QBLM-based competencies
Kapitel
Lizenziert
Nicht lizenziert Erfordert eine Authentifizierung

14 Implementation and evaluation of an eXplainable artificial intelligence to explain the evaluation of an assessment analytics algorithm for freetext exams in psychology courses in higher education to attest QBLM-based competencies

  • , , , , , , und
Veröffentlichen auch Sie bei De Gruyter Brill

Abstract

In the realm of higher education, the exploration of eXplainable artificial intelligence (XAI), elucidating the mechanisms behind artificial intelligence systems, becomes increasingly pivotal as institutions seek transparency and comprehension in leveraging advanced technologies for diverse academic applications. Based on our previous research, we outlined an automated approach for generating test and training data for assessing free-text answers in a digital university course on work organization and design for a natural language processing (NLP) algorithm, encompassing research methodology, theoretical background, concept, implementation, evaluation, and future improvements. This chapter presents the underlying NLP algorithm and the corresponding XAI component, for which the test and training data was created. Therefore, we will present the state-of-the-art in the area of XAI and NLP for the higher education sector. Subsequently, we will present the current state of technology in our educational system, the Knowledge Management Ecosystem Portal (KM-EP), and its qualification-based learning model-related subsystems. The corresponding concepts and proof of concept implementations and evaluations are presented. The chapter concludes with a summary and discussion.

Abstract

In the realm of higher education, the exploration of eXplainable artificial intelligence (XAI), elucidating the mechanisms behind artificial intelligence systems, becomes increasingly pivotal as institutions seek transparency and comprehension in leveraging advanced technologies for diverse academic applications. Based on our previous research, we outlined an automated approach for generating test and training data for assessing free-text answers in a digital university course on work organization and design for a natural language processing (NLP) algorithm, encompassing research methodology, theoretical background, concept, implementation, evaluation, and future improvements. This chapter presents the underlying NLP algorithm and the corresponding XAI component, for which the test and training data was created. Therefore, we will present the state-of-the-art in the area of XAI and NLP for the higher education sector. Subsequently, we will present the current state of technology in our educational system, the Knowledge Management Ecosystem Portal (KM-EP), and its qualification-based learning model-related subsystems. The corresponding concepts and proof of concept implementations and evaluations are presented. The chapter concludes with a summary and discussion.

Kapitel in diesem Buch

  1. Frontmatter I
  2. Preface V
  3. Contents VII
  4. Methods and instrumentation
  5. 1 Identifying and estimating outliers in time series with nonstationary mean through multiobjective optimization method 1
  6. 2 Using the intentionally linked entities (ILE) database system to create hypergraph databases with fast and reliable relationship linking, with example applications 21
  7. 3 Rapid and automated determination of cluster numbers for high-dimensional big data: a comprehensive update 37
  8. 4 Canonical correlation analysis and exploratory factor analysis of the four major centrality metrics 49
  9. 5 Navigating the landscape of automated data preprocessing: an in-depth review of automated machine learning platforms 71
  10. 6 Generating random XML 83
  11. Applications and case studies
  12. 7 Exploring autism risk: a deep dive into graph neural networks and gene interaction data 105
  13. 8 Leveraging ChatGPT and table arrangement techniques in advanced newspaper content analysis for stock insights 121
  14. 9 An experimental study on road surface classification 145
  15. 10 RNN models for evaluating financial indices: examining volatility and demand-supply shifts in financial markets during COVID-19 165
  16. 11 Topological methods for vibration feature extraction 185
  17. 12 Dyna-SPECTS: DYNAmic enSemble of Price Elasticity Computation models using Thompson Sampling in e-commerce 215
  18. 13 Creating a metadata schema for reservoirs of data: a systems engineering approach 251
  19. 14 Implementation and evaluation of an eXplainable artificial intelligence to explain the evaluation of an assessment analytics algorithm for freetext exams in psychology courses in higher education to attest QBLM-based competencies 271
  20. 15 Toward a skill-centered qualification ontology supporting data mining of human resources in knowledge-based enterprise process representations 307
  21. Index 333
Heruntergeladen am 21.3.2026 von https://www.degruyterbrill.com/document/doi/10.1515/9783111344553-014/html
Button zum nach oben scrollen