A Comparison of Natural Language Understanding Platforms for Chatbots in Software Engineering

Chatbots are envisioned to dramatically change the future of Software Engineering, allowing practitioners to chat and inquire about their software projects and interact with different services using natural language. At the heart of every chatbot is a Natural Language Understanding (NLU) component t...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on software engineering Vol. 48; no. 8; pp. 3087 - 3102
Main Authors: Abdellatif, Ahmad, Badran, Khaled, Costa, Diego Elias, Shihab, Emad
Format: Journal Article
Language:English
Published: New York IEEE 01.08.2022
IEEE Computer Society
Subjects:
Chatbot
Chatbots
Classification
empirical software engineering
Feature extraction
Java
Natural language
natural language understanding platforms
Questions
Software
Software chatbots
Software engineering
Stability analysis
Task analysis
XML
ISSN:0098-5589, 1939-3520
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract Chatbots are envisioned to dramatically change the future of Software Engineering, allowing practitioners to chat and inquire about their software projects and interact with different services using natural language. At the heart of every chatbot is a Natural Language Understanding (NLU) component that enables the chatbot to understand natural language input. Recently, many NLU platforms were provided to serve as an off-the-shelf NLU component for chatbots, however, selecting the best NLU for Software Engineering chatbots remains an open challenge. Therefore, in this paper, we evaluate four of the most commonly used NLUs, namely IBM Watson, Google Dialogflow, Rasa, and Microsoft LUIS to shed light on which NLU should be used in Software Engineering based chatbots. Specifically, we examine the NLUs' performance in classifying intents, confidence scores stability, and extracting entities. To evaluate the NLUs, we use two datasets that reflect two common tasks performed by Software Engineering practitioners, 1) the task of chatting with the chatbot to ask questions about software repositories 2) the task of asking development questions on Q&A forums (e.g., Stack Overflow). According to our findings, IBM Watson is the best performing NLU when considering the three aspects (intents classification, confidence scores, and entity extraction). However, the results from each individual aspect show that, in intents classification, IBM Watson performs the best with an F1-measure<inline-formula><tex-math notation="LaTeX">></tex-math> <mml:math><mml:mo>></mml:mo></mml:math><inline-graphic xlink:href="abdellatif-ieq1-3078384.gif"/> </inline-formula>84%, but in confidence scores, Rasa comes on top with a median confidence score higher than 0.91. Our results also show that all NLUs, except for Dialogflow, generally provide trustable confidence scores. For entity extraction, Microsoft LUIS and IBM Watson outperform other NLUs in the two SE tasks. Our results provide guidance to software engineering practitioners when deciding which NLU to use in their chatbots.
AbstractList Chatbots are envisioned to dramatically change the future of Software Engineering, allowing practitioners to chat and inquire about their software projects and interact with different services using natural language. At the heart of every chatbot is a Natural Language Understanding (NLU) component that enables the chatbot to understand natural language input. Recently, many NLU platforms were provided to serve as an off-the-shelf NLU component for chatbots, however, selecting the best NLU for Software Engineering chatbots remains an open challenge. Therefore, in this paper, we evaluate four of the most commonly used NLUs, namely IBM Watson, Google Dialogflow, Rasa, and Microsoft LUIS to shed light on which NLU should be used in Software Engineering based chatbots. Specifically, we examine the NLUs' performance in classifying intents, confidence scores stability, and extracting entities. To evaluate the NLUs, we use two datasets that reflect two common tasks performed by Software Engineering practitioners, 1) the task of chatting with the chatbot to ask questions about software repositories 2) the task of asking development questions on Q&A forums (e.g., Stack Overflow). According to our findings, IBM Watson is the best performing NLU when considering the three aspects (intents classification, confidence scores, and entity extraction). However, the results from each individual aspect show that, in intents classification, IBM Watson performs the best with an F1-measure<inline-formula><tex-math notation="LaTeX">></tex-math> <mml:math><mml:mo>></mml:mo></mml:math><inline-graphic xlink:href="abdellatif-ieq1-3078384.gif"/> </inline-formula>84%, but in confidence scores, Rasa comes on top with a median confidence score higher than 0.91. Our results also show that all NLUs, except for Dialogflow, generally provide trustable confidence scores. For entity extraction, Microsoft LUIS and IBM Watson outperform other NLUs in the two SE tasks. Our results provide guidance to software engineering practitioners when deciding which NLU to use in their chatbots.
