An inter-modal attention-based deep learning framework using unified modality for multimodal fake news, hate speech and offensive language detection

Fake news, hate speech and offensive language are related evil triplets currently affecting modern societies. Text modality for the computational detection of these phenomena has been widely used. In recent times, multimodal studies in this direction are attracting a lot of interests because of the...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Information systems (Oxford) Ročník 123; s. 102378
Hlavní autoři: Ayetiran, Eniafe Festus, Özgöbek, Özlem
Médium: Journal Article
Jazyk:angličtina
Vydáno: Elsevier Ltd 01.07.2024
Témata:
ISSN:0306-4379, 1873-6076
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Abstract Fake news, hate speech and offensive language are related evil triplets currently affecting modern societies. Text modality for the computational detection of these phenomena has been widely used. In recent times, multimodal studies in this direction are attracting a lot of interests because of the potentials offered by other modalities in contributing to the detection of these menaces. However, a major problem in multimodal content understanding is how to effectively model the complementarity of the different modalities due to their diverse characteristics and features. From a multimodal point of view, the three tasks have been studied mainly using image and text modalities. Improving the effectiveness of the diverse multimodal approaches is still an open research topic. In addition to the traditional text and image modalities, we consider image–texts which are rarely used in previous studies but which contain useful information for enhancing the effectiveness of a prediction model. In order to ease multimodal content understanding and enhance prediction, we leverage recent advances in computer vision and deep learning for these tasks. First, we unify the modalities by creating a text representation of the images and image–texts, in addition to the main text. Secondly, we propose a multi-layer deep neural network with inter-modal attention mechanism to model the complementarity among these modalities. We conduct extensive experiments involving three standard datasets covering the three tasks. Experimental results show that detection of fake news, hate speech and offensive language can benefit from this approach. Furthermore, we conduct robust ablation experiments to show the effectiveness of our approach. Our model predominantly outperforms prior works across the datasets. •A unified deep learning model can be used for multimodal fake news, hate speech and offensive language detection.•Unifying modalities is useful for multimodal content understanding.•Inter-modal attention mechanism is effective for multimodal-based deep learning models.•The inter-modal attention deep learning framework is effective for fake news, hate speech and offensive language detection.•Incorporation of image-texts as additional modality improves performance. The model can be tuned to use desired number of modalities.
AbstractList Fake news, hate speech and offensive language are related evil triplets currently affecting modern societies. Text modality for the computational detection of these phenomena has been widely used. In recent times, multimodal studies in this direction are attracting a lot of interests because of the potentials offered by other modalities in contributing to the detection of these menaces. However, a major problem in multimodal content understanding is how to effectively model the complementarity of the different modalities due to their diverse characteristics and features. From a multimodal point of view, the three tasks have been studied mainly using image and text modalities. Improving the effectiveness of the diverse multimodal approaches is still an open research topic. In addition to the traditional text and image modalities, we consider image–texts which are rarely used in previous studies but which contain useful information for enhancing the effectiveness of a prediction model. In order to ease multimodal content understanding and enhance prediction, we leverage recent advances in computer vision and deep learning for these tasks. First, we unify the modalities by creating a text representation of the images and image–texts, in addition to the main text. Secondly, we propose a multi-layer deep neural network with inter-modal attention mechanism to model the complementarity among these modalities. We conduct extensive experiments involving three standard datasets covering the three tasks. Experimental results show that detection of fake news, hate speech and offensive language can benefit from this approach. Furthermore, we conduct robust ablation experiments to show the effectiveness of our approach. Our model predominantly outperforms prior works across the datasets. •A unified deep learning model can be used for multimodal fake news, hate speech and offensive language detection.•Unifying modalities is useful for multimodal content understanding.•Inter-modal attention mechanism is effective for multimodal-based deep learning models.•The inter-modal attention deep learning framework is effective for fake news, hate speech and offensive language detection.•Incorporation of image-texts as additional modality improves performance. The model can be tuned to use desired number of modalities.
