Making machine intelligence less scary for criminal analysts: reflections on designing a visual comparative case analysis tool View Full Text


Ontology type: schema:ScholarlyArticle      Open Access: True


Article Info

DATE

2018-02-16

AUTHORS

Wolfgang Jentner, Dominik Sacha, Florian Stoffel, Geoffrey Ellis, Leishi Zhang, Daniel A. Keim

ABSTRACT

A fundamental task in criminal intelligence analysis is to analyze the similarity of crime cases, called comparative case analysis (CCA), to identify common crime patterns and to reason about unsolved crimes. Typically, the data are complex and high dimensional and the use of complex analytical processes would be appropriate. State-of-the-art CCA tools lack flexibility in interactive data exploration and fall short of computational transparency in terms of revealing alternative methods and results. In this paper, we report on the design of the Concept Explorer, a flexible, transparent and interactive CCA system. During this design process, we observed that most criminal analysts are not able to understand the underlying complex technical processes, which decrease the users’ trust in the results and hence a reluctance to use the tool. Our CCA solution implements a computational pipeline together with a visual platform that allows the analysts to interact with each stage of the analysis process and to validate the result. The proposed visual analytics workflow iteratively supports the interpretation of the results of clustering with the respective feature relations, the development of alternative models, as well as cluster verification. The visualizations offer an understandable and usable way for the analyst to provide feedback to the system and to observe the impact of their interactions. Expert feedback confirmed that our user-centered design decisions made this computational complexity less scary to criminal analysts. More... »

PAGES

1225-1241

References to SciGraph publications

Identifiers

URI

http://scigraph.springernature.com/pub.10.1007/s00371-018-1483-0

DOI

http://dx.doi.org/10.1007/s00371-018-1483-0

DIMENSIONS

https://app.dimensions.ai/details/publication/pub.1101082300


Indexing Status Check whether this publication has been indexed by Scopus and Web Of Science using the SN Indexing Status Tool
Incoming Citations Browse incoming citations for this publication using opencitations.net

JSON-LD is the canonical representation for SciGraph data.

TIP: You can open this SciGraph record using an external JSON-LD service: JSON-LD Playground Google SDTT

