Managing Quality of Human-Based eServices

Abstract

Modern business strategies consider Web-based outsourcing of microjobs to the masses. Respective business activities are however difficult to manage. Traditional approaches of covering human tasks in business processes build on assumptions of limited process scale and closed organizational models that are not valid in crowdsourcing scenarios. Web services have been proposed as a means to represent human tasks that allow leveraging interaction, brokerage and composition capabilities of SOC for human interaction management. In this paper we argue that crowdsourcing requires considering qualitative constraints and sketch a platform for managing the quality of human-based eServices.

Statistical Quality Control for Human-Based Electronic Services

“…Because of the nature of pServices as Web based software services that deliver human intelligence, perception, or action to customers as massively scalable resources [10], it is obvious that pServices require some kind of Web platform. Figure 2 gives an overview of the basic pService scenario which comprises three roles: the pService requester, the pService platform and the workers who belong to a worker pool.…”

“…The MTurk platform acts as a broker between requesters who publish human intelligence tasks (HITs) and workers who work on those tasks in return for a typically small monetary compensation. Kern et al proposed the term people services (pServices) for this type of human-based electronic services [10].…”

“…Within the multifaceted dimensions of quality, this paper concentrates on the correctness dimension as the ability to return a minimum percentage of results that are free of error [10]. According to Jurans definition of quality as fitness for use [8], the paper assumes that the service requester can clearly categorize a task result as correct or incorrect.…”

Modeling context-aware and socially-enriched mashups

“…Thus, when combining human and software-based services, these differences must be considered in the design of compositions. We propose the extension of existing QoS models with regard to human attributes that reect human behavior [15]. Table 1 shows a set of quality attributes, along with their deni-tion, that can be applied to both human and machine-based services or to only one of these two types of services.…”

Quality Assurance for Human-Based Electronic Services: A Decision Matrix for Choosing the Right Approach

“…The MTurk platform acts as a broker between requesters who publish human intelligence tasks (HITs) and workers who perform those tasks in return for a small amount of money. Kern et al proposed the term people services (pServices) for this type of human-based electronic services and define it as "Web-based software services that deliver human intelligence, perception, or action to customers as massively scalable resources" [3]. As there is limited control over the individual contributors, particular attention has to be paid to the quality of the work results.…”