Fahima DJELIL

Abstract. Self-regulation is a well-established concept for which we already know different learning strategies, including cognitive strategies (reviewing courses, organizing information, memorizing), metacognitive strategies (self-assessment, planning) and strategies for seeking additional information (using documentary resources, asking others for help) [1]. Many recent studies agree on the relevance of Self-Regulated Learning (SRL), and point out the need for more empirical analysis of learner’s activities. One of the main objectives of such research is to reduce the number of drop out students, to enhance learners' motivation and increase learning success [2],[3]. This project aims to design and develop a modeling approach based on Dynamic Bayesian Networks (DBN), to provide students with SRL features and foster their autonomy. DBNs are used in different domains in decision making [4]. At the intersection between Knowledge representation and Machine Learning in Artificial Intelligence (AI), both the structure and the conditional dependencies of a DBN, can be learned using a variety of possible algorithms or specified by hand [4],[5]. This approach will be implemented as an extension of an existing online platform developed by France-IOI. France IOI has developed a small LMS (Learning Management System) which is used to organize large scale online contests, such as Castor Informatique France (700 000 participants in 2019) and the Algorea programming contest (220 000 participants in 2020). The LMS also includes learning tracks on programming basics and other related topics, dedicated to students starting from the 4th grade. A typical learning track is composed of interactive programming exercises sequences, along with small courses or videos and quizzes. Many of the exercises are composed of several versions (up to 4) of increased difficulties. Students who solve the hardest versions are awarded with the highest scores. Based on students’ interactions with the learning platform, and embedded SRL features, such as perceptions of progress, the designed approach will help student to: 

• define specific goals, plan and monitor their activities, and make decisions. 
• select strategies, based on the set of available exercises, and their difficulty levels. 
• monitor their activities as effectively as possible, to optimize their learning with a high level of autonomy. 

Keywords. Dynamic Bayesian Network (DBN), Student Modelling, Artificial Intelligence, Self-Regulation Learning (SRL) 

References 

1. Zimmerman B. & Martinez-Pons M : Development of a structured interview for assessing student use of self-regulated learning strategies. American educational research journal, vol. 23, n° 4, p. 614-628 (1986). 
2. De Barba, P., Kennedy, G.E., Ainley, M.: The role of students' motivation and participation in predicting performance in a mooc. Journal of Computer Assisted Learning 32(3), 218-231 (2016). 
3. Riel, J., Lawless, K.A.: Developments in mooc technologies and participation since 2012. In: Encyclopedia of Information Science and Technology, Fourth Edition, pp. 7888-7897. IGI Global (2018) 
4. Alpaydin, E.: Introduction to machine learning. MIT press (2020) 
5. Murphy, K. P. (2012). Machine learning: a probabilistic perspective. MIT press. 

Abstract. Self-regulation is a well-established concept for which we already know different learning strategies, including cognitive strategies (reviewing courses, organizing information, memorizing), metacognitive strategies (self-assessment, planning) and strategies for seeking additional information (using documentary resources, asking others for help) [1]. Many recent studies agree on the relevance of Self-Regulated Learning (SRL), and point out the need for more empirical analysis of learner activities. One of the main objectives of such research is to reduce the number of drop out students, to enhance learners' motivation and increase learning success [2],[3].

This thesis aims to design and develop a modelling approach based on Dynamic Bayesian Networks (DBN) and Open Learner Models (OLM), to provide students with SRL features and foster their autonomy.

DBNs are used in different domains in decision making [4]. At the intersection between Knowledge representation and Machine Learning in Artificial Intelligence (AI), both the structure and the conditional dependencies of a DBN, can be learned using a variety of possible algorithms or specified by hand [4],[5]. The OLM approach is used to support the learner’s reflection process by providing formative feedback on the learning process or even engaging negotiation with the learner [6]. Previous works on OLMs showed interesting effects on engagement with the learning content [7].

Our objective is to implement these approaches as extensions of existing online platforms developed by France-IOI, on one hand, and on existing MOOCs developed by IMT Atlantique, which are available on Edx and Fun platforms, on another hand. The learning content includes tracks on programming basics and other related topics, dedicated to students from different levels, starting from the 4th grade in secondary level to undergraduate Higher Education. Based on student interactions with the learning platforms and embedded SRL features, such as perceptions of progress, the designed approach will help students to:

• define specific goals, plan and monitor their activities, and make decisions.
• select strategies, based on the set of available learning resources and their difficulty levels.
• monitor their activities as effectively as possible, to optimize their learning with a high level of autonomy.