ArticleNumber 102378
Author Ayetiran, Eniafe Festus
Özgöbek, Özlem
Author_xml – sequence: 1
  givenname: Eniafe Festus
  orcidid: 0000-0002-6816-2781
  surname: Ayetiran
  fullname: Ayetiran, Eniafe Festus
  email: eniafe.ayetiran@ntnu.no
  organization: Department of Computer Science, Norwegian University of Science and Technology, Trondheim, Norway
– sequence: 2
  givenname: Özlem
  orcidid: 0000-0003-2612-2009
  surname: Özgöbek
  fullname: Özgöbek, Özlem
  email: ozlem.ozgobek@ntnu.no
  organization: Department of Computer Science, Norwegian University of Science and Technology, Trondheim, Norway
BookMark eNp9kM1OwzAQhC0EEqVw5-gHIMVO0qTlhhB_EhIXOFsbZ7fdNnUq2wXxHjwwDuWEBKfVSPPt7M6JOHS9QyHOtZpopavL1YTDJFd5mWRe1LMDMdKzusgqVVeHYqQKVWVlUc-PxUkIK6VUPp3PR-Lz2kl2EX226VvoJMSILnLvsgYCtrJF3MoOwTt2C0keNvje-7XchUHvHBMn1zfL8UNS7-Vm10XebyNYo3T4Hi7kEiLKsEW0SwmulT0RusBvKDtwix0sMGVFtEP2qTgi6AKe_cyxeL27fbl5yJ6e7x9vrp8yWxRVzBpFDc51U4MFymnaltDUClWpCW1uc43JYbGpdPKUDWByaCI1o5aUnlIxFtV-r_V9CB7JWI4wXBA9cGe0MkO3ZmU4mKFbs-82geoXuPW8Af_xH3K1RzA99MboTbCMzmLLPn1t2p7_hr8AECWYMw
CitedBy_id crossref_primary_10_1145_3748326
crossref_primary_10_1016_j_eswa_2025_129756
crossref_primary_10_3390_e26121114
crossref_primary_10_1051_itmconf_20257802017
crossref_primary_10_2478_nor_2025_0015
crossref_primary_10_1007_s13042_025_02715_9
crossref_primary_10_1109_ACCESS_2024_3406258
crossref_primary_10_1007_s42979_024_03280_8
crossref_primary_10_1016_j_asoc_2025_113277
crossref_primary_10_1007_s44379_025_00033_z
crossref_primary_10_1016_j_asoc_2024_112358
crossref_primary_10_1016_j_knosys_2025_113249
crossref_primary_10_1108_DTA_06_2023_0230
crossref_primary_10_1016_j_aej_2025_03_071
crossref_primary_10_1016_j_rineng_2025_104752
crossref_primary_10_1016_j_inffus_2025_103628
crossref_primary_10_1016_j_neucom_2025_131118
crossref_primary_10_1007_s12559_024_10356_3
Cites_doi 10.1016/j.knosys.2021.106902
10.1162/neco.1997.9.8.1735
10.1016/j.inffus.2022.12.016
10.1016/0031-3203(82)90024-3
10.1016/j.neucom.2020.10.042
10.1016/j.knosys.2022.109409
10.1089/big.2020.0062
10.1016/j.ipm.2021.102610
10.1016/j.ipm.2023.103474
ContentType Journal Article
Copyright 2024 The Author(s)
Copyright_xml – notice: 2024 The Author(s)
DBID 6I.
AAFTH
AAYXX
CITATION
DOI 10.1016/j.is.2024.102378
DatabaseName ScienceDirect Open Access Titles
Elsevier:ScienceDirect:Open Access
CrossRef
DatabaseTitle CrossRef
DatabaseTitleList
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
Computer Science
EISSN 1873-6076
ExternalDocumentID 10_1016_j_is_2024_102378
S030643792400036X
GroupedDBID --K
--M
-~X
.DC
.~1
0R~
13V
1B1
1~.
1~5
29I
4.4
457
4G.
5GY
5VS
63O
6I.
7-5
71M
77K
8P~
9JN
9JO
AAAKF
AAAKG
AACTN
AAEDT
AAEDW
AAFTH
AAIAV
AAIKJ
AAKOC
AALRI
AAOAW
AAQFI
AAQXK
AARIN
AAXUO
AAYFN
ABBOA
ABFNM
ABKBG
ABMAC
ABMVD
ABTAH
ABUCO
ABXDB
ABYKQ
ACDAQ
ACGFS
ACHRH
ACNNM
ACNTT
ACRLP
ACZNC
ADBBV
ADEZE
ADJOM
ADMUD
AEBSH
AEKER
AENEX
AFFNX
AFKWA
AFTJW
AGHFR
AGJBL
AGUBO
AGUMN
AGYEJ
AHHHB
AHZHX
AI.
