Supporting and Transforming High-Stakes Investigations with Expert-Led Crowdsourcing

Simple item page
dc.contributor.authorVenkatagiri, Sukriten
dc.contributor.committeechairLuther, Kurten
dc.contributor.committeememberMitra, Tanushreeen
dc.contributor.committeememberNorth, Christopher L.en
dc.contributor.committeememberStarbird, Kateen
dc.contributor.committeememberRho, Ha Rimen
dc.contributor.departmentComputer Science and Applicationsen
dc.date.accessioned2022-12-21T09:00:19Zen
dc.date.available2022-12-21T09:00:19Zen
dc.date.issued2022-12-20en
dc.description.abstractExpert investigators leverage their advanced skills and deep experience to solve complex investigations, but they face limits on their time and attention. In contrast, crowds of novices can be highly scalable and parallelizable, but lack expertise and may engage in vigilante behavior. In this dissertation, I introduce and evaluate the framework of expert-led crowdsourcing through three studies across two domains, journalism and law enforcement. First, through an ethnographic study of two law enforcement murder investigations, I uncover tensions in a real-world crowdsourced investigation and introduce the expert-led crowdsourcing framework. Second, I instantiate expert-led crowdsourcing in two collaboration systems: GroundTruth and CuriOSINTy. GroundTruth is focused on one specific investigative task, image geolocation. CuriOSINTy expands the flexibility and scope of expert-led crowdsourcing to handle more complex and multiple investigative tasks: identifying and debunking misinformation. Third, I introduce a framework for understanding how expert-led crowdsourced investigations work and how to better support them. Finally, I conclude with a discussion of how expert-led crowdsourcing enables experts and crowds to do more than either could alone, as well as how it can be generalized to other domains.en
dc.description.abstractgeneralExpert investigators leverage their advanced skills and deep experience to solve complex investigations, but they face limits on their time and attention. In contrast, there is growing interest among non-professional members of the public to participate in investigations, but they lack the expertise or may engage in harmful behavior. In this dissertation, I introduce a new concept called, expert-led crowdsourcing, that allows professionals and non-professionals to work together on a high-stakes investigations in two domains: journalism and law enforcement. First, I explored how expert-led crowdsourcing played out in CrowdSolve, a real-world investigation of two decades-old murder cases. At CrowdSolve, over 250 amateur sleuths supported eight law enforcement experts to uncover new leads two for the two cases. Second, I build two software applications, GroundTruth and CuriOSINTy, to better support expert-led crowdsourced investigations. GroundTruth helps investigators work with a crowd to find the exact geographic location where a photo was taken. CuriOSINTy extends GroundTruth's capabilities to help investigators with more complex and multiple investigative tasks involved in identifying and debunking misinformation on social media. Third, I compared and contrasted the three prior studies to develop a more detailed understanding of expert-led crowdsourced investigations and how to better support them. Finally, I conclude with a discussion of how expert-led crowdsourcing enables experts and crowds to do more than either could alone, as well as how it can be used in other professions.en
dc.description.degreeDoctor of Philosophyen
dc.format.mediumETDen
dc.identifier.othervt_gsexam:35757en
dc.identifier.urihttp://hdl.handle.net/10919/112963en
dc.language.isoenen
dc.publisherVirginia Techen
dc.rightsCreative Commons Attribution-NonCommercial-ShareAlike 4.0 Internationalen
dc.rights.urihttp://creativecommons.org/licenses/by-nc-sa/4.0/en
dc.subjectexpert-led crowdsourcingen
dc.subjectcrowdsourcingen
dc.subjectexpertsen
dc.subjectinvestigationsen
dc.subjectsensemakingen
dc.subjecthuman–computer interactionen
dc.subjectcomputer-supported collaborative worken
dc.subjectHCIen
dc.subjectCSCWen
dc.titleSupporting and Transforming High-Stakes Investigations with Expert-Led Crowdsourcingen
dc.typeDissertationen
thesis.degree.disciplineComputer Science and Applicationsen
thesis.degree.grantorVirginia Polytechnic Institute and State Universityen
thesis.degree.leveldoctoralen
thesis.degree.nameDoctor of Philosophyen

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Venkatagiri_S_D_2022.pdf
Size:
15.6 MB
Format:
Adobe Portable Document Format
Download

Collections

Doctoral Dissertations