 The modelling approach will follow these three steps:

These three main steps will guide the development of a predictive model that will be informed from empirical corpus data as well as a theoretical understanding of a self-regulated process.

Keywords. Self-Regulation Learning (SRL), Dynamic Bayesian Network (DBN), Bayesian Knowledge Tracing, Open Learner Models (OLM).

References

1. Zimmerman B. & Martinez-Pons M: Development of a structured interview for assessing student use of self-regulated learning strategies. American educational research journal, vol. 23, n° 4, p. 614-628 (1986). 
2. De Barba, P., Kennedy, G.E., Ainley, M.: The role of students' motivation and participation in predicting performance in a mooc. Journal of Computer Assisted Learning 32(3), 218-231 (2016).
3. Riel, J., Lawless, K.A.: Developments in mooc technologies and participation since 2012. In: Encyclopedia of Information Science and Technology, Fourth Edition, pp. 7888-7897. IGI Global (2018)
4. Alpaydin, E.: Introduction to machine learning. MIT press (2020)
5. Murphy, K. P. (2012). Machine learning: a probabilistic perspective. MIT press.
6. Bull S., J. Kay (2010) “Open learner models,” in Advances in intelligent tutoring systems,  pp. 301–322,  Springer.
7. A. Nussbaumer, E.-C. Hillemann, C. Gütl, D. Al-bert, “A competence-based service for supporting self-regulated learning in virtual environments.,”Journal ofLearning Analytics, vol. 2, no. 1, pp. 101–133, (2015).

Abstract. A current trend in higher education is to provide students with group work activities. Existing research has focused on studying the effectiveness of this approach and impact on learner success. Several studies have shown that cooperation in learning is an important factor for success in higher education (Vaughan 2002, Kooloos et al 2011). For instance, there is an interest in the way group dynamics (equitable, individually dominated group...) impact individual educational outcomes (Theobald 2017). Student attitudes have a strong impact on group dynamics and on academic performance. Therefore, it is important for a teacher to monitor these dynamics, to better understand student productions and make decisions. However, few tools exist to help teachers monitor group dynamics in a meaningful way.
This project aims to improve an existing digital platform called LabNbook (http://labnbook.imag.fr). Evolutions will concern the design of a new tool based on Learning Analytics to provide visual indicators through learning dashboards on the basis of learning data. This will support teachers in the assessment of group skills and make decisions on the interventions to be carried out. This project will also include an evaluation of the dashboards usage and impacts in practice within a scholarly context.
Keywords. Group work, Learning Analytics Dashboards, User Experience, LabNbook, Usage and Impact Evaluation 

Candidate Profile 
The candidate should hold a PhD Degree in Data Science/Data Analytics, with good relational skills and high interest in the Education Research domain. Competencies in the User Centered Approach or in the Design Based Research methodology are required.
We highly recommend applications from the French speaking community, to make easier experiments within French scholarly institutions. 

Missions
The candidate will conduct a preliminary literature review, as well as a need analysis of users in the French academic context (teachers and students), to define relevant indicators characterizing group work. The candidate will also handle the existing dashboard of the LabNbook platform, and other advanced functionalities which are under development.
The candidate will design the expected improvements that will be integrated into the LabNbook platform. This mission will be conducted with the LabNbook team, which continuously carries out the design and the development of the existing activity dashboard, as well as research on relevant indicators to visualize by collecting data and using Learning Analytics. 
He/she will conduct experiments in order to validate the research findings regarding the platform usage evaluation and the dashboard appropriation comprising the new implemented functionalities. 

Principal activities 
-    Handling the existing LabNbook platform and dashboard.
-    Defining relevant indicators on collaboration/cooperation in group work, on the basis of literature. 
-    Analyzing data and developing appropriate algorithms to calculate these indicators.
-    Proposing appropriate visualizations.
-    Improving the existing dashboard.
-    Analyzing and evaluating usages, especially teachers’ usages. 

References 

• Kooloos J.G., Klaassen T., Vereijken M., Van Kuppeveld S., Bolhuis S., Vorstenbosch M., Collaborative group work: Effects of group size and assignment structure on learning gain, student satisfaction and perceived participation. Med Teach, 33(12), 2011. 
• Vaughan W., Effects of cooperative learning on achievement and attitude among students. Journal of Educational Research, 95(6), 2002
• Theobald E.J., Eddy S.L., Grunspan D.Z., Wiggins B.L., Crowe A.J., Student perception of group dynamics predicts individual performance: Comfort and equity matter. PloS ONE, 12(7), 2017.