Chatbots are envisioned to dramatically change the future of Software Engineering, allowing practitioners to chat and inquire about their software projects and interact with different services using natural language. At the heart of every chatbot is a Natural Language Understanding (NLU) component that enables the chatbot to understand natural language input. Recently, many NLU platforms were provided to serve as an off-the-shelf NLU component for chatbots, however, selecting the best NLU for Software Engineering chatbots remains an open challenge. Therefore, in this paper, we evaluate four of the most commonly used NLUs, namely IBM Watson, Google Dialogflow, Rasa, and Microsoft LUIS to shed light on which NLU should be used in Software Engineering based chatbots. Specifically, we examine the NLUs’ performance in classifying intents, confidence scores stability, and extracting entities. To evaluate the NLUs, we use two datasets that reflect two common tasks performed by Software Engineering practitioners, 1) the task of chatting with the chatbot to ask questions about software repositories 2) the task of asking development questions on Q&A forums (e.g., Stack Overflow). According to our findings, IBM Watson is the best performing NLU when considering the three aspects (intents classification, confidence scores, and entity extraction). However, the results from each individual aspect show that, in intents classification, IBM Watson performs the best with an F1-measure[Formula Omitted]84%, but in confidence scores, Rasa comes on top with a median confidence score higher than 0.91. Our results also show that all NLUs, except for Dialogflow, generally provide trustable confidence scores. For entity extraction, Microsoft LUIS and IBM Watson outperform other NLUs in the two SE tasks. Our results provide guidance to software engineering practitioners when deciding which NLU to use in their chatbots.
Author Abdellatif, Ahmad
Costa, Diego Elias
Badran, Khaled
Shihab, Emad
Author_xml – sequence: 1
  givenname: Ahmad
  orcidid: 0000-0003-1863-9147
  surname: Abdellatif
  fullname: Abdellatif, Ahmad
  email: a_bdella@encs.concordia.ca
  organization: Department of Computer Science and Software Engineering, Data-Driven Analysis of Software (DAS) Lab, Concordia University, Montréal, QC, Canada
– sequence: 2
  givenname: Khaled
  surname: Badran
  fullname: Badran, Khaled
  email: k_badran@encs.concordia.ca
  organization: Department of Computer Science and Software Engineering, Data-Driven Analysis of Software (DAS) Lab, Concordia University, Montréal, QC, Canada
– sequence: 3
  givenname: Diego Elias
  orcidid: 0000-0001-7084-2594
  surname: Costa
  fullname: Costa, Diego Elias
  email: d_damasc@encs.concordia.ca
  organization: Department of Computer Science and Software Engineering, Data-Driven Analysis of Software (DAS) Lab, Concordia University, Montréal, QC, Canada
– sequence: 4
  givenname: Emad
  orcidid: 0000-0003-1285-9878
  surname: Shihab
  fullname: Shihab, Emad
