AI Chatbots and Subject Cataloging: A Performance Test

Libraries show an increasing interest in incorporating AI tools into their workflows, particularly easily accessible and free-to-use chatbots. However, empirical evidence is limited regarding the effectiveness of these tools to perform traditionally time-consuming subject cataloging tasks. In this s...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Library resources & technical services Ročník 69; číslo 2
Hlavní autoři: Dobreski, Brian, Hastings, Christopher
Médium: Journal Article
Jazyk:angličtina
Vydáno: American Library Association 01.04.2025
Témata:
Artificial intelligence
Classification
Classification (Library Science)
Intelligent agent
Intelligent agents
Libraries
Subject cataloging
Subject cataloging and indexing
Technology application
United States
ISSN:0024-2527
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Abstract Libraries show an increasing interest in incorporating AI tools into their workflows, particularly easily accessible and free-to-use chatbots. However, empirical evidence is limited regarding the effectiveness of these tools to perform traditionally time-consuming subject cataloging tasks. In this study, researchers sought to assess the performance of AI tools in performing basic subject heading and classification number assignment. Using a well-established instructional cataloging text as a basis, researchers developed and administered a test designed to evaluate the effectiveness of three chatbots (ChatGPT, Gemini, Copilot) in assigning Dewey Decimal Classification, Library of Congress Classification, and Library of Congress Subject Heading terms and numbers. The quantity and quality of errors in chatbot responses were analyzed. Overall performance of these tools was poor, particularly for assigning classification numbers. Frequent sources of error included assigning overly broad numbers or numbers for incorrect topics. Although subject heading assignment was also poor, ChatGPT showed more promise here, backing up previous observations that chatbots may hold more immediate potential for this task. Although AI chatbots do not show promise in reducing time and effort associated with subject cataloging at this time, this may change in the future. For now, findings from this study offer caveats for catalogers already working with these tools and underscore the continuing importance of human expertise and oversight in cataloging.
AbstractList Libraries show an increasing interest in incorporating AI tools into their workflows, particularly easily accessible and free-to-use chatbots. However, empirical evidence is limited regarding the effectiveness of these tools to perform traditionally time-consuming subject cataloging tasks. In this study, researchers sought to assess the performance of AI tools in performing basic subject heading and classification number assignment. Using a well-established instructional cataloging text as a basis, researchers developed and administered a test designed to evaluate the effectiveness of three chatbots (ChatGPT, Gemini, Copilot) in assigning Dewey Decimal Classification, Library of Congress Classification, and Library of Congress Subject Heading terms and numbers. The quantity and quality of errors in chatbot responses were analyzed. Overall performance of these tools was poor, particularly for assigning classification numbers. Frequent sources of error included assigning overly broad numbers or numbers for incorrect topics. Although subject heading assignment was also poor, ChatGPT showed more promise here, backing up previous observations that chatbots may hold more immediate potential for this task. Although AI chatbots do not show promise in reducing time and effort associated with subject cataloging at this time, this may change in the future. For now, findings from this study offer caveats for catalogers already working with these tools and underscore the continuing importance of human expertise and oversight in cataloging.
Audience Trade
Author Hastings, Christopher
Dobreski, Brian
Author_xml – sequence: 1
  fullname: Dobreski, Brian
– sequence: 2
  fullname: Hastings, Christopher
BookMark eNp90M1Kw0AQAOA9VLCtHnyDBU8iqZvsTzbeQtAqFCtY8Rgmm8makm4guwUf34A9WKgyh4Hhm2FmZmTieoeEXMVsIbVid90Q_EJlLp6QKWOJiBKZpOdk5v2WMSaFUFOi8mdafEKo-uApuJq-7astmkALCND1tnX2nub0FYemH3bgDNIN-nBBzhroPF4e8py8Pz5siqdotV4-F_kqsknMZcQVqKTWUvEatEqxypo0g9RUqYJEmIo1QplYqrSuRJzVQjMNtQDeKOAxZ8Dn5PpnroUOy9Y1fRjA7FpvylyLca7gWo4qOqEsOhzGGxw27Vg-8osTfowad6052XB71DCagF_Bwt77Mt98FC_H-uZvrZer_1Y_WNN3HVosx2cW69_-GzsLj4g
ClassificationCodes 8231
519210
3573006
8230000
ContentType Journal Article
Copyright COPYRIGHT 2025 American Library Association
Copyright_xml – notice: COPYRIGHT 2025 American Library Association
DBID 8GL
ATWCN
DOI 10.5860/lrts.69n1
DatabaseName Gale In Context: High School
Gale In Context: Middle School
DatabaseTitleList

DeliveryMethod fulltext_linktorsrc
Discipline Library & Information Science
ExternalDocumentID A845634385
GeographicLocations United States
GeographicLocations_xml – name: United States
GroupedDBID -DZ
-ET
-W8
-~X
.4I
.GO
11K
29L
5GY
66.
