From “Events” to “Activities”: Creating Abstraction Techniques for Mining Students’ Model-Based Inquiry Processes (original) (raw)
Related papers
Recognizing patterns of student’s modeling behaviour patterns via process mining
Smart Learning Environments, 2019
Evaluating student learning effect plays an essential role in education, which is typically done by assessing student's final deliverables. However, the student's learning process has not been properly explored in the past. In this paper, we propose an interactive student learning effect evaluation framework which focuses on in-process learning effect evaluation. In particular, our proposal analyzes students modeling assignment based on their operation records by using techniques of frequent sequential pattern mining, user behavior analysis, feature engineering, and process mining. A comprehensive online modeling platform has been developed to enable data collection. We have carried out a case study, in which we applied our approach to a real teaching scenario, consisting of student online modeling behavior data collected from 24 students majoring in computer science. We also associate our process mining results with the numeric evaluation values. The preliminary result of case analysis has shown good potential to mine student modeling patterns and interpret their behaviors, contributing to student learning effect evaluation.
Domain experts should provide relevant domain knowledge to an Intelligent Tutoring System (ITS) so that it can guide a learner during problemsolving learning activities. However, for many ill-defined domains, the domain knowledge is hard to define explicitly. In previous works, we showed how sequential pattern mining can be used to extract a partial problem space from logged user interactions, and how it can support tutoring services during problem-solving exercises. This article describes an extension of this approach to extract a problem space that is richer and more adapted for supporting tutoring services. We combined sequential pattern mining with (1) dimensional pattern mining (2) time intervals, (3) the automatic clustering of valued actions and (4) closed sequences mining. Some tutoring services have been implemented and an experiment has been conducted in a tutoring system
Inducing High-Level Behaviors from Problem-Solving Traces Using Machine-Learning Tools
IEEE Intelligent Systems, 2000
This paper applies machine learning techniques to student modeling. It presents a method for discovering high-level student behaviors from a very large set of low-level traces corresponding to problem-solving actions in a learning environment. Basic actions are encoded into sets of domain-dependent attribute-value patterns called cases. Then a domain-independent hierarchical clustering identifies what we call general attitudes, yielding automatic diagnosis expressed in natural language, addressed in principle to teachers. The method can be applied to individual students or to entire groups, like a class. We exhibit examples of this system applied to thousands of students' actions in the domain of algebraic transformations.
Induction of High-level Behaviors from Problem-solving Traces using Machine Learning Tools
This paper applies machine learning techniques to student modeling. It presents a method for discovering high-level student behaviors from a very large set of low-level traces corresponding to problem-solving actions in a learning environment. Basic actions are encoded into sets of domain-dependent attribute-value patterns called cases. Then a domain-independent hierarchical clustering identifies what we call general attitudes, yielding automatic diagnosis expressed in natural language, addressed in principle to teachers. The method can be applied to individual students or to entire groups, like a class. We exhibit examples of this system applied to thousands of students' actions in the domain of algebraic transformations.
Pixed: An ITS that guides students with the help of learners' interaction logs
Pixed (Project Integrating eXperience in Distance Learning) is a research project attempting to use learners' interaction logs gathered as learning episodes to provide contextual help for learners trying to navigate their way through an ontology-based Intelligent Tutoring System (ITS). First, we propose a model to describe a learning session, a way to log learners' interaction and to decompose it into learning episodes. Then we use the case-based reasoning paradigm to offer contextual help to the learner, providing her/him with an adapted link structure for the course.
Using intelligent agents for the analysis of students' interaction and learning
Years of marking large numbers of group projects on specifications as part of a software engineering course has suggested that although the problems are illformed and hence the solutions various, there are some patterns in the learning process. The way students adhere to or deviate from these patterns, such as semantic rules for diagrams, or templates for the report, are a good guide to the students' understanding of their work. We developed software to enable remote groups to work on the projects. To extend this software we have developed a number of rule-based agents that guide students by analysing their learning approach and interaction patterns.