  email: eshihab@encs.concordia.ca
  organization: Department of Computer Science and Software Engineering, Data-Driven Analysis of Software (DAS) Lab, Concordia University, Montréal, QC, Canada
BookMark eNp9kE1LAzEQhoNUsFbvgpeA562TZLObHEupH1BUaHuUJbs7WyNtUpMU8d-7peLBg5cZGJ5nXnjPycB5h4RcMRgzBvp2uZiNOXA2FlAqofITMmRa6ExIDgMyBNAqk1LpM3Ie4zsAyLKUQ_I6oVO_3Zlgo3fUd_TJpH0wGzo3br03a6Qr12KIybjWujV92ZjU-bCNtJ90-mZS7VOk1tGF79KnCUhnbm0dYujxC3LamU3Ey589Iqu72XL6kM2f7x-nk3nWCFmmrGygVgVAwTrdIMfCcNRNjQWqDk1e8lr115zzutBN27RM1QgCWKGkFC1nYkRujn93wX_sMabq3e-D6yMrXvak1lyKnoIj1QQfY8Cu2gW7NeGrYlAdSqz6EqtDidVPib1S_FEam0yy3qVg7OY_8fooWkT8zdE5L3LIxTfNeoFO
CODEN IESEDJ
CitedBy_id crossref_primary_10_1016_j_procs_2024_03_243
crossref_primary_10_1111_joie_12347
crossref_primary_10_3233_JIFS_224279
crossref_primary_10_1007_s11042_025_20659_8
crossref_primary_10_1016_j_ijinfomgt_2023_102699
crossref_primary_10_1007_s11423_025_10472_3
crossref_primary_10_2196_50767
crossref_primary_10_3390_ai5020041
crossref_primary_10_1016_j_jss_2025_112600
crossref_primary_10_1111_joor_13986
crossref_primary_10_7717_peerj_cs_866
crossref_primary_10_1016_j_pmcj_2023_101797
crossref_primary_10_1145_3660812
crossref_primary_10_3390_app13116777
crossref_primary_10_1007_s42001_023_00218_7
crossref_primary_10_25046_aj100103
crossref_primary_10_3390_electronics10182300
crossref_primary_10_1080_10494820_2023_2232823
crossref_primary_10_1186_s12909_024_05371_9
crossref_primary_10_1145_3637228
crossref_primary_10_1016_j_procir_2023_09_130
crossref_primary_10_1109_ACCESS_2023_3339553
crossref_primary_10_22395_rium_v24n47a4
crossref_primary_10_1145_3730578
crossref_primary_10_1055_a_2673_6412
crossref_primary_10_1134_S0361768824700774
crossref_primary_10_1016_j_datak_2025_102461
crossref_primary_10_1007_s10115_024_02074_x
crossref_primary_10_3390_app11104510
crossref_primary_10_1145_3704806
Cites_doi 10.1109/SANER.2016.10
10.1109/chase.2017.14
10.1145/3338906.3340442
10.1145/3180155.3180238
10.1145/3379597.3387472
10.1109/ICSE-NIER.2017.17
10.1109/Innovate-Data.2018.00010
10.1002/spe.1053
10.3115/1556328.1556341
10.1145/1806799.1806828
10.1109/CHASE.2015.13
10.1093/nsr/nwx106
10.1007/s10664-019-09788-5
10.1109/ASE.2017.8115628
10.1109/BotSE.2019.00020
10.1109/BotSE.2019.00008
10.1109/ASE.2017.8115681
10.1109/MS.2017.31
10.1145/3274451
10.1177/001316446002000104
10.1109/ESEM.2011.36
10.1145/2568225.2568233
10.1145/3387940.3391505
10.1177/2515245919847421
10.1109/SNAMS.2018.8554770
10.1145/2851581.2892311
10.1145/3387940.3391501
10.1109/MS.2017.4541027
10.1191/1478088706qp0630a
10.1145/2950290.2983989
10.1177/001316447303300309
10.1145/3173574.3173632
10.1109/IALP.2018.8629181
10.1145/3387940.3391534
10.1145/1978942.1979366
10.5220/0007252100190030
10.1109/BotSE.2019.00015
10.1109/BotSE.2019.00016
10.2200/s00196ed1v01y200906aim006
ContentType Journal Article
Copyright Copyright IEEE Computer Society 2022
Copyright_xml – notice: Copyright IEEE Computer Society 2022
DBID 97E
RIA
RIE
AAYXX
CITATION
JQ2
K9.
