Type of Publication: | Contribution to a conference collection |
Publication status: | Published |
URI (citable link): | http://nbn-resolving.de/urn:nbn:de:bsz:352-2-1dk03mfjgsyvb7 |
Author: | Sperrle, Fabian; Schlegel, Udo; El-Assady, Mennatallah; Keim, Daniel |
Year of publication: | 2019 |
Conference: | ACM CHI 2019 Workshop: Where is the Human? Bridging the Gap Between AI and HCI, May 4, 2019, Glasgow |
Published in: | ACM CHI 2019 Workshop: Where is the Human? Bridging the Gap Between AI and HCI |
URL of original publication: | http://bib.dbvis.de/uploadedFiles/Where_is_the_human_9.pdf, Last access on Mar 25, 2019 |
Summary: |
Human-in-the-loop model-building processes are increasingly popular as they incorporate human intuition and not easily externalized domain knowledge. However, we argue that the inclusion of the human, and in particular direct model manipulations, result in a high risk of creating biased models and results. We present a new approach of “Human Trust Modeling” that lets systems model the users’ intentions and deduce whether they have understood the underlying modeling processes and act coherently. Using this trust model, systems can enable or disable and encourage or discourage interactions to mitigate bias.
|
Subject (DDC): | 004 Computer Science |
Link to License: | In Copyright |
Bibliography of Konstanz: | Yes |
SPERRLE, Fabian, Udo SCHLEGEL, Mennatallah EL-ASSADY, Daniel KEIM, 2019. Human Trust Modeling for Bias Mitigation in Artificial Intelligence. ACM CHI 2019 Workshop: Where is the Human? Bridging the Gap Between AI and HCI. Glasgow, May 4, 2019. In: ACM CHI 2019 Workshop: Where is the Human? Bridging the Gap Between AI and HCI
@inproceedings{Sperrle2019Human-45547, title={Human Trust Modeling for Bias Mitigation in Artificial Intelligence}, url={http://bib.dbvis.de/uploadedFiles/Where_is_the_human_9.pdf}, year={2019}, booktitle={ACM CHI 2019 Workshop: Where is the Human? Bridging the Gap Between AI and HCI}, author={Sperrle, Fabian and Schlegel, Udo and El-Assady, Mennatallah and Keim, Daniel} }
<rdf:RDF xmlns:dcterms="http://purl.org/dc/terms/" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#" xmlns:bibo="http://purl.org/ontology/bibo/" xmlns:dspace="http://digital-repositories.org/ontologies/dspace/0.1.0#" xmlns:foaf="http://xmlns.com/foaf/0.1/" xmlns:void="http://rdfs.org/ns/void#" xmlns:xsd="http://www.w3.org/2001/XMLSchema#" > <rdf:Description rdf:about="https://kops.uni-konstanz.de/rdf/resource/123456789/45547"> <dc:contributor>Sperrle, Fabian</dc:contributor> <dc:language>eng</dc:language> <dcterms:rights rdf:resource="https://rightsstatements.org/page/InC/1.0/"/> <dspace:hasBitstream rdf:resource="https://kops.uni-konstanz.de/bitstream/123456789/45547/1/Sperrle_2-1dk03mfjgsyvb7.pdf"/> <foaf:homepage rdf:resource="http://localhost:8080/jspui"/> <dc:contributor>Keim, Daniel</dc:contributor> <dc:contributor>Schlegel, Udo</dc:contributor> <dspace:isPartOfCollection rdf:resource="https://kops.uni-konstanz.de/rdf/resource/123456789/36"/> <dc:creator>El-Assady, Mennatallah</dc:creator> <void:sparqlEndpoint rdf:resource="http://localhost/fuseki/dspace/sparql"/> <dc:contributor>El-Assady, Mennatallah</dc:contributor> <dcterms:abstract xml:lang="eng">Human-in-the-loop model-building processes are increasingly popular as they incorporate human intuition and not easily externalized domain knowledge. However, we argue that the inclusion of the human, and in particular direct model manipulations, result in a high risk of creating biased models and results. We present a new approach of “Human Trust Modeling” that lets systems model the users’ intentions and deduce whether they have understood the underlying modeling processes and act coherently. Using this trust model, systems can enable or disable and encourage or discourage interactions to mitigate bias.</dcterms:abstract> <dcterms:hasPart rdf:resource="https://kops.uni-konstanz.de/bitstream/123456789/45547/1/Sperrle_2-1dk03mfjgsyvb7.pdf"/> <dc:rights>terms-of-use</dc:rights> <dcterms:title>Human Trust Modeling for Bias Mitigation in Artificial Intelligence</dcterms:title> <dc:date rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2019-03-25T13:29:25Z</dc:date> <dcterms:issued>2019</dcterms:issued> <dc:creator>Schlegel, Udo</dc:creator> <dcterms:available rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2019-03-25T13:29:25Z</dcterms:available> <dcterms:isPartOf rdf:resource="https://kops.uni-konstanz.de/rdf/resource/123456789/36"/> <dc:creator>Keim, Daniel</dc:creator> <bibo:uri rdf:resource="https://kops.uni-konstanz.de/handle/123456789/45547"/> <dc:creator>Sperrle, Fabian</dc:creator> </rdf:Description> </rdf:RDF>
Sperrle_2-1dk03mfjgsyvb7.pdf | 129 |