AIALX
AIEXJ
AIKHN
AITUG
AJOXV
AKRWK
ALEQD
ALMA_UNASSIGNED_HOLDINGS
AMFUW
AMRAJ
AOUOD
APLSM
ASPBG
AVWKF
AXJTR
AZFZN
BKOJK
BLXMC
BNSAS
CS3
DU5
EBS
EFJIC
EJD
EO8
EO9
EP2
EP3
F5P
FDB
FEDTE
FGOYB
FIRID
FNPLU
FYGXN
G-Q
G8K
GBLVA
GBOLZ
HAMUX
HF~
HLZ
HVGLF
HZ~
H~9
IHE
J1W
KOM
LG9
M41
MO0
N9A
O-L
O9-
OAUVE
OZT
P-8
P-9
P2P
PC.
PQQKQ
Q38
R2-
RIG
RNS
ROL
RPZ
SBC
SDF
SDG
SDP
SES
SEW
SPC
SPCBC
SSB
SSD
SSL
SSV
SSZ
T5K
TN5
UHS
VH1
WUQ
XSW
ZCG
ZY4
~G-
77I
9DU
AATTM
AAXKI
AAYWO
AAYXX
ABDPE
ABJNI
ABWVN
ACLOT
ACRPL
ACVFH
ADCNI
ADNMO
ADVLN
AEIPS
AEUPX
AFJKZ
AFPUW
AGQPQ
AIGII
AIIUN
AKBMS
AKYEP
ANKPU
APXCP
CITATION
EFKBS
EFLBG
~HD
ID FETCH-LOGICAL-c336t-b0fbe91b7acaf2f5d4ab70e041fec2c21eb0fceb611b74bae5d41ff08fdf015f3
ISICitedReferencesCount 17
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001217561900001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 0306-4379
IngestDate Tue Nov 18 21:18:50 EST 2025
Sat Nov 29 06:20:20 EST 2025
Sat May 04 15:44:47 EDT 2024
IsDoiOpenAccess true
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Keywords Inter-modal attention
Unified modality
BiLSTM-CNN
Hate speech
Multimodal fusion
Offensive language
Fake news
Multimodal content understanding
Language English
License This is an open access article under the CC BY license.
LinkModel OpenURL
MergedId FETCHMERGED-LOGICAL-c336t-b0fbe91b7acaf2f5d4ab70e041fec2c21eb0fceb611b74bae5d41ff08fdf015f3
ORCID 0000-0003-2612-2009
0000-0002-6816-2781
OpenAccessLink https://dx.doi.org/10.1016/j.is.2024.102378
ParticipantIDs crossref_citationtrail_10_1016_j_is_2024_102378
crossref_primary_10_1016_j_is_2024_102378
elsevier_sciencedirect_doi_10_1016_j_is_2024_102378
PublicationCentury 2000
PublicationDate July 2024
2024-07-00
PublicationDateYYYYMMDD 2024-07-01
PublicationDate_xml – month: 07
  year: 2024
  text: July 2024
PublicationDecade 2020
PublicationTitle Information systems (Oxford)
PublicationYear 2024
Publisher Elsevier Ltd
Publisher_xml – name: Elsevier Ltd
References Maity, Jha, Saha, Bhattacharyya (b29) 2022
Pramanick, Sharma, Dimitrov, Akhtar, Nakov, Chakraborty (b34) 2021
Koutlis, Schinas, Papadopoulos (b8) 2023
Radford, Kim, Hallacy, Ramesh, Goh, Agarwal, Sastry, Askell, Mishkin, Clark, Krueger, Sutskever (b37) 2021; vol. 139
Chen, Wang, Liu, Lew (b10) 2021; 426
