Exploiting activity traces and learners’ reports to support self-regulation in project-based learning

Abstract : Project-based Learning (PBL) is a learner-oriented instructional method, which enables learners to carry out challenging and authentic projects by thorough investigations. PBL affords learners the opportunities to organize and plan the project, to collaborate with peers and to look for the resources and guidance to achieve the project goals. However, PBL is difficult to implement successfully because learners often lack of the self-regulation skills required to monitor, reflect, manage and assess their project activities and learning. Self-Regulated Learning (SRL) can train learners to gain these skills. However, most learning systems used in PBL focus on providing rich learning materials to the learners but rarely offer possibilities to monitor and analyze their project and learning processes. The main goal of this thesis is to support SRL during PBL situations. We propose a general architecture of Project-based Learning Management System (PBLMS), which help learners to understand how to regulate their learning activities during the projects. This general architecture integrates an existing Learning Management System (LMS) and two tools we propose: a reporting tool and a dynamic dashboard. The reporting tool enhances learners' reflective processes by leading them to describe their non-instrumented activities, their reflections and assessments on the project activities based on semi-structured sentences. The system can record automatically the activity traces of the users' interactions with the LMS, the reporting tool and the dashboard. These activity traces are merged with the self-reporting data so that indicators can be calculated basing on this entire information. The dynamic dashboard supports learners in creating customizable indicators. Learners can specify the data to take into account, the calculation and the visualization modes. We implemented this theoretical proposition with the development of the DDART (Dynamic Dashboard based on Activity and self-Reporting Traces) platform that integrates the reporting tool and the dynamic dashboard. To evaluate the proposition, we firstly test the ability of DDART to recreate a large sample of indicators that are proposed in existing researches about the analysis of activities, cognition, emotion and social network. Furthermore, an experiment was conducted to evaluate the usability and perceived utility of DDART. According to the results of this experiment, we found that DDART supports learners' reflections on the way they carry out the project and provides them with the opportunities to monitor their activities and learning, even if the indicator creation could be difficult for the novices.
Document type :
Complete list of metadatas

Cited literature [98 references]  Display  Hide  Download

Contributor : Abes Star <>
Submitted on : Tuesday, October 6, 2015 - 4:25:09 PM
Last modification on : Wednesday, November 20, 2019 - 3:01:44 AM
Long-term archiving on: Thursday, January 7, 2016 - 10:43:03 AM


Version validated by the jury (STAR)


  • HAL Id : tel-01212256, version 2


Min Ji. Exploiting activity traces and learners’ reports to support self-regulation in project-based learning. Machine Learning [cs.LG]. INSA de Lyon, 2015. English. ⟨NNT : 2015ISAL0032⟩. ⟨tel-01212256v2⟩



Record views


Files downloads