[
  {
    "@context": "https://springernature.github.io/scigraph/jsonld/sgcontext.json", 
    "about": [
      {
        "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/08", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "name": "Information and Computing Sciences", 
        "type": "DefinedTerm"
      }, 
      {
        "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/0801", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "name": "Artificial Intelligence and Image Processing", 
        "type": "DefinedTerm"
      }, 
      {
        "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/0806", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "name": "Information Systems", 
        "type": "DefinedTerm"
      }
    ], 
    "author": [
      {
        "affiliation": {
          "alternateName": "Universit\u00e4t Konstanz, Universit\u00e4tsstra\u00dfe 10, 78464, Konstanz, Germany", 
          "id": "http://www.grid.ac/institutes/grid.9811.1", 
          "name": [
            "Universit\u00e4t Konstanz, Universit\u00e4tsstra\u00dfe 10, 78464, Konstanz, Germany"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Jentner", 
        "givenName": "Wolfgang", 
        "id": "sg:person.010324047633.88", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.010324047633.88"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Universit\u00e4t Konstanz, Universit\u00e4tsstra\u00dfe 10, 78464, Konstanz, Germany", 
          "id": "http://www.grid.ac/institutes/grid.9811.1", 
          "name": [
            "Universit\u00e4t Konstanz, Universit\u00e4tsstra\u00dfe 10, 78464, Konstanz, Germany"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Sacha", 
        "givenName": "Dominik", 
        "id": "sg:person.01311725047.83", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01311725047.83"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Universit\u00e4t Konstanz, Universit\u00e4tsstra\u00dfe 10, 78464, Konstanz, Germany", 
          "id": "http://www.grid.ac/institutes/grid.9811.1", 
          "name": [
            "Universit\u00e4t Konstanz, Universit\u00e4tsstra\u00dfe 10, 78464, Konstanz, Germany"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Stoffel", 
        "givenName": "Florian", 
        "id": "sg:person.0634434147.05", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0634434147.05"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Universit\u00e4t Konstanz, Universit\u00e4tsstra\u00dfe 10, 78464, Konstanz, Germany", 
          "id": "http://www.grid.ac/institutes/grid.9811.1", 
          "name": [
            "Universit\u00e4t Konstanz, Universit\u00e4tsstra\u00dfe 10, 78464, Konstanz, Germany"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Ellis", 
        "givenName": "Geoffrey", 
        "id": "sg:person.0750662547.01", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0750662547.01"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Middlesex University, London, UK", 
          "id": "http://www.grid.ac/institutes/grid.15822.3c", 
          "name": [
            "Middlesex University, London, UK"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Zhang", 
        "givenName": "Leishi", 
        "id": "sg:person.01204645707.14", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01204645707.14"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Universit\u00e4t Konstanz, Universit\u00e4tsstra\u00dfe 10, 78464, Konstanz, Germany", 
          "id": "http://www.grid.ac/institutes/grid.9811.1", 
          "name": [
            "Universit\u00e4t Konstanz, Universit\u00e4tsstra\u00dfe 10, 78464, Konstanz, Germany"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Keim", 
        "givenName": "Daniel A.", 
        "id": "sg:person.0635776571.01", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0635776571.01"
        ], 
        "type": "Person"
      }
    ], 
    "citation": [
      {
        "id": "sg:pub.10.1007/978-3-540-70904-6_6", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1018081363", 
          "https://doi.org/10.1007/978-3-540-70904-6_6"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/978-3-642-37453-1_5", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1009568116", 
          "https://doi.org/10.1007/978-3-642-37453-1_5"
        ], 
        "type": "CreativeWork"
      }
    ], 
    "datePublished": "2018-02-16", 
    "datePublishedReg": "2018-02-16", 