DOI 10.1109/TSE.2021.3078384
DatabaseName IEEE All-Society Periodicals Package (ASPP) 2005-present
IEEE All-Society Periodicals Package (ASPP) 1998-Present
IEEE Electronic Library (IEL)
CrossRef
ProQuest Computer Science Collection
ProQuest Health & Medical Complete (Alumni)
DatabaseTitle CrossRef
ProQuest Health & Medical Complete (Alumni)
ProQuest Computer Science Collection
DatabaseTitleList
ProQuest Health & Medical Complete (Alumni)
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Xplore
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Computer Science
EISSN 1939-3520
EndPage 3102
ExternalDocumentID 10_1109_TSE_2021_3078384
9426404
Genre orig-research
GroupedDBID --Z
-DZ
-~X
.DC
0R~
29I
4.4
5GY
6IK
85S
8R4
8R5
97E
AAJGR
AARMG
AASAJ
AAWTH
ABAZT
ABPPZ
ABQJQ
ABVLG
ACGFO
ACGOD
ACIWK
ACNCT
AENEX
AGQYO
AHBIQ
AKJIK
AKQYR
ALMA_UNASSIGNED_HOLDINGS
ASUFR
ATWAV
BEFXN
BFFAM
BGNUA
BKEBE
BKOMP
BPEOZ
CS3
DU5
EBS
EDO
EJD
HZ~
I-F
IEDLZ
IFIPE
IPLJI
JAVBF
LAI
M43
MS~
O9-
OCL
P2P
Q2X
RIA
RIE
RNS
RXW
S10
TAE
TN5
TWZ
UHB
UPT
WH7
YZZ
AAYXX
CITATION
JQ2
K9.
ID FETCH-LOGICAL-c357t-7c0b860061f9ce2e6a2e9cbe6e8fea472b8e2e422b69cdcd18be030168553d213
IEDL.DBID RIE
ISICitedReferencesCount 52
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000846878500022&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 0098-5589
IngestDate Fri Oct 03 03:50:28 EDT 2025
Sat Nov 29 03:10:26 EST 2025
Tue Nov 18 21:32:40 EST 2025
Wed Aug 27 02:02:18 EDT 2025
IsPeerReviewed true
IsScholarly true
Issue 8
Language English
License https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html
https://doi.org/10.15223/policy-029
https://doi.org/10.15223/policy-037
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c357t-7c0b860061f9ce2e6a2e9cbe6e8fea472b8e2e422b69cdcd18be030168553d213
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ORCID 0000-0003-1863-9147
0000-0001-7084-2594
0000-0003-1285-9878
PQID 2703099253
PQPubID 21418
PageCount 16
ParticipantIDs crossref_primary_10_1109_TSE_2021_3078384
proquest_journals_2703099253
crossref_citationtrail_10_1109_TSE_2021_3078384
ieee_primary_9426404
PublicationCentury 2000
PublicationDate 2022-08-01
PublicationDateYYYYMMDD 2022-08-01
PublicationDate_xml – month: 08
  year: 2022
  text: 2022-08-01
  day: 01
PublicationDecade 2020
PublicationPlace New York
PublicationPlace_xml – name: New York
PublicationTitle IEEE transactions on software engineering
PublicationTitleAbbrev TSE
PublicationYear 2022
Publisher IEEE
IEEE Computer Society
Publisher_xml – name: IEEE
– name: IEEE Computer Society
References ref13
(ref69) 2019
ref15
ref52
ref55
ref54
(ref56) 2020
ref17
ref18
(ref27) 2020
ref50
(ref57) 2020
ref46
(ref42) 2020
ref45
Conference (ref7) 2019
(ref22) 2020
ref85
ref44
Angara (ref79) 2018
(ref33) 2019
Brundage (ref86) 2020
(ref59) 2020
Braun (ref14)
ref49
(ref28) 2019
(ref10) 2020
(ref16) 2020
ref9
Abdellatif (ref31) 2021
ref4
Ask (ref25) 2016
(ref30) 2020
ref3
ref6
ref5
ref82
ref84
ref83
(ref8) 2019
ref80
(ref48) 2020
(ref34) 2019
ref78
ref37
(ref51) 2020
(ref58) 2020
ref36
Canonico (ref19) 2018
(ref68) 2020
ref75
ref74
ref77
ref76
Gregori (ref20) 2017
Munir (ref47) 2016; 21
(ref21) 2020
ref2
ref1
ref39
(ref81) 2020
(ref11) 2020
ref38
(ref41) 2020
Han (ref53) Elsevier
(ref64) 2020
Urli (ref71)
ref70
(ref61) 2019
ref72
ref24
(ref63) 2019
(ref29) 2020
(ref35) 2019
ref66
ref65
(ref23) 2019
(ref40) 2020
(ref60) 2020
Urli (ref12)
(ref26) 2020
Lebeuf (ref73) 2018
(ref67) 2019
ref62
(ref32) 2019
(ref43) 2020
References_xml – year: 2021
  ident: ref31
  article-title: A comparison of natural language understanding platforms for chatbots in software engineering | zenodo
– year: 2020
  ident: ref11
  article-title: Dependabot
– year: 2019
  ident: ref61
  article-title: Duckling
– year: 2020
  ident: ref59
  article-title: Dialogflow matches irrelevant phrases to existing intents
– year: 2020
  ident: ref40
  article-title: Developer entities
– year: 2018
  ident: ref19
  article-title: A comparison and critique of natural language understanding tools
  publication-title: Cloud Comput.
