MULTI-CASE: A Transformer-based Ethics-aware Multimodal Investigative Intelligence Framework

AI-driven models are increasingly deployed in operational analytics solutions, for instance, in investigative journalism or the intelligence community. Current approaches face two primary challenges: ethical and privacy concerns, as well as difficulties in efficiently combining heterogeneous data so...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Fischer, Maximilian T, Metz, Yannick, Joos, Lucas, Miller, Matthias, Keim, Daniel A
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title
container_volume
creator Fischer, Maximilian T
Metz, Yannick
Joos, Lucas
Miller, Matthias
Keim, Daniel A
description AI-driven models are increasingly deployed in operational analytics solutions, for instance, in investigative journalism or the intelligence community. Current approaches face two primary challenges: ethical and privacy concerns, as well as difficulties in efficiently combining heterogeneous data sources for multimodal analytics. To tackle the challenge of multimodal analytics, we present MULTI-CASE, a holistic visual analytics framework tailored towards ethics-aware and multimodal intelligence exploration, designed in collaboration with domain experts. It leverages an equal joint agency between human and AI to explore and assess heterogeneous information spaces, checking and balancing automation through Visual Analytics. MULTI-CASE operates on a fully-integrated data model and features type-specific analysis with multiple linked components, including a combined search, annotated text view, and graph-based analysis. Parts of the underlying entity detection are based on a RoBERTa-based language model, which we tailored towards user requirements through fine-tuning. An overarching knowledge exploration graph combines all information streams, provides in-situ explanations, transparent source attribution, and facilitates effective exploration. To assess our approach, we conducted a comprehensive set of evaluations: We benchmarked the underlying language model on relevant NER tasks, achieving state-of-the-art performance. The demonstrator was assessed according to intelligence capability assessments, while the methodology was evaluated according to ethics design guidelines. As a case study, we present our framework in an investigative journalism setting, supporting war crime investigations. Finally, we conduct a formative user evaluation with domain experts in law enforcement. Our evaluations confirm that our framework facilitates human agency and steering in security-sensitive applications.
doi_str_mv 10.48550/arxiv.2401.01955
format Article
fullrecord <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_2401_01955</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2401_01955</sourcerecordid><originalsourceid>FETCH-LOGICAL-a675-2ea8cf45bdb91b369ea027580dc4a0e03afecd0da3ce3b51662f04bd477a4a833</originalsourceid><addsrcrecordid>eNotz71OwzAYhWEvDKhwAUz4Bhyc2M4PWxSlECkVA-lWKfpsfykW-UFOSOHuoYXp6F2O9BByF_JApkrxB_Bfbg0iycOAh5lS1-Sw29dNxYr8tXykOW08jHM3-QE90zCjpeXy5szM4AQe6e6zX9wwWehpNa44L-4Ii1vxtxbse3fE0SDdehjwNPn3G3LVQT_j7f9uSLMtm-KZ1S9PVZHXDOJEsQghNZ1U2uos1CLOEHiUqJRbI4EjF9ChsdyCMCi0CuM46rjUViYJSEiF2JD7v9sLr_3wbgD_3Z6Z7YUpfgACw041</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>MULTI-CASE: A Transformer-based Ethics-aware Multimodal Investigative Intelligence Framework</title><source>arXiv.org</source><creator>Fischer, Maximilian T ; Metz, Yannick ; Joos, Lucas ; Miller, Matthias ; Keim, Daniel A</creator><creatorcontrib>Fischer, Maximilian T ; Metz, Yannick ; Joos, Lucas ; Miller, Matthias ; Keim, Daniel A</creatorcontrib><description>AI-driven models are increasingly deployed in operational analytics solutions, for instance, in investigative journalism or the intelligence community. Current approaches face two primary challenges: ethical and privacy concerns, as well as difficulties in efficiently combining heterogeneous data sources for multimodal analytics. To tackle the challenge of multimodal analytics, we present MULTI-CASE, a holistic visual analytics framework tailored towards ethics-aware and multimodal intelligence exploration, designed in collaboration with domain experts. It leverages an equal joint agency between human and AI to explore and assess heterogeneous information spaces, checking