    "description": "A fundamental task in criminal intelligence analysis is to analyze the similarity of crime cases, called comparative case analysis (CCA), to identify common crime patterns and to reason about unsolved crimes. Typically, the data are complex and high dimensional and the use of complex analytical processes would be appropriate. State-of-the-art CCA tools lack flexibility in interactive data exploration and fall short of computational transparency in terms of revealing alternative methods and results. In this paper, we report on the design of the Concept Explorer, a flexible, transparent and interactive CCA system. During this design process, we observed that most criminal analysts are not able to understand the underlying complex technical processes, which decrease the users\u2019 trust in the results and hence a reluctance to use the tool. Our CCA solution implements a computational pipeline together with a visual platform that allows the analysts to interact with each stage of the analysis process and to validate the result. The proposed visual analytics workflow iteratively supports the interpretation of the results of clustering with the respective feature relations, the development of alternative models, as well as cluster verification. The visualizations offer an understandable and usable way for the analyst to provide feedback to the system and to observe the impact of their interactions. Expert feedback confirmed that our user-centered design decisions made this computational complexity less scary to criminal analysts.", 
    "genre": "article", 
    "id": "sg:pub.10.1007/s00371-018-1483-0", 
    "isAccessibleForFree": true, 
    "isFundedItemOf": [
      {
        "id": "sg:grant.3793901", 
        "type": "MonetaryGrant"
      }
    ], 
    "isPartOf": [
      {
        "id": "sg:journal.1046897", 
        "issn": [
          "0178-2789", 
          "1432-2315"
        ], 
        "name": "The Visual Computer", 
        "publisher": "Springer Nature", 
        "type": "Periodical"
      }, 
      {
        "issueNumber": "9", 
        "type": "PublicationIssue"
      }, 
      {
        "type": "PublicationVolume", 
        "volumeNumber": "34"
      }
    ], 
    "keywords": [
      "criminal analysts", 
      "interactive data exploration", 
      "criminal intelligence analysis", 
      "complex analytical processes", 
      "visual analytics", 
      "user trust", 
      "machine intelligence", 
      "computational transparency", 
      "data exploration", 
      "computational complexity", 
      "visual platform", 
      "intelligence analysis", 
      "fundamental task", 
      "complex technical processes", 
      "usable way", 
      "feature relations", 
      "design decisions", 
      "analysis process", 
      "analysis tools", 
      "design process", 
      "expert feedback", 
      "crime patterns", 
      "CCA system", 
      "computational pipeline", 
      "unsolved crimes", 
      "analysts", 
      "crime cases", 
      "technical processes", 
      "analytics", 
      "tool", 
      "analytical process", 
      "trust", 
      "intelligence", 
      "comparative case analysis", 
      "CCA solution", 
      "feedback", 
      "task", 
      "platform", 
      "verification", 
      "system", 
      "visualization", 
      "complexity", 
      "case analysis", 
      "pipeline", 
      "flexibility", 
      "process", 
      "decisions", 
      "Explorer", 
      "design", 
      "exploration", 
      "results", 
      "transparency", 
      "solution", 
      "way", 
      "model", 
      "similarity", 
      "data", 
      "method", 
      "alternative method", 
      "terms", 
      "use", 
      "analysis", 
      "state", 
      "development", 
      "crime", 
      "reasons", 
      "patterns", 
      "alternative models", 
      "interpretation", 
      "stage", 
      "interaction", 
      "cases", 
      "impact", 
      "relation", 
      "reluctance", 
      "reflection", 
      "paper"
    ], 
    "name": "Making machine intelligence less scary for criminal analysts: reflections on designing a visual comparative case analysis tool", 
    "pagination": "1225-1241", 
    "productId": [
      {
        "name": "dimensions_id", 
        "type": "PropertyValue", 
        "value": [
          "pub.1101082300"
        ]
      }, 
      {
        "name": "doi", 
        "type": "PropertyValue", 
        "value": [
          "10.1007/s00371-018-1483-0"
        ]
      }
    ], 
    "sameAs": [
      "https://doi.org/10.1007/s00371-018-1483-0", 
      "https://app.dimensions.ai/details/publication/pub.1101082300"
    ], 
    "sdDataset": "articles", 
    "sdDatePublished": "2022-09-02T16:03", 
    "sdLicense": "https://scigraph.springernature.com/explorer/license/", 
    "sdPublisher": {
      "name": "Springer Nature - SN SciGraph project", 
      "type": "Organization"
    }, 
    "sdSource": "s3://com-springernature-scigraph/baseset/20220902/entities/gbq_results/article/article_784.jsonl", 
    "type": "ScholarlyArticle", 
    "url": "https://doi.org/10.1007/s00371-018-1483-0"
  }
]
 