– ident: ref37
  doi: 10.1109/SANER.2016.10
– ident: ref83
  doi: 10.1109/chase.2017.14
– year: 2020
  ident: ref27
  article-title: LUIS (language understanding) cognitive services
– year: 2020
  ident: ref42
  article-title: Training data format
– ident: ref54
  doi: 10.1145/3338906.3340442
– year: 2020
  ident: ref56
  article-title: Training phrases
– year: 2019
  ident: ref63
  article-title: multiple entity recognition issue #427
– ident: ref74
  doi: 10.1145/3180155.3180238
– ident: ref5
  doi: 10.1145/3379597.3387472
– year: 2019
  ident: ref69
  article-title: A slack slash command app to file browser bugs in JIRA
– ident: ref75
  doi: 10.1109/ICSE-NIER.2017.17
– ident: ref15
  doi: 10.1109/Innovate-Data.2018.00010
– year: 2019
  ident: ref8
  article-title: 1st international workshop on bots in software engineering
– start-page: 95
  volume-title: Proc. 40th Int. Conf. Softw. Eng. Softw. Eng. Pract.
  ident: ref71
  article-title: How to design a program repair bot? Insights from the repairnator project
– year: 2020
  ident: ref86
  article-title: Toward trustworthy ai development: Mechanisms for supporting verifiable claims
– year: 2019
  ident: ref35
  article-title: Watson assistant v1
– year: 2020
  ident: ref41
  article-title: Entity types - language understanding - azure cognitive services
– ident: ref62
  doi: 10.1002/spe.1053
– year: 2017
  ident: ref20
  article-title: Evaluation of modern tools for an OMSCS advisor chatbot
– year: 2020
  ident: ref22
  article-title: Artificial intelligence - comparison between LUIS.ai vs API.ai vs WIT.ai?
– ident: ref80
  doi: 10.3115/1556328.1556341
– ident: ref84
  doi: 10.1145/1806799.1806828
– start-page: 95
  volume-title: Proc. 40th Int. Conf. Softw. Eng. Softw. Eng. Pract.
  ident: ref12
  article-title: How to design a program repair bot?: Insights from the repairnator project
– ident: ref46
  doi: 10.1109/CHASE.2015.13
– year: 2020
  ident: ref68
  article-title: Good example utterances - language understanding - azure cognitive services
– ident: ref66
  doi: 10.1093/nsr/nwx106
– year: 2019
  ident: ref23
  article-title: NLP - build chatbot for education purporse
– ident: ref3
  doi: 10.1007/s10664-019-09788-5
– year: 2019
  ident: ref34
  article-title: Query
– year: 2020
  ident: ref10
  article-title: Code deployment tools
– year: 2020
  ident: ref21
  article-title: Natural language processing
– ident: ref77
  doi: 10.1109/ASE.2017.8115628
– year: 2020
  ident: ref26
  article-title: The impact of conversational bots in the customer experience
– ident: ref70
  doi: 10.1109/BotSE.2019.00020
– ident: ref72
  doi: 10.1109/BotSE.2019.00008
– ident: ref2
  doi: 10.1109/ASE.2017.8115681
– ident: ref39
  doi: 10.1109/MS.2017.31
– year: 2020
  ident: ref64
  article-title: History dialogflow documentation
– year: 2020
  ident: ref60
  article-title: Entities
– ident: ref9
  doi: 10.1145/3274451
– ident: ref49
  doi: 10.1177/001316446002000104
– year: 2019
  ident: ref32
  article-title: Confidence and fallback intents
– ident: ref44
  doi: 10.1109/ESEM.2011.36
– ident: ref82
  doi: 10.1145/2568225.2568233
– year: 2019
  ident: ref7
  article-title: The chatbot conference
– start-page: 174
  volume-title: Proc. 18th Annu. SIGdial Meeting Discourse Dialogue.