and balancing automation through Visual Analytics. MULTI-CASE operates on a fully-integrated data model and features type-specific analysis with multiple linked components, including a combined search, annotated text view, and graph-based analysis. Parts of the underlying entity detection are based on a RoBERTa-based language model, which we tailored towards user requirements through fine-tuning. An overarching knowledge exploration graph combines all information streams, provides in-situ explanations, transparent source attribution, and facilitates effective exploration. To assess our approach, we conducted a comprehensive set of evaluations: We benchmarked the underlying language model on relevant NER tasks, achieving state-of-the-art performance. The demonstrator was assessed according to intelligence capability assessments, while the methodology was evaluated according to ethics design guidelines. As a case study, we present our framework in an investigative journalism setting, supporting war crime investigations. Finally, we conduct a formative user evaluation with domain experts in law enforcement. Our evaluations confirm that our framework facilitates human agency and steering in security-sensitive applications.</description><identifier>DOI: 10.48550/arxiv.2401.01955</identifier><language>eng</language><subject>Computer Science - Human-Computer Interaction ; Computer Science - Multimedia</subject><creationdate>2024-01</creationdate><rights>http://arxiv.org/licenses/nonexclusive-distrib/1.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,780,885</link.rule.ids><linktorsrc>$$Uhttps://arxiv.org/abs/2401.01955$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.2401.01955$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Fischer, Maximilian T</creatorcontrib><creatorcontrib>Metz, Yannick</creatorcontrib><creatorcontrib>Joos, Lucas</creatorcontrib><creatorcontrib>Miller, Matthias</creatorcontrib><creatorcontrib>Keim, Daniel A</creatorcontrib><title>MULTI-CASE: A Transformer-based Ethics-aware Multimodal Investigative Intelligence Framework</title><description>AI-driven models are increasingly deployed in operational analytics solutions, for instance, in investigative journalism or the intelligence community. Current approaches face two primary challenges: ethical and privacy concerns, as well as difficulties in efficiently combining heterogeneous data sources for multimodal analytics. To tackle the challenge of multimodal analytics, we present MULTI-CASE, a holistic visual analytics framework tailored towards ethics-aware and multimodal intelligence exploration, designed in collaboration with domain experts. It leverages an equal joint agency between human and AI to explore and assess heterogeneous information spaces, checking and balancing automation through Visual Analytics. MULTI-CASE operates on a fully-integrated data model and features type-specific analysis with multiple linked components, including a combined search, annotated text view, and graph-based analysis. Parts of the underlying entity detection are based on a RoBERTa-based language model, which we tailored towards user requirements through fine-tuning. An overarching knowledge exploration graph combines all information streams, provides in-situ explanations, transparent source attribution, and facilitates effective exploration. To assess our approach, we conducted a comprehensive set of evaluations: We benchmarked the underlying language model on relevant NER tasks, achieving state-of-the-art performance. The demonstrator was assessed according to intelligence capability assessments, while the methodology was evaluated according to ethics design guidelines. As a case study, we present our framework in an investigative journalism setting, supporting war crime investigations. Finally, we conduct a formative user evaluation with domain experts in law enforcement. Our evaluations confirm that our framework facilitates human agency and steering in security-sensitive applications.