Download the RDF metadata as:  json-ld nt turtle xml License info

HOW TO GET THIS DATA PROGRAMMATICALLY:

JSON-LD is a popular format for linked data which is fully compatible with JSON.

curl -H 'Accept: application/ld+json' 'https://scigraph.springernature.com/pub.10.1007/s00371-018-1483-0'

N-Triples is a line-based linked data format ideal for batch operations.

curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/pub.10.1007/s00371-018-1483-0'

Turtle is a human-readable linked data format.

curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/s00371-018-1483-0'

RDF/XML is a standard XML format for linked data.

curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/s00371-018-1483-0'


 

This table displays all metadata directly associated to this object as RDF triples.

186 TRIPLES      21 PREDICATES      104 URIs      93 LITERALS      6 BLANK NODES

Subject Predicate Object
1 sg:pub.10.1007/s00371-018-1483-0 schema:about anzsrc-for:08
2 anzsrc-for:0801
3 anzsrc-for:0806
4 schema:author Nff61a1a94a9947e39658c353a5b395ec
5 schema:citation sg:pub.10.1007/978-3-540-70904-6_6
6 sg:pub.10.1007/978-3-642-37453-1_5
7 schema:datePublished 2018-02-16
8 schema:datePublishedReg 2018-02-16
9 schema:description A fundamental task in criminal intelligence analysis is to analyze the similarity of crime cases, called comparative case analysis (CCA), to identify common crime patterns and to reason about unsolved crimes. Typically, the data are complex and high dimensional and the use of complex analytical processes would be appropriate. State-of-the-art CCA tools lack flexibility in interactive data exploration and fall short of computational transparency in terms of revealing alternative methods and results. In this paper, we report on the design of the Concept Explorer, a flexible, transparent and interactive CCA system. During this design process, we observed that most criminal analysts are not able to understand the underlying complex technical processes, which decrease the users’ trust in the results and hence a reluctance to use the tool. Our CCA solution implements a computational pipeline together with a visual platform that allows the analysts to interact with each stage of the analysis process and to validate the result. The proposed visual analytics workflow iteratively supports the interpretation of the results of clustering with the respective feature relations, the development of alternative models, as well as cluster verification. The visualizations offer an understandable and usable way for the analyst to provide feedback to the system and to observe the impact of their interactions. Expert feedback confirmed that our user-centered design decisions made this computational complexity less scary to criminal analysts.
10 schema:genre article
11 schema:isAccessibleForFree true
12 schema:isPartOf N4ad2ea38204f454098efebc60b9f393f
13 Nac360139b048464d983dbba3f4dea9e3
14 sg:journal.1046897
15 schema:keywords CCA solution
16 CCA system
17 Explorer
18 alternative method
19 alternative models
20 analysis
21 analysis process
22 analysis tools
23 analysts
24 analytical process
25 analytics
26 case analysis
27 cases
28 comparative case analysis
29 complex analytical processes
30 complex technical processes
31 complexity
32 computational complexity
33 computational pipeline
34 computational transparency
35 crime
36 crime cases
37 crime patterns
38 criminal analysts
39 criminal intelligence analysis
40 data
41 data exploration
42 decisions
43 design
44 design decisions
45 design process
46 development
47 expert feedback
48 exploration
49 feature relations
50 feedback
51 flexibility
52 fundamental task
53 impact
54 intelligence
55 intelligence analysis
56 interaction
57 interactive data exploration
58 interpretation
59 machine intelligence
60 method
61 model
62 paper
63 patterns
64 pipeline
65 platform
66 process
67 reasons
68 reflection
69 relation
70 reluctance
71 results
72 similarity
73 solution
74 stage
75 state
76 system
77 task
78 technical processes
79 terms
80 tool
81 transparency
82 trust
83 unsolved crimes
84 usable way
85 use
86 user trust
87 verification
88 visual analytics
89 visual platform
90 visualization
91 way
92 schema:name Making machine intelligence less scary for criminal analysts: reflections on designing a visual comparative case analysis tool
93 schema:pagination 1225-1241
94 schema:productId N4d7b564a0c424fb4836838a55159015d
95 Nb582e62bcec74a78a878fcf85ccc05b7
96 schema:sameAs https://app.dimensions.ai/details/publication/pub.1101082300
97 https://doi.org/10.1007/s00371-018-1483-0