  ident: ref14
  article-title: Evaluating natural language understanding services for conversational question answering systems
– year: 2016
  ident: ref25
  article-title: The state of chatbots
  publication-title: Rep., Forrester Res., Cambridge, MA, USA, Rep. 20
– year: 2019
  ident: ref67
  article-title: rasa/crf_entity_extractor.py at master rasahq/rasa
– year: 2020
  ident: ref16
  article-title: Chatbot for AWS monitoring
– year: 2020
  ident: ref43
  article-title: Creating entities
– ident: ref78
  doi: 10.1145/3387940.3391505
– year: 2018
  ident: ref73
  article-title: A taxonomy of software bots: Towards a deeper understanding of software bot characteristics
– ident: ref85
  doi: 10.1177/2515245919847421
– ident: ref13
  doi: 10.1109/SNAMS.2018.8554770
– ident: ref17
  doi: 10.1145/2851581.2892311
– year: 2018
  ident: ref79
  article-title: Towards a deeper understanding of current conversational frameworks through the design and development of a cognitive agent
– ident: ref6
  doi: 10.1145/3387940.3391501
– ident: ref24
  doi: 10.1109/MS.2017.4541027
– ident: ref45
  doi: 10.1191/1478088706qp0630a
– ident: ref1
  doi: 10.1145/2950290.2983989
– ident: ref50
  doi: 10.1177/001316447303300309
– year: 2020
  ident: ref57
  article-title: Defining intents
– ident: ref18
  doi: 10.1145/3173574.3173632
– ident: ref55
  doi: 10.1109/IALP.2018.8629181
– volume-title: Data Mining: Concepts and Techniques (The Morgan Kaufmann Series in Data Management Systems)
  year: Elsevier
  ident: ref53
– ident: ref4
  doi: 10.1145/3387940.3391534
– year: 2020
  ident: ref81
  article-title: Dialogflow agent validation
– year: 2019
  ident: ref28
  article-title: IBM Watson
– ident: ref38
  doi: 10.1145/1978942.1979366
– volume: 21
  start-page: 684
  issue: 2
  volume-title: Empirical Softw. Eng.
  year: 2016
  ident: ref47
  article-title: Open innovation in software engineering: A systematic mapping study
– ident: ref36
  doi: 10.5220/0007252100190030
– year: 2020
  ident: ref58
  article-title: Chatbot dialogflow returning answers with confidence score below ML classification threshold
– year: 2020
  ident: ref48
  article-title: Frequently asked questions
– year: 2019
  ident: ref33
  article-title: Prediction scores - language understanding - azure cognitive services
– year: 2020
  ident: ref29
  article-title: Dialogflow
– year: 2020
  ident: ref30
  article-title: Rasa: Open source conversational AI
– ident: ref52
  doi: 10.1109/BotSE.2019.00015
– ident: ref76
  doi: 10.1109/BotSE.2019.00016
– ident: ref65
  doi: 10.2200/s00196ed1v01y200906aim006
– year: 2020
  ident: ref51
  article-title: PHP mysqli query returns empty error message
SSID ssj0005775
ssib053395008
Score 2.5690336
Snippet Chatbots are envisioned to dramatically change the future of Software Engineering, allowing practitioners to chat and inquire about their software projects and...