</description><subject>Computer Science - Human-Computer Interaction</subject><subject>Computer Science - Multimedia</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNotz71OwzAYhWEvDKhwAUz4Bhyc2M4PWxSlECkVA-lWKfpsfykW-UFOSOHuoYXp6F2O9BByF_JApkrxB_Bfbg0iycOAh5lS1-Sw29dNxYr8tXykOW08jHM3-QE90zCjpeXy5szM4AQe6e6zX9wwWehpNa44L-4Ii1vxtxbse3fE0SDdehjwNPn3G3LVQT_j7f9uSLMtm-KZ1S9PVZHXDOJEsQghNZ1U2uos1CLOEHiUqJRbI4EjF9ChsdyCMCi0CuM46rjUViYJSEiF2JD7v9sLr_3wbgD_3Z6Z7YUpfgACw041</recordid><startdate>20240103</startdate><enddate>20240103</enddate><creator>Fischer, Maximilian T</creator><creator>Metz, Yannick</creator><creator>Joos, Lucas</creator><creator>Miller, Matthias</creator><creator>Keim, Daniel A</creator><scope>AKY</scope><scope>GOX</scope></search><sort><creationdate>20240103</creationdate><title>MULTI-CASE: A Transformer-based Ethics-aware Multimodal Investigative Intelligence Framework</title><author>Fischer, Maximilian T ; Metz, Yannick ; Joos, Lucas ; Miller, Matthias ; Keim, Daniel A</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a675-2ea8cf45bdb91b369ea027580dc4a0e03afecd0da3ce3b51662f04bd477a4a833</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><topic>Computer Science - Human-Computer Interaction</topic><topic>Computer Science - Multimedia</topic><toplevel>online_resources</toplevel><creatorcontrib>Fischer, Maximilian T</creatorcontrib><creatorcontrib>Metz, Yannick</creatorcontrib><creatorcontrib>Joos, Lucas</creatorcontrib><creatorcontrib>Miller, Matthias</creatorcontrib><creatorcontrib>Keim, Daniel A</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Fischer, Maximilian T</au><au>Metz, Yannick</au><au>Joos, Lucas</au><au>Miller, Matthias</au><au>Keim, Daniel A</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>MULTI-CASE: A Transformer-based Ethics-aware Multimodal Investigative Intelligence Framework</atitle><date>2024-01-03</date><risdate>2024</risdate><abstract>AI-driven models are increasingly deployed in operational analytics solutions, for instance, in investigative journalism or the intelligence community. Current approaches face two primary challenges: ethical and privacy concerns, as well as difficulties in efficiently combining heterogeneous data sources for multimodal analytics. To tackle the challenge of multimodal analytics, we present MULTI-CASE, a holistic visual analytics framework tailored towards ethics-aware and multimodal intelligence exploration, designed in collaboration with domain experts. It leverages an equal joint agency between human and AI to explore and assess heterogeneous information spaces, checking and balancing automation through Visual Analytics. MULTI-CASE operates on a fully-integrated data model and features type-specific analysis with multiple linked components, including a combined search, annotated text view, and graph-based analysis. Parts of the underlying entity detection are based on a RoBERTa-based language model, which we tailored towards user requirements through fine-tuning. An overarching knowledge exploration graph combines all information streams, provides in-situ explanations, transparent source attribution, and facilitates effective exploration. To assess our approach, we conducted a comprehensive set of evaluations: We benchmarked the underlying language model on relevant NER tasks, achieving state-of-the-art performance. The demonstrator was assessed according to intelligence capability assessments, while the methodology was evaluated according to ethics design guidelines. As a case study, we present our framework in an investigative journalism setting, supporting war crime investigations. Finally, we conduct a formative user evaluation with domain experts in law enforcement. Our evaluations confirm that our framework facilitates human agency and steering in security-sensitive applications.</abstract><doi>10.48550/arxiv.2401.01955</doi><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier DOI: 10.48550/arxiv.2401.01955
ispartof
issn
language eng
recordid cdi_arxiv_primary_2401_01955
source arXiv.org
subjects Computer Science - Human-Computer Interaction
Computer Science - Multimedia
title MULTI-CASE: A Transformer-based Ethics-aware Multimodal Investigative Intelligence Framework
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-10T17%3A53%3A46IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-arxiv_GOX&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=MULTI-CASE:%20A%20Transformer-based%20Ethics-aware%20Multimodal%20Investigative%20Intelligence%20Framework&rft.au=Fischer,%20Maximilian%20T&rft.date=2024-01-03&rft_id=info:doi/10.48550/arxiv.2401.01955&rft_dat=%3Carxiv_GOX%3E2401_01955%3C/arxiv_GOX%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true