Hosseinmardi, Rafiq, Han, Lv, Mishra (b26) 2016
Chen, Li, Zhang, Sui, Lv, Lu, Shang (b23) 2022
Suryawanshi, Chakravarthi, Arcan, Buitelaar (b4) 2020
Fukushima, Miyake (b40) 1982; 15
Lahat, Adali, Jutten (b13) 2014
Khattar, Goud, Gupta, Varma (b3) 2019
Bozarth, Budak (b9) 2020
Li, Li, Xiong, Hoi (b38) 2022; vol. 162
Rizzi, Gasparini, Saibene, Rosso, Fersini (b32) 2023; 60
Srivastava, Hinton, Krizhevsky, Sutskever, Salakhutdinov (b48) 2014; 15
Giachanou, Rosso (b1) 2020
Giachanou, Zhang, Rosso (b19) 2020; vol. 12284
Zhong, Wang, Liu (b35) 2022; vol. 13141
Xiong, Zhang, Batra, Xi, Shi, Liu (b25) 2023; 93
Alam, Cresci, Chakraborty, Silvestri, Dimitrov, Martino, Shaar, Firooz, Nakov (b14) 2022
Kim (b41) 2014
Wang, Ma, Jin, Yuan, Xun, Jha, Su, Gao (b15) 2018
Wu, Zhan, Zhang, Wang, Xu (b22) 2021; ACL/IJCNLP 2021
Segura-Bedmar, Alonso-Bartolome (b12) 2022; 13
Xue, Wang, Tian, Li, Shi, Wei (b21) 2021; 58
European Foundation for South Asian Studies (b2) 2021
Fersini, Gasparini, Rizzi, Saibene, Chulvi, Rosso, Lees, Sorensen (b31) 2022
Pennington, Socher, Manning (b46) 2014
D. Kiela, H. Firooz, A. Mohan, V. Goswami, A. Singh, P. Ringshia, D. Testuggine, The Hateful Memes Challenge: Detecting Hate Speech in Multimodal Memes, in: H. Larochelle, M. Ranzato, R. Hadsell, M. Balcan, H. Lin (Eds.), Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020, December 6-12, 2020, Virtual, 2020.
Graves, Jaitly, Mohamed (b11) 2013
Ayetiran (b43) 2022; 252
Yang, Zhu, Liu, Han, Hu (b7) 2022
K. Simonyan, A. Zisserman, Very Deep Convolutional Networks for Large-Scale Image Recognition, in: Y. Bengio, Y. LeCun (Eds.), 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, May 7-9, 2015, Conference Track Proceedings, 2015.
Yang, Peng, Ghosh, Shilon, Ma, Moore, Predovic (b27) 2019
T. Dozat, Incorporating nesterov momentum into adam, in: 4th International Conference on Learning Representations, ICLR 2016 Workshop Track, San Juan, Puerto Rico, USA, May 2-4, 2016, Conference Track Proceedings, 2016.
Ayetiran, Sojka, Novotný (b44) 2021; 219
Li, Li, Le, Wang, Savarese, Hoi (b36) 2022
D.P. Kingma, J. Ba, Adam: A Method for Stochastic Optimization, in: Y. Bengio, Y. LeCun (Eds.), 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, May 7-9, 2015, Conference Track Proceedings, 2015.
