Crowdsourcing

About: Crowdsourcing is a research topic. Over the lifetime, 12889 publications have been published within this topic receiving 230638 citations.

Crowdsourcing for on-street smart parking

Abstract: Crowdsourcing has inspired a variety of novel mobile applications. However, identifying common practices across different applications is still challenging. In this paper, we use smart parking as a case study to investigate features of crowdsourcing that may apply to other mobile applications. Based on this we derive principles for efficiently harnessing crowdsourcing. We draw three key guidelines: First, we suggest that that the organizer can play an important role in coordinating participants', a key factor to successful crowdsourcing experience. Second, we suggest that the expected participation rate is a key factor when designing the crowdsourcing system: a system with a lower expected participation rate will place a higher burden in individual participants (e.g., through more complex interfaces that aim to improve the accuracy of the collected data). Finally, we suggest that not only above certain threshold of contributors, a crowdsourcing-based system is resilient to freeriding but, surprisingly, that including freeriders (i.e., actors that do not participate in system effort but share its benefits in terms of coordination) benefits the entire system.

The Value of Marketing Crowdsourced New Products as Such: Evidence from two Randomized Field Experiments

Abstract: To complement their in-house, designer-driven efforts, companies are increasingly experimenting with crowdsourcing initiatives in which they invite their user communities to generate new product ideas. Although innovation scholars have begun to analyze the objective promise of crowdsourcing, the current research is unique in pointing out that merely marketing the source of design to customers might bring about an incremental increase in product sales. The findings from two randomized field experiments reveal that labeling crowdsourced new products as such—that is, marketing the product as “customer-ideated” at the point of purchase versus not mentioning the specific source of design—increased the product’s actual market performance by up to 20%. Two controlled follow-up studies reveal that the effect observed in two distinct consumer goods domains (food and electronics) can be attributed to a quality inference: consumers perceive “customer-ideated” products to be based on ideas that address their ...

New Strategies for Image Annotation: Overview of the Photo Annotation Task at ImageCLEF 2010

Abstract: The ImageCLEF 2010 Photo Annotation Task poses the challenge of automated annotation of 93 visual concepts in Flickr photos. The participants were provided with a training set of 8,000 Flickr im- ages including annotations, EXIF data and Flickr user tags. Testing was performed on 10,000 Flickr images, dierentiated between approaches considering solely visual information, approaches relying on textual in- formation and multi-modal approaches. Half of the ground truth was acquired with a crowdsourcing approach. The evaluation followed two evaluation paradigms: per concept and per example. In total, 17 research teams participated in the multi-label classification challenge with 63 sub- missions. Summarizing the results, the task could be solved with a MAP of 0.455 in the multi-modal configuration, with a MAP of 0.407 in the visual-only configuration and with a MAP of 0.234 in the textual con- figuration. For the evaluation per example, 0.66 F-ex and 0.66 OS-FCS could be achieved for the multi-modal configuration, 0.68 F-ex and 0.65 OS-FCS for the visual configuration and 0.26 F-ex and 0.37 OS-FCS for the textual configuration.

Crowd-Based Deduplication: An Adaptive Approach

Abstract: Data deduplication stands as a building block for data integration and data cleaning. The state-of-the-art techniques focus on how to exploit crowdsourcing to improve the accuracy of deduplication. However, they either incur significant overheads on the crowd or offer inferior accuracy. This paper presents ACD, a new crowd-based algorithm for data deduplication. The basic idea of ACD is to adopt correlation clustering (which is a classic machine-based algorithm for data deduplication) under a crowd-based setting. We propose non-trivial techniques to reduce the time required in performing correlation clustering with the crowd, and devise methods to postprocess the results of correlation clustering for better accuracy of deduplication. With extensive experiments on the Amazon Mechanical Turk, we demonstrate that ACD outperforms the states of the art by offering a high precision of deduplication while incurring moderate crowdsourcing overheads.

A Platform for Urban Analytics and Semantic Data Integration in City Planning

Abstract: This paper presents a novel web-based platform that supports the analysis, integration, and visualization of large-scale and heterogeneous urban data, with application to city planning and decision-making. Motivated by the non-scalable character of conventional urban analytics methods, as well as by the interoperability challenges present in contemporary data silos, the illustrated system – coined SocialGlass – leverages the combined potential of diverse urban data sources. These include sensor and social media streams (Twitter, Instagram, Foursquare), publicly available municipal records, and resources from knowledge repositories. Through data science, semantic integration, and crowdsourcing techniques the platform enables the mapping of demographic information, human movement patterns, place popularity, traffic conditions, as well as citizens’ and visitors’ opinions and preferences about specific venues in a city. The paper further demonstrates an implemented prototype of the platform and its deployment in real-world use cases for monitoring, analyzing, and assessing city-scale events.