77I
77K
7X7
85S
88E
8FE
8FG
8FI
8FJ
8FW
8G5
8GL
8R4
8R5
AAFWJ
AAHSB
ABCQX
ABDBF
ABDPE
ABPPZ
ABUFD
ABUWG
ABZEH
ACHQT
ACIHN
ACNCT
ACUHS
ADBBV
ADMHG
AEAQA
AFFHD
AFKRA
AFPKN
ALMA_UNASSIGNED_HOLDINGS
ALSLI
ARAPS
ATWCN
AZQEC
B0M
BCU
BEC
BENPR
BGLVJ
BLC
BPHCQ
BVXVI
CCPQU
CNYFK
DWQXO
EAD
EAP
EAS
EBS
EDJ
EJD
ELW
EMK
EPL
ESX
F5P
FYUFA
GICCO
GNUQQ
GROUPED_DOAJ
GUQSH
HCIFZ
HMCUK
H~9
IAO
IEA
IER
IMI
IOF
IPO
ISE
ISN
ITC
KWQ
L7B
M1O
M1P
M2O
MET
MVM
OK1
P62
PADUT
PHGZM
PHGZT
PJZUB
PPXIY
PQGLB
PQQKQ
PROAC
PRQQA
PSQYO
Q2X
QF3
QF4
QM7
QN7
RAL
RPD
RWL
RXW
S10
SJFOW
SJN
TAE
TN5
U5U
UHB
UKHRP
UPT
WH7
XH6
YCV
YOJ
YQT
YR5
YZZ
ZCA
~8M
~A~
ID FETCH-LOGICAL-g2135-36a62d8563da867eb9f79a7cb76a24cb0f46c1567db419d4808ad4a3f6a3130a3
ISSN 0024-2527
IngestDate Sat Nov 29 13:47:11 EST 2025
Mon Nov 24 15:48:12 EST 2025
Sat Nov 29 10:32:54 EST 2025
Thu Nov 13 15:56:49 EST 2025
Thu Nov 13 15:56:44 EST 2025
Mon Nov 24 15:38:02 EST 2025
IsPeerReviewed true
IsScholarly true
Issue 2
Language English
LinkModel OpenURL
MergedId FETCHMERGED-LOGICAL-g2135-36a62d8563da867eb9f79a7cb76a24cb0f46c1567db419d4808ad4a3f6a3130a3
ParticipantIDs gale_infotracmisc_A845634385
gale_infotracgeneralonefile_A845634385
gale_infotracacademiconefile_A845634385
gale_incontextgauss_ATWCN_A845634385
gale_incontextgauss_8GL_A845634385
gale_incontextcollege_GICCO_A845634385
PublicationCentury 2000
PublicationDate 20250401
PublicationDateYYYYMMDD 2025-04-01
PublicationDate_xml – month: 04
  year: 2025
  text: 20250401
  day: 01
PublicationDecade 2020
PublicationTitle Library resources & technical services
PublicationTitleAlternate Library Resources & Technical Services
PublicationYear 2025
Publisher American Library Association
Publisher_xml – name: American Library Association
SSID ssj0005446
Score 2.3348238
Snippet Libraries show an increasing interest in incorporating AI tools into their workflows, particularly easily accessible and free-to-use chatbots. However,...