98 schema:sdDatePublished 2022-09-02T16:03
99 schema:sdLicense https://scigraph.springernature.com/explorer/license/
100 schema:sdPublisher Nbdaa15008bcb46cfa89232f4262f3b6b
101 schema:url https://doi.org/10.1007/s00371-018-1483-0
102 sgo:license sg:explorer/license/
103 sgo:sdDataset articles
104 rdf:type schema:ScholarlyArticle
105 N169c15090da649028bf4430cea52a39a rdf:first sg:person.0634434147.05
106 rdf:rest Nc31f3a9d1ff24f06a1f610fd0b404308
107 N4a6a7f62afd047a794b6f70c8488c514 rdf:first sg:person.01204645707.14
108 rdf:rest Nc1ceea6f68354b9e905c6278f97a79c5
109 N4ad2ea38204f454098efebc60b9f393f schema:volumeNumber 34
110 rdf:type schema:PublicationVolume
111 N4d7b564a0c424fb4836838a55159015d schema:name doi
112 schema:value 10.1007/s00371-018-1483-0
113 rdf:type schema:PropertyValue
114 N56a947841f2d49e086764be8982fbdfc rdf:first sg:person.01311725047.83
115 rdf:rest N169c15090da649028bf4430cea52a39a
116 Nac360139b048464d983dbba3f4dea9e3 schema:issueNumber 9
117 rdf:type schema:PublicationIssue
118 Nb582e62bcec74a78a878fcf85ccc05b7 schema:name dimensions_id
119 schema:value pub.1101082300
120 rdf:type schema:PropertyValue
121 Nbdaa15008bcb46cfa89232f4262f3b6b schema:name Springer Nature - SN SciGraph project
122 rdf:type schema:Organization
123 Nc1ceea6f68354b9e905c6278f97a79c5 rdf:first sg:person.0635776571.01
124 rdf:rest rdf:nil
125 Nc31f3a9d1ff24f06a1f610fd0b404308 rdf:first sg:person.0750662547.01
126 rdf:rest N4a6a7f62afd047a794b6f70c8488c514
127 Nff61a1a94a9947e39658c353a5b395ec rdf:first sg:person.010324047633.88
128 rdf:rest N56a947841f2d49e086764be8982fbdfc
129 anzsrc-for:08 schema:inDefinedTermSet anzsrc-for:
130 schema:name Information and Computing Sciences
131 rdf:type schema:DefinedTerm
132 anzsrc-for:0801 schema:inDefinedTermSet anzsrc-for:
133 schema:name Artificial Intelligence and Image Processing
134 rdf:type schema:DefinedTerm
135 anzsrc-for:0806 schema:inDefinedTermSet anzsrc-for:
136 schema:name Information Systems
137 rdf:type schema:DefinedTerm
138 sg:grant.3793901 http://pending.schema.org/fundedItem sg:pub.10.1007/s00371-018-1483-0
139 rdf:type schema:MonetaryGrant
140 sg:journal.1046897 schema:issn 0178-2789
141 1432-2315
142 schema:name The Visual Computer
143 schema:publisher Springer Nature
144 rdf:type schema:Periodical
145 sg:person.010324047633.88 schema:affiliation grid-institutes:grid.9811.1
146 schema:familyName Jentner
147 schema:givenName Wolfgang
148 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.010324047633.88
149 rdf:type schema:Person
150 sg:person.01204645707.14 schema:affiliation grid-institutes:grid.15822.3c
151 schema:familyName Zhang
152 schema:givenName Leishi
153 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01204645707.14
154 rdf:type schema:Person
155 sg:person.01311725047.83 schema:affiliation grid-institutes:grid.9811.1
156 schema:familyName Sacha
157 schema:givenName Dominik
158 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01311725047.83
159 rdf:type schema:Person
160 sg:person.0634434147.05 schema:affiliation grid-institutes:grid.9811.1
161 schema:familyName Stoffel
162 schema:givenName Florian
163 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0634434147.05
164 rdf:type schema:Person
165 sg:person.0635776571.01 schema:affiliation grid-institutes:grid.9811.1
166 schema:familyName Keim
167 schema:givenName Daniel A.
168 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0635776571.01
169 rdf:type schema:Person
170 sg:person.0750662547.01 schema:affiliation grid-institutes:grid.9811.1
171 schema:familyName Ellis
172 schema:givenName Geoffrey
173 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0750662547.01
174 rdf:type schema:Person
175 sg:pub.10.1007/978-3-540-70904-6_6 schema:sameAs https://app.dimensions.ai/details/publication/pub.1018081363
176 https://doi.org/10.1007/978-3-540-70904-6_6
177 rdf:type schema:CreativeWork
178 sg:pub.10.1007/978-3-642-37453-1_5 schema:sameAs https://app.dimensions.ai/details/publication/pub.1009568116
179 https://doi.org/10.1007/978-3-642-37453-1_5
180 rdf:type schema:CreativeWork
181 grid-institutes:grid.15822.3c schema:alternateName Middlesex University, London, UK
182 schema:name Middlesex University, London, UK
183 rdf:type schema:Organization
184 grid-institutes:grid.9811.1 schema:alternateName Universität Konstanz, Universitätsstraße 10, 78464, Konstanz, Germany
185 schema:name Universität Konstanz, Universitätsstraße 10, 78464, Konstanz, Germany
186 rdf:type schema:Organization
 




Preview window. Press ESC to close (or click here)


...