Online social media platforms like Twitter, provide opinion rich repositories for conducting sentiment analysis. Users engage in open discussions on a variety of topics across a wide cross-section of problem domains. Commercial, government, educational, non-profit and other types of agencies are increasingly relying on extracting conversations on Twitter to determine the general sentiment of the public on particular topics, products, services and issues. Despite being readily available and in abundance, it is also laced with nuances which can disrupt, skew and potentially lead to inaccurate analysis if not handled properly. In this paper, we propose an SOA framework to enable the pre-processing of data origination on Twitter, and configurable components that allow data consumers to filter the data using useful social media signals.

State-of-the-art practices have recognized the utility of leveraging human intervention as a crucial aspect of modern computing systems. The emerging crowdsourcing paradigm is based on harnessing human intelligence, effort and rational behaviors to augment computation and analysis. In addition to the crowdsourcing paradigm, new techniques have emerged that incorporate machine and human computational resources together forming a hybrid intelligence when addressing complex problems and tasks. This combined technique is particularly impactful if human and machine contributions can scale automatically in response to their respective efficiency and effectiveness when addressing subsets of a bigger problem - an approach that we have named mixed elastic systems. In this survey, we highlight state-of-the-art projects that investigate crowdsourcing, hybrid intelligence systems and mixed elastic systems. We also present a taxonomy and classification of the broader domain of human-enhanced computing systems as it assimilates crowdsourcing, hybrid intelligence, and mixed elastic systems.

The 15th edition of the "Adaptive Computing (and Agents) for Enhanced Collaboration" track at WETICE 2017 focuses on the areas of adaptive agent-based services and adaptive techniques for enterprises. The purpose of the track is to bring together researches in the fields of software agents and adaptive computing as they relate to the context of adaptive techniques and enterprise collaboration. This report briefly discusses the content of the papers accepted for presentation in the track.

Crowdsourcing labor market platforms consist of a variety of jobs spanning multiple problem domains and their respective specialized or diverse worker pools. Each platform currently operates independently and isolated from the potential benefits of sharing job and worker pool data across platforms. Previous work introduces infrastructure that optimizes the sharing of both job and worker data collectively, called the open push-pull model. In this paper, to support automated recommendation of workers, we introduce an interoperability standard and computational method that facilitates the aggregation of job data while supporting scalability in response to increasing volumes of data. (i.e. workers and jobs continuously entering the system).

Generally, in crowdsourcing, providers advertise their task offerings (i.e. the open call model) largely to crowdworkers who subscribe their interest in working (i.e. subscription model). The combined open call and subscription model represent significant bottlenecks for recruitment in the paradigm of crowdsourcing. Consequently, attracting and retaining a crowd are the major challenges to the success of a crowdsourcing platform and forming a labor market. To address this problem, we introduce a worker-job matching model for crowdsourcing supported by a service-oriented architecture. The service-oriented architecture implements a push-pull mechanism and an underlying algorithm based on collaborative filtering techniques. Preliminary studies show that the infrastructure can effectively infer the levels of expertise of potential crowdworkers based on their profile and past performance history.

While the crowd sourcing paradigm facilitates the use of human-enacted resources from large groups of individuals, matching workers with jobs is limited by the need for these potential workers to proactively subscribe to various networks. This subscription phase is part of an "open call model" that reduces the ability for crowd sourcing platforms to scale or retain crowd-oriented workers. Leveraging collaborative filtering techniques, in this paper, we propose an alternative model that seeks to address the issue through a recommendation technique and system that exploits a push-pull model.

We investigate the decision-making and behavior of robotic biped goalkeepers, applied to the RoboCup 3D Soccer Simulation League. We introduce two approaches to the goalkeeper’s behavior: first a heuristics-based approach that uses linear regression and Kalman filters for improved perception, and another based on mental models which uses nonlinear regression for ball trajectory filtering. Our experiments consist of 30,000 kick-and-save tests, using 100 random angle and distance kicks from six distance categories and four angle categories repeated 30 times. Our benchmark results show that both proposed approaches bring significant improvements for the goalkeeper’s save success rates ( \(>\) 200 %) and validate the applicability of the novel mental model based decision-making process. These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Increasing popularity in the use of crowd sourcing has led to many tasks that can be fulfilled by the wisdom of human actors. When natural disasters or criminal activities occur, then sometimes crowd sourced tasks must be generated in real-time and must be fulfilled in an on-demand fashion. Effective use of crowd sourcing techniques requires an array of services that fulfil many dimensions of the overall problem such as resource selection and allocation, solution selection, and compensation. Any architecture that can provide these services in real-time, on demand requires a dynamic configurable infrastructure. This paper describes an adaptive framework for on-demand crowd sourced tasks supported by a design pattern-inspired architecture.

Despite the plethora of polls, surveys, and reports stating that most companies are embracing Big Data, there is slow adoption of Big Data technologies, like Hadoop, in enterprises. One of the primary reasons for this is that companies have significant investments in legacy languages and systems and the process of migrating to newer (Big Data) technologies would represent a substantial commitment of time and money, while threatening the ir short-term service quality and revenue goals. In this paper, we propose a possible solution that enables existing infrastructure to access Big Data systems via a services application programming interface (API); minimizing the migration drag and (possibly negative) business repercussions.

Crowd computing leverages human input in order to execute tasks that are computationally expensive, due to complexity and/or scale. Combined with automation, crowd computing can help solve problems efficiently and effectively. In this work, we introduce an elasticity framework that adaptively optimi