Table 3 Summarization of the utilized approaches.
From: Enhancing intercultural competence in technical higher education through AI-driven frameworks
Methods | What it is? | How it is used? | Why it is good for Eduction? |
|---|---|---|---|
Apriori | Discovers common patterns and teaching activities tend to be most strongly linked to gains in students’ intercultural competence | It reveals which students’ ICC | Informs educators about which specific combinations of learning activities (e.g., projects, discussions) are best at promoting |
SimRank | Calculate how similar two items (such as students) are based on their relations to other things that share similarities | It measures the intercultural traits of the students How the formation of valuable peer groups and focus on instruction where it’s needed most | It groups students with similar intercultural profiles, which can allow peer interaction among the targeted institution |
MK-means Clustering | Clustering data points together by similarity. What the basis of their ICC characteristics (i.e. attitude, knowledge, skill). | Students are divided into clusters on different groups of students, based on their level of intercultural competence | Teachers can tailor instruction to different groups based on their level of intercultural competence |
Fuzzy Comprehe-nsive Evaluation (FCE) | Assesses qualitative factors using fuzzy logic, which deals with uncertainty and partial truths | Translates imprecise human judgments (e.g., "good,” "average,” “poor”) regarding ICC into numerical values | Enables subjective qualities such as attitude and cultural awareness to be measured in a reproducible, computational manner |
