Optimizing Peer Learning in Online Groups with Affinities

Abstract

We investigate online group formation where members seek to increase their learning potential via collaboration. We capture two common learning models: LpA where each member learns from all higher skilled ones, and LpD where the least skilled member learns from the most skilled one. We formulate the problem of forming groups with the purpose of optimizing peer learning under different affinity structures: AffD where group affinity is the smallest between all members, and AffC where group affinity is the smallest between a designated member (e.g., the least skilled or the most skilled) and all others. This gives rise to multiple variants of a multiobjective optimization problem. We propose principled modeling of these problems and investigate theoretical and algorithmic challenges. We first present hardness results, and then develop computationally efficient algorithms with constant approximation factors. Our real-data experiments demonstrate with statistical significance that forming groups considering affinity improves learning. Our extensive synthetic experiments demonstrate the qualitative and scalability aspects of our solutions.

Mobile-assisted vocabulary learning through the Shanbay App outside the classroom: Effects of self-regulation and peer scaffolding

“…The two classes were randomly assigned as two groups: the experimental group with peer scaffolding (37 people) and the control group without peer scaffolding (34 people). Participants in each group were further grouped into small vocabulary learning teams consisting of 4–5 teammates, based on the statement that peer learning usually takes place by forming small groups consisting of 3–5 members ( Agrawal et al, 2014 ; Esfandiari et al, 2019 ).…”

Task Assignment Strategies for Crowd Worker Ability Improvement

“…Assignment algorithms are usually designed to improve platform-centric and requester-centric goals such as result quality, completion time and throughput. There are also task assignment solutions that consider worker-centric goals, such as mental stress [37], motivation [48], affinity [22] and boredom [13].…”

“…They include scaffolding where tasks are combined in alternating difficulty levels, and collaboration where workers learn from their interactions with higher-skilled peers. In online labor marketplaces, a few studies focused on the role of task difficulty and workers' ability to complete micro-tasks in improving skills [23], and how affinity between workers can be used to form teams that collaborate to produce high quality contributions while also improving skills [22]. Usually, such approaches require additional human cost to build training material or give feedback to workers.…”

Maximizing diversity over clustered data

“…Other related work includes the team-formation problem [13], where it is asked to select team members who bear a small communication cost, formulated as a Steiner tree or diameter. Esfandiari et al [7] have a different focus, partitioning students into different groups to encourage peer learning, so as to optimize some special affinity structure such as a star in each group.…”