Self-organization in online collaborative work settings

Abstract

As the volume and complexity of distributed online work increases, collaboration among people who have never worked together in the past is becoming increasingly necessary. Recent research has proposed algorithms to maximize the performance of online collaborations by grouping workers in a top-down fashion and according to a set of predefined decision criteria. This approach often means that workers have little say in the collaboration formation process. Depriving users of control over whom they will work with can stifle creativity and initiative-taking, increase psychological discomfort, and, overall, result in less-than-optimal collaboration results—especially when the task concerned is open-ended, creative, and complex. In this work, we propose an alternative model, called Self-Organizing Pairs (SOPs), which relies on the crowd of online workers themselves to organize into effective work dyads. Supported but not guided by an algorithm, SOPs are a new human-centered computational structure, which enables participants to control, correct, and guide the output of their collaboration as a collective. Experimental results, comparing SOPs to two benchmarks that do not allow user agency, and on an iterative task of fictional story writing, reveal that participants in the SOPs condition produce creative outcomes of higher quality, and report higher satisfaction with their collaboration. Finally, we find that similarly to machine learning-based self-organization, human SOPs exhibit emergent collective properties, including the presence of an objective function and the tendency to form more distinct clusters of compatible collaborators.

Trust Assessment Under the Integrated Air-Space-Ground Network Environment

“…Also, the overall architecture of DyLAN (Figure 1) reflects the optimal collaboration organization of human online workers (Lykourentzou et al, 2022), and reveals significant performance in agent collaborations. Therefore, simulating human collaboration by LLM-agent collaborations under Dy-LAN might also be possible.…”

“…For instance, Liu et al (2015) show that skill contribution is essential for selecting crowd workers to solve outsourced tasks efficiently. Based on peer rating, Lykourentzou et al (2022) develop an algorithm for managing online workers in an optimal organization. Building upon these prior works, we introduce an automatic algorithm to optimize the team of agents by quantifying agents' contributions based on their peer ratings.…”