Hochreiter, Schmidhuber (b39) 1997; 9
Lee, Cao, Fan, Jiang, Chong (b33) 2021
Giachanou, Zhang, Rosso (b20) 2020
Luong, Pham, Manning (b42) 2015
Singhal, Shah, Chakraborty, Kumaraguru, Satoh (b16) 2019
Yang, Zhu, Liu, Han, Hu (b30) 2022
Gomez, Gibert, Gómez, Karatzas (b6) 2020
Ioffe, Szegedy (b49) 2015; vol. 37
Shu, Mahudeswaran, Wang, Lee, Liu (b45) 2020; 8
Zhou, Wu, Zafarani (b5) 2020; 12085
Devlin, Chang, Lee, Toutanova (b17) 2019
Zhang, Giachanou, Rosso (b24) 2024
Xue (10.1016/j.is.2024.102378_b21) 2021; 58
Radford (10.1016/j.is.2024.102378_b37) 2021; vol. 139
Xiong (10.1016/j.is.2024.102378_b25) 2023; 93
Yang (10.1016/j.is.2024.102378_b27) 2019
Maity (10.1016/j.is.2024.102378_b29) 2022
Fersini (10.1016/j.is.2024.102378_b31) 2022
Luong (10.1016/j.is.2024.102378_b42) 2015
Bozarth (10.1016/j.is.2024.102378_b9) 2020
Chen (10.1016/j.is.2024.102378_b23) 2022
Gomez (10.1016/j.is.2024.102378_b6) 2020
Suryawanshi (10.1016/j.is.2024.102378_b4) 2020
Hochreiter (10.1016/j.is.2024.102378_b39) 1997; 9
Yang (10.1016/j.is.2024.102378_b7) 2022
Zhang (10.1016/j.is.2024.102378_b24) 2024
Li (10.1016/j.is.2024.102378_b38) 2022; vol. 162
Li (10.1016/j.is.2024.102378_b36) 2022
Lee (10.1016/j.is.2024.102378_b33) 2021
Zhong (10.1016/j.is.2024.102378_b35) 2022; vol. 13141
Ayetiran (10.1016/j.is.2024.102378_b43) 2022; 252
Srivastava (10.1016/j.is.2024.102378_b48) 2014; 15
10.1016/j.is.2024.102378_b47
Rizzi (10.1016/j.is.2024.102378_b32) 2023; 60
Shu (10.1016/j.is.2024.102378_b45) 2020; 8
Singhal (10.1016/j.is.2024.102378_b16) 2019
Giachanou (10.1016/j.is.2024.102378_b1) 2020
Giachanou (10.1016/j.is.2024.102378_b19) 2020; vol. 12284
Giachanou (10.1016/j.is.2024.102378_b20) 2020
Khattar (10.1016/j.is.2024.102378_b3) 2019
10.1016/j.is.2024.102378_b18
Lahat (10.1016/j.is.2024.102378_b13) 2014
Graves (10.1016/j.is.2024.102378_b11) 2013
Wang (10.1016/j.is.2024.102378_b15) 2018
Chen (10.1016/j.is.2024.102378_b10) 2021; 426
Pramanick (10.1016/j.is.2024.102378_b34) 2021
Kim (10.1016/j.is.2024.102378_b41) 2014
10.1016/j.is.2024.102378_b50
Fukushima (10.1016/j.is.2024.102378_b40) 1982; 15
Pennington (10.1016/j.is.2024.102378_b46) 2014
Ioffe (10.1016/j.is.2024.102378_b49) 2015; vol. 37
Alam (10.1016/j.is.2024.102378_b14) 2022
Koutlis (10.1016/j.is.2024.102378_b8) 2023
10.1016/j.is.2024.102378_b28
Ayetiran (10.1016/j.is.2024.102378_b44) 2021; 219
Hosseinmardi (10.1016/j.is.2024.102378_b26) 2016
Devlin (10.1016/j.is.2024.102378_b17) 2019
Zhou (10.1016/j.is.2024.102378_b5) 2020; 12085
European Foundation for South Asian Studies (10.1016/j.is.2024.102378_b2) 2021
Wu (10.1016/j.is.2024.102378_b22) 2021; ACL/IJCNLP 2021
Yang (10.1016/j.is.2024.102378_b30) 2022
Segura-Bedmar (10.1016/j.is.2024.102378_b12) 2022; 13
References_xml – start-page: 11
  year: 2019
  end-page: 18
  ident: b27
  article-title: Exploring deep multimodal fusion of text and photo for hate speech classification
  publication-title: Proceedings of the Third Workshop on Abusive Language Online
– start-page: 60
  year: 2020
  end-page: 71
  ident: b9
  article-title: Toward a better performance evaluation framework for fake news classification
  publication-title: Proceedings of the Fourteenth International AAAI Conference on Web and Social Media, ICWSM 2020, Held Virtually, Original Venue: Atlanta, Georgia, USA, June 8-11, 2020
– volume: 9
  start-page: 1735
  year: 1997
  end-page: 1780
  ident: b39
  article-title: Long short-term memory
  publication-title: Neural Comput.
