Dynamic Learning Path Prediction — A Learning Analytics Solution

Govindarajan, K.; Kumar, Vive; Kinshuk, Kinshuk

doi:10.1109/t4e.2016.047

Cited by 18 publications

(10 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The full packaged product solution proposed by Fiallo and Gutiérrez (2017) provides the study of evidence in trigonometry in a software environment with dynamic geometry in 10th form. Another example of the full packaged solution is a system that can automatically configure the optimal learning route for students on a set of loaded learning materials (Govindarajan, Kumar & Kinshuk, 2017). Sommer et al (2014) in their works describe the online system of recommendations for e-learning in engineering education, which can also be designated as a full packeged solution.…”

Section: Analysis Of Foreign Studiesmentioning

confidence: 99%

Full Packaged Learning Solutions for Studying Mathematics at School

Utemov

Khusainova

Sergeeva

et al. 2018

EURASIA J MATH SCI T

View full text Add to dashboard Cite

The speed of modern changes in the system of teaching reflects an unprecedented accelerated renewal of means, forms and methods of teaching. Today, it is very important to test new learning solutions that reduce teachers' time on organization of students' educational activities. The idea of solving this problem is to combine the theory and practice of taking managerial actions and pedagogy in order to identify the type of learning solutions that reduce teachers' time, in particular teachers of mathematics, to prepare for classes. Thus, the purpose of the article is to justify full packaged learning solutions as an effective means of reducing the time spent on organizing the educational activities of schoolchildren. The authors of the article have determined the full packaged product as a package of program-methodical and subject-developing support that can be used by consumers of educational services (children, parents, teachers, administrators, employers) for independent use (a turn-key project). The leading methods of research are monitoring the organizational activities of teachers during math lessons, talking to teachers, analyzing methodical work and teachers' profiles, modeling and statistical processing of research results. As a result of the 2016-2017 experiment, where 21 teachers of mathematics took part, the authors of the article have defined types of learning solutions for mathematics teachers (adjustable, integrated and packaged); have described the stages of development and phases of creating a full packaged learning solution. Evaluation of the effectiveness of using full packaged product allowed to make a conclusion about an average decrease of time costs by 22% while preparing for classes. The theoretical significance of the article is due to the contribution to the development of scientific ideas about the means of methodical support for teachers of mathematics. The practical use of the proposed methods allows to organize a step-by-step transition from the development of adjustable solutions to full packaged learning solutions for studying school mathematics that contribute to reducing teachers' time spent on the organization of educational activities of students. The value of the full packaged product is justified with the help of a "project triangle", which connects key parameters for assessing the effectiveness of providing methodical support to mathematics teachers: the amount of work, time and costs. Changing the value of one parameter leads to changes of the values of others. Full packaged product allows to balance these parameters and achieve the planned educational result. Keywords: full packaged learning solutions, math teaching tools, types of learning solutions, phases of creating full packaged learning solutions, stages of development of full packaged learning solutions Utemov et al.

show abstract

Section: Analysis Of Foreign Studiesmentioning

confidence: 99%

Full Packaged Learning Solutions for Studying Mathematics at School

Utemov

Khusainova

Sergeeva

et al. 2018

EURASIA J MATH SCI T

View full text Add to dashboard Cite

show abstract

“…The proficiency comprises both measuring a target outcome achievement, and the competence changes during the process of learning for each learning outcome. It then predicts a dynamic path regarding the information from the clusters (Govindarajan, Kumar, & Kinshuk, ). In Protus, which is proposed by Vesin, Milicevic, Ivanovic, and Budimac (), the authors also use clustering for learning path recommendation.…”

Section: Related Workmentioning

confidence: 99%

Estimating time and score uncertainty in generating successful learning paths under time constraints

2018

View full text Add to dashboard Cite

This paper addresses the problem of course (path) generation when a learner's available time is not enough to follow the complete course. We propose a method to recommend successful paths regarding a learner's available time and his/her knowledge background. Our recommender is an instance of long term goal recommender systems (LTRS). This method, after locating a target learner in a course graph, applies a depth‐first search algorithm to find all paths for the learner given a time limitation. In addition, our method estimates learning time and score for all paths. It also indicates the probability of error for the estimated time and score for each path. Finally, our method recommends a path that satisfies the learner's time restriction while maximizing expected learning score. In order to evaluate our proposals for time and score estimation, we used the mean absolute error and average MAE. We have evaluated time and score estimation methods, including one proposed in the literature, on two E‐learning datasets.

show abstract

“…e prociency includes both measuring the achievement of a target outcome, and the competence and metacompetence changes during the learning process for each dened learning outcome. Second, it predicts the dynamic path based on the clustered information [12].…”

Section: Related Workmentioning

confidence: 99%

Rutico

Nabizadeh

Jorge

Leal

2017

Adjunct Publication of the 25th Conference on User Modeling, Adaptation and Personalization

View full text Add to dashboard Cite

Nowadays using E-learning platforms such as Intelligent Tutoring Systems (ITS) that support users to learn subjects are quite common. Despite the availability and the advantages of these systems, they ignore the learners' time limitation for learning a subject. In this paper we propose RUTICO, that recommends successful learning paths with respect to a learner's knowledge background and under a time constraint. RUTICO, which is an example of Long Term goal Recommender Systems (LTRS), aer locating a learner in the course graph, it utilizes a Depth-rst search (DFS) algorithm to nd all possible paths for a learner given a time restriction. RUTICO also estimates learning time and score for the paths and nally, it recommends a path with the maximum score that satises the learner time restriction. In order to evaluate the ability of RUTICO in estimating time and score for paths, we used the Mean Absolute Error and Error. Our results show that we are able to generate a learning path that maximizes a learner's score under a time restriction.

show abstract

Dynamic Learning Path Prediction — A Learning Analytics Solution

Cited by 18 publications

References 10 publications

Full Packaged Learning Solutions for Studying Mathematics at School

Full Packaged Learning Solutions for Studying Mathematics at School

Estimating time and score uncertainty in generating successful learning paths under time constraints

Rutico

Contact Info

Product

Resources

About