Crowdsourced annotation is vital to both collecting labelled data to tra...
A key challenge in professional fact-checking is its limited scalability...
Automatically assigning tasks to people is challenging because human
per...
Algorithmic bias often arises as a result of differential subgroup valid...
Human-AI complementarity is important when neither the algorithm nor the...
In evaluation campaigns, participants often explore variations of popula...
Misinformation threatens modern society by promoting distrust in science...
How can we better understand the broad, diverse, shifting, and invisible...
When annotators label data, a key metric for quality assurance is
inter-...
Developing methods to adversarially challenge NLP systems is a promising...
Recent work has emphasized the importance of balancing competing objecti...
We present ProtoTEx, a novel white-box NLP classification architecture b...
We conducted a lab-based eye-tracking study to investigate how the
inter...
In hybrid human-machine deferral frameworks, a classifier can defer unce...
We propose a novel three-stage FIND-RESOLVE-LABEL workflow for crowdsour...
This volume contains the position papers presented at CSCW 2021 Workshop...
The efficacy of machine learning (ML) models depends on both algorithms ...
Fact-checking is the process (human, automated, or hybrid) by which clai...
Building a benchmark dataset for hate speech detection presents several
...
Human-machine complementarity is important when neither the algorithm no...
We consider a class of variable effort human annotation tasks in which t...
Machine learning models are often implemented in cohort with humans in t...
Shared-task campaigns such as NIST TREC select documents to judge by poo...
Hate speech detection research has predominantly focused on purely
conte...
While search efficacy has been evaluated traditionally on the basis of r...
The effect of user bias in fact-checking has not been explored extensive...
Crowdsourcing offers an affordable and scalable means to collect relevan...
Though detection systems have been developed to identify obscene content...
Though detection systems have been developed to identify obscene content...
Because researchers typically do not have the time or space to present m...
To create a new IR test collection at minimal cost, we must carefully se...
A fundamental advantage of neural models for NLP is their ability to lea...
We propose a new active learning (AL) method for text classification wit...
TurKontrol, and algorithm presented in (Dai et al. 2010), uses a POMDP t...
This paper considers the challenge of evaluating a set of classifiers, a...
This paper tackles temporal resolution of documents, such as determining...