– start-page: 6625
  year: 2022
  end-page: 6643
  ident: b14
  article-title: A survey on multimodal disinformation detection
  publication-title: Proceedings of the 29th International Conference on Computational Linguistics
– start-page: 39
  year: 2019
  end-page: 47
  ident: b16
  article-title: SpotFake: A multi-modal framework for fake news detection
  publication-title: Fifth IEEE International Conference on Multimedia Big Data, BigMM 2019, Singapore, September 11-13, 2019
– volume: vol. 37
  start-page: 448
  year: 2015
  end-page: 456
  ident: b49
  article-title: Batch normalization: Accelerating deep network training by reducing internal covariate shift
  publication-title: Proceedings of the 32nd International Conference on Machine Learning, ICML 2015, Lille, France, 6-11 July 2015
– volume: vol. 139
  start-page: 8748
  year: 2021
  end-page: 8763
  ident: b37
  article-title: Learning transferable visual models from natural language supervision
  publication-title: Proceedings of the 38th International Conference on Machine Learning, ICML 2021, 18-24 July 2021, Virtual Event
– year: 2021
  ident: b2
  article-title: The role of fake news in fueling hate speech and extremism online; promoting adequate measures for tackling the phenomenon
– start-page: 849
  year: 2018
  end-page: 857
  ident: b15
  article-title: EANN: event adversarial neural networks for multi-modal fake news detection
  publication-title: Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, KDD 2018, London, UK, August 19-23, 2018
– start-page: 1412
  year: 2015
  end-page: 1421
  ident: b42
  article-title: Effective approaches to attention-based neural machine translation
  publication-title: Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing, EMNLP 2015, Lisbon, Portugal, September 17-21, 2015
– volume: 426
  start-page: 195
  year: 2021
  end-page: 215
  ident: b10
  article-title: New ideas and trends in deep multimodal content understanding: A review
  publication-title: Neurocomputing
– start-page: 2915
  year: 2019
  end-page: 2921
  ident: b3
  article-title: MVAE: multimodal variational autoencoder for fake news detection
  publication-title: The World Wide Web Conference, WWW 2019, San Francisco, CA, USA, May 13-17, 2019
– volume: 13
  start-page: 284
  year: 2022
  ident: b12
  article-title: Multimodal fake news detection
  publication-title: Inf.
– start-page: 4439
  year: 2021
  end-page: 4455
  ident: b34
  article-title: MOMENTA: A multimodal framework for detecting harmful memes and their targets
  publication-title: Findings of the Association for Computational Linguistics: EMNLP 2021, Virtual Event / Punta Cana, Dominican Republic, 16-20 November, 2021
– start-page: 1746
  year: 2014
  end-page: 1751
  ident: b41
  article-title: Convolutional neural networks for sentence classification
  publication-title: Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing, EMNLP 2014, October 25-29, 2014, Doha, Qatar, a Meeting of SIGDAT, a Special Interest Group of the ACL
– volume: 8
  start-page: 171
  year: 2020
  end-page: 188
  ident: b45
  article-title: FakeNewsNet: A data repository with news content, social context, and spatiotemporal information for studying fake news on social media
  publication-title: Big Data
– reference: D.P. Kingma, J. Ba, Adam: A Method for Stochastic Optimization, in: Y. Bengio, Y. LeCun (Eds.), 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, May 7-9, 2015, Conference Track Proceedings, 2015.
– reference: D. Kiela, H. Firooz, A. Mohan, V. Goswami, A. Singh, P. Ringshia, D. Testuggine, The Hateful Memes Challenge: Detecting Hate Speech in Multimodal Memes, in: H. Larochelle, M. Ranzato, R. Hadsell, M. Balcan, H. Lin (Eds.), Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020, December 6-12, 2020, Virtual, 2020.
– volume: 252
  year: 2022
  ident: b43
  article-title: Attention-based aspect sentiment classification using enhanced learning through CNN-BiLSTM networks
  publication-title: Knowl.-Based Syst.
