Smart Tutoring System: A Predictive Personalized Feedback in a Pedagogical Sequence

Abstract

Feedback may be an effective interaction provided by the intelligent tutoring system. Nevertheless, the learning feedback is not easily definable, especially in front of learners with their characteristics and preferences. In this work, the authors propose to predict personalized feedback in a programming language learning context that promotes the feedback of the ITS according to the learner preferences and learner style. The recommended method uses a combination of machine learning techniques to suggest the best appropriate feedback according to learner’s preferences and characteristics. 
 For that purpose, the predictive personalized feedback method will respect the following phases: collect the learning experience from the learning resources (LR) and learner preferences (LP), generate groups of clusters that contain the common characteristics using the k-means algorithm, and define the association rules between the four categories and their corresponding activity. Finally, generate the personalized feedback and propose the recommendation through the intervention of an expert in the field.

Genetic Approach for Improved Prediction of Adaptive Learning Activities in Intelligent Tutoring System

“…8 shows the evolution of the fitness function averaging 50 generations using the genetic algorithm uniform where the fitness value is 15. In the Mutation phase, if we change the value in the interval [4,6], which has a coefficient (=2) that corresponds to an activist style, the fitness function decreases. On the other hand, if we change the value in the interval [1,3], which has a coefficient (=-1) that corresponds to a theorist style, the fitness function progresses exponentially.…”

“…However, the problem that online learning systems lack is to optimize the learner activities during a learning process. Meanwhile, various researchers have already addressed this topic by providing several solutions [2], such as eye-tracking technology [3] clustering [4] and classification methods [5] to detect the learner style, etc. These solutions allow the detection of the learning style and subsequently deduce the list of appropriate activities.…”

Exploring Perceptions of Online Feedback in Teaching EFL Speaking and Writing Skills during the COVID-19 Pandemic

“…Feedback has been considered an essential element in the EFL classroom to provide evidence related to the students' learning, performance, knowledge, or understanding (Hibbi et al, 2021;Bognár et al, 2021). However, feedback does not necessarily lead students to self-correction and improvement (Lee, 2017).…”

Hybrid Approach for Wind Turbines Power Curve Modeling Founded on Multi-Agent System and Two Machine Learning Algorithms, K-Means Method and the K-Nearest Neighbors, in the Retrieve Phase of the Dynamic Case Based Reasoning

“…Data clustering is the process of aggregation of items in a manner such that items in the same group are more identical to each other than in other groups [13]. In other words, the main objective is to find homogeneous subgroups with common characteristics [14] within the data such that data points in each cluster are as similar as possible according to a similarity measure such as Euclidean-based distance or correlation-based distance. Unlike supervised learning, clustering is considered an unsupervised learning method since we don't have the ground truth to compare the output of the clustering algorithm to the true labels to evaluate its performance.…”

“…The K-Means Machine Learning algorithm is the most popular clustering algorithm. It is an iterative algorithm that tries to partition the dataset into K pre-defined distinct subgroups (clusters) where each data point belongs to only one group [14]. The main objective of the K-Means Machine Learning algorithm is to make the intra-cluster data points as similar as possible while also keeping the clusters as different as possible [15].…”