Usage of Visual Analytics to Support Immigration-Related, Personalised Language Training Scenarios

Antzoulatos, Gerasimos; Mavropoulos, Thanassis; Tzionis, Grigorios; Karakostas, Anastasios; Almudena, Gonzalez Costas,; Burgos, Marta González; Vrochidis, Stefanos; Kompatsiaris, Ioannis

doi:10.1007/978-3-030-96296-8_61

Cited by 1 publication

(3 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this work, an experimental comparison between two well-known XAI approaches (PFI and SHAP) in the framework of Language Learning classification problem has been proposed. The proposed Knowledge Generation Model (KGM) for language learning [11] extended by consolidating XAI approaches (PFI and SHAP) to enhance our understanding of language learning problems and advance the interpretability of ML models through the integration of XAI principles. By conducting a comparative analysis of these XAI approaches, we aim to deduce valuable insights into their features and draw conclusions that contribute to the field's knowledge.…”

Section: Discussionmentioning

confidence: 99%

“…In this paper, we employ and extend the proposed Knowledge Generation Model (KGM) (Fig. 1) for language learning [11] by consolidating advanced Machine Learning techniques, to deal with challenges in the language learning domain, along with XAI approaches to provide more interpretable and reliable findings and results. Specifically, the interactive and iterative Visual Analytics schema fosters complex decision-making processes by leveraging two main pipelines of processing data, namely from raw Data to Visualisation (InfoVis process) or Data Mining modeling through the Knowledge Discovery in Databases (KDD) processes [32], coupling with machine learning algorithms (Fig.…”

Section: Proposed Methodologymentioning

confidence: 99%

“…In this paper, our research objective is to explore the application of XAI methodologies in the context of language learning. Specifically, we employ the proposed interactive and iterative Visual Analytics framework [11] along with the two well-known XAI methods, namely the Permutation Feature Importance (PFI) [12] and SHapley Additive exPlanations (SHAP) [13]. These techniques offer interpretability by assigning importance scores to features and providing explanations for individual predictions.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Evaluation of Explainable Artificial Intelligence Methods in Language Learning Classification of Spanish Tertiary Education Students

Tzionis,

Antzoulatos,

Papaioannou

et al. 2024

Lecture Notes in Networks and Systems

View full text Add to dashboard Cite

With the increasing prevalence of AI, significant advancements have been made across various domains, such as healthcare, learning, industry, etc. However, challenges persist in terms of trusting and comprehending the outcomes generated by these technologies. Specifically in the language learning domain, teachers face challenges regarding the classification of the students' learning capabilities and build the appropriate learning path for them. To address these challenges, the concept of Explainable Artificial Intelligence (XAI) was adopted, which is a set of processes and methods that allows human users to interpret, understand and trust the results derived from machine learning models. In this study, we adopt two well-known XAI algorithms, PFI and SHAP in a proposed Knowledge Generation Model equipped with ML models to derive hidden knowledge. The whole framework has been applied and evaluated on the Language Learning Classification of Spanish Tertiary Education Students acquired from the CEDEL2 database. The analysis concludes that in terms of explaining the black-box models, the SHAP model-agnostic method is the most comprehensive and dominant for visualizing feature interactions and feature importance and be applicable to any type of data.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Proposed Methodologymentioning

confidence: 99%