– start-page: 4505
  year: 2022
  end-page: 4514
  ident: b7
  article-title: Multimodal hate speech detection via cross-domain knowledge transfer
  publication-title: MM ’22: The 30th ACM International Conference on Multimedia, Lisboa, Portugal, October 10 - 14, 2022
– volume: ACL/IJCNLP 2021
  start-page: 2560
  year: 2021
  end-page: 2569
  ident: b22
  article-title: Multimodal fusion with co-attention networks for fake news detection
  publication-title: Findings of the Association for Computational Linguistics: ACL/IJCNLP 2021, Online Event, August 1-6, 2021
– start-page: 32
  year: 2020
  end-page: 41
  ident: b4
  article-title: Multimodal meme dataset (multiOFF) for identifying offensive content in image and text
  publication-title: Proceedings of the Second Workshop on Trolling, Aggression and Cyberbullying
– reference: T. Dozat, Incorporating nesterov momentum into adam, in: 4th International Conference on Learning Representations, ICLR 2016 Workshop Track, San Juan, Puerto Rico, USA, May 2-4, 2016, Conference Track Proceedings, 2016.
– start-page: 533
  year: 2022
  end-page: 549
  ident: b31
  article-title: SemEval-2022 task 5: Multimedia automatic misogyny identification
  publication-title: Proceedings of the 16th International Workshop on Semantic Evaluation, SemEval@NAACL 2022, Seattle, Washington, United States, July 14-15, 2022
– start-page: 647
  year: 2020
  end-page: 654
  ident: b20
  article-title: Multimodal multi-image fake news detection
  publication-title: 7th IEEE International Conference on Data Science and Advanced Analytics, DSAA 2020, Sydney, Australia, October 6-9, 2020
– volume: 219
  year: 2021
  ident: b44
  article-title: EDS-MEMBED: multi-sense embeddings based on enhanced distributional semantic structures via a graph walk over word senses
  publication-title: Knowl.-Based Syst.
– volume: 15
  start-page: 455
  year: 1982
  end-page: 469
  ident: b40
  article-title: Neocognitron: A new algorithm for pattern recognition tolerant of deformations and shifts in position
  publication-title: Pattern Recognit.
– year: 2024
  ident: b24
  article-title: Scenefnd: Multimodal fake news detection by modelling scene context information
  publication-title: J. Inf. Sci.
– start-page: 4171
  year: 2019
  end-page: 4186
  ident: b17
  article-title: BERT: pre-training of deep bidirectional transformers for language understanding
  publication-title: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL-HLT 2019, Minneapolis, MN, USA, June 2-7, 2019, Volume 1 (Long and Short Papers)
– volume: vol. 162
  start-page: 12888
  year: 2022
  end-page: 12900
  ident: b38
  article-title: BLIP: bootstrapping language-image pre-training for unified vision-language understanding and generation
  publication-title: International Conference on Machine Learning, ICML 2022, 17-23 July 2022, Baltimore, Maryland, USA
– start-page: 1739
  year: 2022
  end-page: 1749
  ident: b29
  article-title: A multitask framework for sentiment, emotion and sarcasm aware cyberbullying detection from multi-modal code-mixed memes
  publication-title: SIGIR ’22: The 45th International ACM SIGIR Conference on Research and Development in Information Retrieval, Madrid, Spain, July 11 - 15, 2022
– volume: 60
  year: 2023
  ident: b32
  article-title: Recognizing misogynous memes: Biased models and tricky archetypes
  publication-title: Inf. Process. Manag.
– volume: 15
  start-page: 1929
  year: 2014
  end-page: 1958
  ident: b48
  article-title: Dropout: A simple way to prevent neural networks from overfitting
  publication-title: J. Mach. Learn. Res.
– volume: 93
  start-page: 150
  year: 2023
  end-page: 158
  ident: b25
  article-title: TRIMOON: two-round inconsistency-based multi-modal fusion network for fake news detection
  publication-title: Inf. Fusion
– start-page: 4505
  year: 2022
  end-page: 4514
  ident: b30
  article-title: Multimodal hate speech detection via cross-domain knowledge transfer
  publication-title: MM ’22: The 30th ACM International Conference on Multimedia, Lisboa, Portugal, October 10 - 14, 2022
– reference: K. Simonyan, A. Zisserman, Very Deep Convolutional Networks for Large-Scale Image Recognition, in: Y. Bengio, Y. LeCun (Eds.), 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, May 7-9, 2015, Conference Track Proceedings, 2015.
