What did my AI learn? How data scientists make sense of model behavior
Data scientists require rich mental models of how AI systems behave to effectively train,
debug, and work with them. Despite the prevalence of AI analysis tools, there is no general …
debug, and work with them. Despite the prevalence of AI analysis tools, there is no general …
Datavoidant: An ai system for addressing political data voids on social media
The limited information (data voids) on political topics relevant to underrepresented
communities has facilitated the spread of disinformation. Independent journalists who …
communities has facilitated the spread of disinformation. Independent journalists who …
A systematic literature review of online collaborative story writing
S Montanelli, M Ruskov - IFIP Conference on Human-Computer …, 2023 - Springer
Collaboratively writing a narrative is a challenging task. Further complications emerge when
the involved contributors do not know each other, as it commonly occurs in online …
the involved contributors do not know each other, as it commonly occurs in online …
Cicero: Multi-turn, contextual argumentation for accurate crowdsourcing
Traditional approaches for ensuring high quality crowdwork have failed to achieve high-
accuracy on difficult problems. Aggregating redundant answers often fails on the hardest …
accuracy on difficult problems. Aggregating redundant answers often fails on the hardest …
GroundTruth: Augmenting expert image geolocation with crowdsourcing and shared representations
S Venkatagiri, J Thebault-Spieker, R Kohler… - Proceedings of the …, 2019 - dl.acm.org
Expert investigators bring advanced skills and deep experience to analyze visual evidence,
but they face limits on their time and attention. In contrast, crowds of novices can be highly …
but they face limits on their time and attention. In contrast, crowds of novices can be highly …
Evaluating the benefits of the immersive space to think
Sensemaking with large multimedia dataset is a cognitively intensive task that requires
analysts to understand the underlying stories that the dataset tells. Often, analysts use tools …
analysts to understand the underlying stories that the dataset tells. Often, analysts use tools …
Crowdsolve: Managing tensions in an expert-led crowdsourced investigation
Investigators in fields such as journalism and law enforcement have long sought the public's
help with investigations. New technologies have also allowed amateur sleuths to lead their …
help with investigations. New technologies have also allowed amateur sleuths to lead their …
Compete, collaborate, investigate: exploring the social structures of open source intelligence investigations
Online investigations are increasingly conducted by individuals with diverse skill levels and
experiences, with mixed results. Novice investigations often result in vigilantism or doxxing …
experiences, with mixed results. Novice investigations often result in vigilantism or doxxing …
How we write with crowds
MQ Feldman, BJ McInnis - Proceedings of the ACM on Human-Computer …, 2021 - dl.acm.org
Writing is a common task for crowdsourcing researchers exploring complex and creative
work. To better understand how we write with crowds, we conducted both a literature review …
work. To better understand how we write with crowds, we conducted both a literature review …
Sightbi: Exploring cross-view data relationships with biclusters
Multiple-view visualization (MV) has been heavily used in visual analysis tools for
sensemaking of data in various domains (eg, bioinformatics, cybersecurity and text …
sensemaking of data in various domains (eg, bioinformatics, cybersecurity and text …