Self-Organizing Teams in Online Work Settings

Abstract

As the volume and complexity of distributed online work increases, the 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 such teams by grouping workers according to a set of predefined decision criteria. This approach micro-manages workers, who have no say in the team formation process. Depriving users of control over who they will work with stifles creativity, causes psychological discomfort and results in less-than-optimal collaboration results. In this work, we propose an alternative model, called Self-Organizing Teams (SOTs), which relies on the crowd of online workers itself to organize into effective teams. Supported but not guided by an algorithm, SOTs 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 SOTs to two benchmarks that do not offer user agency over the collaboration, reveal that participants in the SOTs condition produce results of higher quality and report higher teamwork satisfaction. We also find that, similarly to machine learning-based self-organization, human SOTs exhibit emergent collective properties, including the presence of an objective function and the tendency to form more distinct clusters of compatible teammates.

Crowdsourcing Team Formation With Worker-Centered Modeling

“…We model worker attributes (Table 1) into two categories: (i) manifest (Section 3.2.1.1) and (ii) latent (Section 3.2.1.2) properties. Manifest attributes are those worker characteristics that are straightforwardly noticeable by others and can be captured into the profiling information of online team formation systems (Lykourentzou et al, 2021). These attributes are the workers' knowledge domain, nationality, educational level, and age.…”

“…The second is a self-organized model, where workers govern the team formation processes (grouping and dismantling), with certain rules concerning whether teams should dismantle in the event of minority dissent or not. This approach is inspired by the SOT framework (Lykourentzou et al, 2021) honoring workers' preferences of teammates through a voting system combined with a graph cutting algorithm. We foresee two SOT models called Radical SOT (R-SOT) and Conservative SOT (C-SOT).…”

“…To coordinate the efforts of such workforce, crowdsourcing research has started to look into team formation algorithms as automated, scalable solutions. Routinely, team formation algorithms match workers according to objectives such as interpersonal compatibility (Lykourentzou et al, 2021) and social network connectivity (Liu et al, 2015;Rahman et al, 2019). One of the limits of computed team formation solutionswhich we address in this study-is the omission of the workers' preferences and evolving relationships in the algorithmic objective function.…”