Crowd4ems: A Crowdsourcing Platform for Gathering And Geolocating Social Media Content in Disaster Response

Abstract

<p><strong>Abstract.</strong> Increase in access to mobile phone devices and social media networks has changed the way people report and respond to disasters. Community-driven initiatives such as Stand By Task Force (SBTF) or GISCorps have shown great potential by crowdsourcing the acquisition, analysis, and geolocation of social media data for disaster responders. These initiatives face two main challenges: (1) most of social media content such as photos and videos are not geolocated, thus preventing the information to be used by emergency responders, and (2) they lack tools to manage volunteers contributions and aggregate them in order to ensure high quality and reliable results. This paper illustrates the use of a crowdsourcing platform that combines automatic methods for gathering information from social media and crowdsourcing techniques, in order to manage and aggregate volunteers contributions. High precision geolocation is achieved by combining data mining techniques for estimating the location of photos and videos from social media, and crowdsourcing for the validation and/or improvement of the estimated location. The evaluation of the proposed approach is carried out using data related to the Amatrice Earthquake in 2016, coming from Flickr, Twitter and Youtube. A common data set is analyzed and geolocated by both the volunteers using the proposed platform and a group of experts. Data quality and data reliability is assessed by comparing volunteers versus experts results. Final results are shown in a web map service providing a global view of the information social media provided about the Amatrice Earthquake event.</p>

A Conceptual Probabilistic Framework for Annotation Aggregation of Citizen Science Data

“…Hence, we contacted a group of ten experts with prior knowledge of disaster response and crisis data. We presented the set of 907 images as tasks to the experts via the Crowd4EMS platform [32]. Crowd4EMS combines automatic methods for gathering information from social media and crowdsourcing techniques, in order to manage and aggregate volunteers' contributions.…”

Analyzing social media with crowdsourcing in Crowd4SDG

“…As mentioned in Section 3.5, crowdsourcing was performed using three different groups of citizens to annotate the relevant images and the severity of damage seen in the photos by humans compared to the AIDR. Specifically, to obtain a ground truth for the labels, we first worked with ten disaster experts and configured a redundancy of 3 for annotations on the Crowd4EMS platform [39], a precursor of CSPB. We then referred to a group of 50 volunteers on Crowd4EMS with a redundancy of 3.…”

“…Social media analysis, including both an automatic analysis of images contained in posts and the collaboration of human computing, has been discussed by several authors in the literature, for example, [2,21,39]. For automatic analysis of images, many recent approaches are based on AI and in particular neural networks, for example, [24,32,35].…”

Image-Based Social Sensing: Combining AI and the Crowd to Mine Policy-Adherence Indicators from Twitter

“…Availability of a committed crowd within the given time [33] and vast volumes of data [34] is often a challenge and a limiting factor for crowdsourcing initiatives. While federating existing communities [35] can ensure commitment, the volume of tasks could hinder the community in sustaining the interest. Volunteer crowdsourcing initiatives are not incentivized and are often motivated by factors including, but not limited to altruism, peer-indulgence, curiosity, fun and in some cases because of the organization that conducts the initiative.…”