SourceID proquest
crossref
ieee
SourceType Aggregation Database
Enrichment Source
Index Database
Publisher
StartPage 3087
SubjectTerms Chatbot
Chatbots
Classification
empirical software engineering
Feature extraction
Java
Natural language
natural language understanding platforms
Questions
Software
Software chatbots
Software engineering
Stability analysis
Task analysis
XML
Title A Comparison of Natural Language Understanding Platforms for Chatbots in Software Engineering
URI https://ieeexplore.ieee.org/document/9426404
https://www.proquest.com/docview/2703099253
Volume 48
WOSCitedRecordID wos000846878500022&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVIEE
  databaseName: IEEE Xplore
  customDbUrl:
  eissn: 1939-3520
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0005775
  issn: 0098-5589
  databaseCode: RIE
  dateStart: 19750101
  isFulltext: true
  titleUrlDefault: https://ieeexplore.ieee.org/
  providerName: IEEE
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1NS8MwGA5zePDi1ClOp-TgRbBbm7b5OI6x4UHGYBvsIiVJ3-JgdLJ2-vdtsrYqiuAllJJA6ZO8H3k_HoTupEhcKmTihOaOKWDKc6SvwNHFSDnV0mOJJZtgkwlfLsW0gR7qWhgAsMln0DOPNpYfb_TOXJX1hVHfpvnnAWNsX6v1mc7BWFj1xwxDLqqQpCv689mocASJ1_NNzIoH31SQ5VT5IYitdhm3_vddJ-i4tCLxYA_7KWpAeoZaFUMDLg9sGz0P8LAmGsSbBE-k7bOBn8prSrz4WtyCp2uZGys2w8WIhy8yV5s8w6sUzwpx_S63gL80MDxHi_FoPnx0SkIFR_shyx2mXcWpsVoSoYEAlQSEVkCBJyADRhQv3gaEKCp0rGOPKzAuE-Vh6MfE8y9QM92kcIlwUthRwpexGysIhGYy4CKmhS3nByzQhHRQv_rHkS67jRvSi3VkvQ5XRAUqkUElKlHpoPt6xeu-08Yfc9sGhXpeCUAHdSsYo_IoZhExMk0IEvpXv6-6RkfE1DTYrL4uaubbHdygQ_2Wr7Ltrd1lH8kCz-4
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1bS8MwFD6ICvriXZzXPPgiWNemuT7KUBTnEJzgi5QkPUVBNtmq_n2brJ2KIvgSSkmg9EvOJefyARwaXcRCmyLi_o6JSZtEJrUYuWoUSjiTyCKQTcheT93f65sZOJ7WwiBiSD7DE_8YYvn50L36q7K29urbN_-c44zRZFKt9ZnQISVvOmRyrnQTlIx1u397VrmCNDlJfdRKsW9KKLCq_BDFQb-cL__vy1ZgqbYjyekE-FWYwcEaLDccDaQ-suvwcEo6U6pBMixIz4ROG6RbX1SSu6_lLeTm2ZTejh2TaiSdR1PaYTkmTwNyWwnsdzNC8qWF4QbcnZ_1OxdRTakQuZTLMpIutkp4u6XQDikKQ1E7iwJVgYZJalX1llFqhXa5yxNl0TtNQnGe5jRJN2F2MBzgFpCisqR0avI4t8i0k4YpnYvKmkuZZI7SFrSbf5y5ut-4p714zoLfEeusQiXzqGQ1Ki04mq54mfTa-GPuukdhOq8GoAW7DYxZfRjHGfVSTWvK0-3fVx3AwkX_upt1L3tXO7BIfYVDyPHbhdly9Ip7MO_eyqfxaD_suA_C0dM1
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=A+Comparison+of+Natural+Language+Understanding+Platforms+for+Chatbots+in+Software+Engineering&rft.jtitle=IEEE+transactions+on+software+engineering&rft.au=Abdellatif%2C+Ahmad&rft.au=Badran%2C+Khaled&rft.au=Costa%2C+Diego+Elias&rft.au=Shihab%2C+Emad&rft.date=2022-08-01&rft.pub=IEEE&rft.issn=0098-5589&rft.volume=48&rft.issue=8&rft.spage=3087&rft.epage=3102&rft_id=info:doi/10.1109%2FTSE.2021.3078384&rft.externalDocID=9426404
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0098-5589&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0098-5589&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0098-5589&client=summon