2020 IEEE Frontiers in Education Conference (FIE), 2020
This full paper of the research-to-practice category addresses the problem of organizing instructional materials and assessment activities in e-learning courses and their effects on learning outcomes. Usually, the teacher organizes the course sequence according to his didactic-pedagogical strategies and expects this help to guide the student through his learning process in the course. However, unless restrictions are imposed, students may choose to follow different paths than those indicated in the material's organization. A question emerges from this context: what are the impacts on the students learning outcomes when they take learning paths other than expected by the teacher? In Virtual Learning Environments, student's interaction with course materials can be stored in the so-called event logs. With the support of Educational Process Mining, it is possible to track the path of how and what specific actions students perform during learning, resulting in process models and historical statistical information. This paper aims to present the application results of PM techniques to verify the students learning paths in an introductory programming course. We used a Moodle event log containing 24605 events collected from 73 undergraduate students. For experiments, we divided this original log file into five other segments of datasets among passed and failed students variations. Techniques to obtain statistical information, Heuristic Miner algorithm to process discovery, and other techniques were applied from the implementations available in ProM Framework and scripts based on PM4Py library. The results showed that overall approved and failed students took different paths and event numbers to perform activities in the course. Besides, we obtained control-flows and frequencies of the activities and connections, thus making it possible to identify the dependencies, which resources started or ended the process, among other things. The analysis of these results provides general and specific information on students' learning paths and can help teachers observe students' behavior patterns and progress.
A tool to support Interaction and Collaboration Analysis of learning activities
An increasing amount of data is collected today during studies in which students and educators are engaged in learning activities using information technology and other tools. These data are indispensable for analysis and evaluation of learning activities, for evaluation of new tools and for students’ meta-cognitive activities. The data can take various forms, including video and audio recordings, log files of computing-related activity, field notes, results of students work in electronic or other forms, activity sheets etc. The need for analysis tools, which can annotate these data, classify them, process them and facilitate their inspection, is of increased importance especially for science education, since the latter involves experimentation and use of laboratory and other equipment that necessitate thorough off-line analysis and evaluation. In this paper we discuss first the key requirements of a new generation of interaction and collaboration analysis tools. We then present how these requirements have lead to the design of a prototype tool, recently developed. This tool can relate and synchronize various streams of field data. An important characteristic of the tool is its support for a multi-layer structure of annotations of various levels of abstraction, through which the activity can be interpreted and presented. This multi-layer representation can be inter-related to the raw field data, and can drive the navigation of the researcher in the activity data. An example of use of this tool for analysis and evaluation of a collaborative problem solving activity is also included.
Process Mining Towards Automated Learning: A Semantic Rule-Based Approach*
Extraction, synthesizing and analyzing of different types of data described as learning components; is indispensable to perform Learning Process mining. The work in this paper adopts process mining technique to propose a novel approach for automated learning that is capable of detecting changes in interaction patterns, and trends in behaviour of learners within a learning execution environment. We take into account the context of the learner in order to find the best possible way for them to learn intuitively in less time and still maintain performance. Our goal is to identify patterns that has effect on user performance, and then respond by making decisions based on adaptive rules centered on captured user profiles through semantic modelling and reasoning. We use the semantics of the captured processes and discovered patterns to create new knowledge for enhancement of existing processes in a learning model. The focus is on augmenting information values of the resulting model based on individual process instances. To ensure validity, we look at the degree at which the learning goal is met, and reliability means the consistency of developing a well-suited inference knowledge to draw conclusions based on improved learning process analysis.
Problem-Solving Knowledge Mining from Users' Actions in an Intelligent Tutoring System
2007
In an intelligent tutoring system (its), the domain expert should provide relevant domain knowledge to the tutor so that it will be able to guide the learner during problem solving. However, in several domains, this knowledge is not predetermined and should be captured or learned from expert users as well as intermediate and novice users. Our hypothesis is that, knowledge discovery (kd) techniques can help to build this domain intelligence in ITS. This paper proposes a framework to capture problem-solving knowledge using a promising approach of data and knowledge discovery based on a combination of sequential pattern mining and association rules discovery techniques. The framework has been implemented and is used to discover new meta knowledge and rules in a given domain which then extend domain knowledge and serve as problem space allowing the intelligent tutoring system to guide learners in problem-solving situations. Preliminary experiments have been conducted using the framework as an alternative to a path-planning problem solver in CanadarmTutor.