SourceID gale
SourceType Aggregation Database
SubjectTerms Artificial intelligence
Classification
Classification (Library Science)
Intelligent agent
Intelligent agents
Libraries
Subject cataloging
Subject cataloging and indexing
Technology application
Title AI Chatbots and Subject Cataloging: A Performance Test
Volume 69
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVAON
  databaseName: DOAJ Directory of Open Access Journals
  issn: 0024-2527
  databaseCode: DOA
  dateStart: 20230101
  customDbUrl:
  isFulltext: true
  dateEnd: 99991231
  titleUrlDefault: https://www.doaj.org/
  omitProxy: false
  ssIdentifier: ssj0005446
  providerName: Directory of Open Access Journals
– providerCode: PRVPQU
  databaseName: Advanced Technologies & Aerospace Database
  issn: 0024-2527
  databaseCode: P5Z
  dateStart: 20031001
  customDbUrl:
  isFulltext: true
  dateEnd: 99991231
  titleUrlDefault: https://search.proquest.com/hightechjournals
  omitProxy: false
  ssIdentifier: ssj0005446
  providerName: ProQuest
– providerCode: PRVPQU
  databaseName: Health & Medical Collection
  issn: 0024-2527
  databaseCode: 7X7
  dateStart: 20031001
  customDbUrl:
  isFulltext: true
  dateEnd: 99991231
  titleUrlDefault: https://search.proquest.com/healthcomplete
  omitProxy: false
  ssIdentifier: ssj0005446
  providerName: ProQuest
– providerCode: PRVPQU
  databaseName: Library Science Database
  issn: 0024-2527
  databaseCode: M1O
  dateStart: 20031001
  customDbUrl:
  isFulltext: true
  dateEnd: 99991231
  titleUrlDefault: https://search.proquest.com/libraryscience
  omitProxy: false
  ssIdentifier: ssj0005446
  providerName: ProQuest
– providerCode: PRVPQU
  databaseName: ProQuest Central
  issn: 0024-2527
  databaseCode: BENPR
  dateStart: 20031001
  customDbUrl:
  isFulltext: true
  dateEnd: 99991231
  titleUrlDefault: https://www.proquest.com/central
  omitProxy: false
  ssIdentifier: ssj0005446
  providerName: ProQuest
– providerCode: PRVPQU
  databaseName: Research Library
  issn: 0024-2527
  databaseCode: M2O
  dateStart: 20031001
  customDbUrl:
  isFulltext: true
  dateEnd: 99991231
  titleUrlDefault: https://search.proquest.com/pqrl
  omitProxy: false
  ssIdentifier: ssj0005446
  providerName: ProQuest
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1Lb9QwELagcOCCWh6i0FYWqpYDCmxsx4_e0hXQSmXbwwK9rWwnWSGhLEpS1J_POHY2SbWHcuASrbIjy843mYzH880gdEyUmVKm88gIriMWFzbSWWyjKctMbgRc2tPz7xdiPpfX1-oqdKar23YCoizl7a36_V-hhnsAtqPO_gPcm0HhBvwG0OEKsMP1XsCn5-4MvTHrxpdfBtPgYi2O66fb1O2VZ6NfDSgDi-6QqWNG-9jO-yoE9-tWQ3y915ZGGSzMxg1ew846dMA-rQYad6Zrl1d9t47BMNZAkkGKSp_e79oJh1ncVaGOIMAiknjKf2dkfT-WoExkm-1OJHfJjr-qpv7AVRn3H6hN2mAqwd2jjMrkIXpERKJcDt_X-LLP6WGemdXNwJeSciN_3Iwbvr0DL2Kxi54G9x-nHrY99CAvn6HDsFA8wYEd5paKg9l9jnh6jjtIMUCKA6S4h_QEp3gAKHaAvkDfPn9azM6i0O8iWpGYJhHlmpNMwhIzLbnIjSqE0sK614gwa6YF4xb22_AGsVhlTE6lzpimBdcUXBFNX6Kdcl3mrxCWilnY2XIJAzHBiFbCGNcgKivAX43pPpq4h7B0FUBKl2JkfZhqCfOZXS77B72P3o4FV_qmrpfyy8VI6HibULr4MZuPxN4FsWLdVNrqwACBKbsiZCPJyUhy5UuwbxM8GAmCbbSDv1_fd5w36Emv7wdop6lu8kP02P5pftbVURuoOWpV7S-suIUp
linkProvider ProQuest
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=AI+Chatbots+and+Subject+Cataloging%3A+A+Performance+Test&rft.jtitle=Library+resources+%26+technical+services&rft.au=Dobreski%2C+Brian&rft.au=Hastings%2C+Christopher&rft.date=2025-04-01&rft.pub=American+Library+Association&rft.issn=0024-2527&rft.volume=69&rft.issue=2&rft_id=info:doi/10.5860%2Flrts.69n1&rft.externalDocID=A845634385
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0024-2527&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0024-2527&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0024-2527&client=summon