– start-page: 1459
  year: 2020
  end-page: 1467
  ident: b6
  article-title: Exploring hate speech detection in multimodal publications
  publication-title: IEEE Winter Conference on Applications of Computer Vision, WACV 2020, Snowmass Village, CO, USA, March 1-5, 2020
– start-page: 101
  year: 2014
  end-page: 105
  ident: b13
  article-title: Challenges in multimodal data fusion
  publication-title: 22nd European Signal Processing Conference, EUSIPCO 2014, Lisbon, Portugal, September 1-5, 2014
– start-page: 3503
  year: 2020
  end-page: 3504
  ident: b1
  article-title: The battle against online harmful information: The cases of fake news and hate speech
  publication-title: CIKM ’20: The 29th ACM International Conference on Information and Knowledge Management, Virtual Event, Ireland, October 19-23, 2020
– volume: vol. 12284
  start-page: 30
  year: 2020
  end-page: 38
  ident: b19
  article-title: Multimodal fake news detection with textual, visual and semantic information
  publication-title: Text, Speech, and Dialogue - 23rd International Conference, TSD 2020, Brno, Czech Republic, September 8-11, 2020, Proceedings
– start-page: 186
  year: 2016
  end-page: 192
  ident: b26
  article-title: Prediction of cyberbullying incidents in a media-based social network
  publication-title: 2016 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2016, San Francisco, CA, USA, August 18-21, 2016
– start-page: 1532
  year: 2014
  end-page: 1543
  ident: b46
  article-title: Glove: Global vectors for word representation
  publication-title: Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing, EMNLP 2014, October 25-29, 2014, Doha, Qatar, a Meeting of SIGDAT, a Special Interest Group of the ACL
– year: 2022
  ident: b36
  article-title: LAVIS: A library for language-vision intelligence
– volume: 58
  year: 2021
  ident: b21
  article-title: Detecting fake news by exploring the consistency of multimodal data
  publication-title: Inf. Process. Manag.
– start-page: 586
  year: 2023
  end-page: 591
  ident: b8
  article-title: MemeFier: Dual-stage modality fusion for image meme classification
  publication-title: Proceedings of the 2023 ACM International Conference on Multimedia Retrieval, ICMR 2023, Thessaloniki, Greece, June 12-15, 2023
– volume: 12085
  start-page: 354
  year: 2020
  end-page: 367
  ident: b5
  article-title: SAFE: similarity-aware multi-modal fake news detection
  publication-title: Advances in Knowledge Discovery and Data Mining - 24th Pacific-Asia Conference, PAKDD 2020, Singapore, May 11-14, 2020, Proceedings, Part II
– start-page: 5138
  year: 2021
  end-page: 5147
  ident: b33
  article-title: Disentangling hate in online memes
  publication-title: MM ’21: ACM Multimedia Conference, Virtual Event, China, October 20 - 24, 2021
– volume: vol. 13141
  start-page: 599
  year: 2022
  end-page: 611
  ident: b35
  article-title: Combining knowledge and multi-modal fusion for meme classification
  publication-title: MultiMedia Modeling - 28th International Conference, MMM 2022, Phu Quoc, Vietnam, June 6-10, 2022, Proceedings, Part I
– start-page: 273
  year: 2013
  end-page: 278
  ident: b11
  article-title: Hybrid speech recognition with deep bidirectional LSTM
  publication-title: 2013 IEEE Workshop on Automatic Speech Recognition and Understanding, Olomouc, Czech Republic, December 8-12, 2013
– start-page: 2897
  year: 2022
  end-page: 2905
  ident: b23
  article-title: Cross-modal ambiguity learning for multimodal fake news detection
  publication-title: WWW ’22: The ACM Web Conference 2022, Virtual Event, Lyon, France, April 25 - 29, 2022
– volume: vol. 162
  start-page: 12888
  year: 2022
  ident: 10.1016/j.is.2024.102378_b38
  article-title: BLIP: bootstrapping language-image pre-training for unified vision-language understanding and generation
– start-page: 5138
  year: 2021
  ident: 10.1016/j.is.2024.102378_b33
  article-title: Disentangling hate in online memes
– start-page: 2897
  year: 2022
  ident: 10.1016/j.is.2024.102378_b23
  article-title: Cross-modal ambiguity learning for multimodal fake news detection
– year: 2024
  ident: 10.1016/j.is.2024.102378_b24
  article-title: Scenefnd: Multimodal fake news detection by modelling scene context information
  publication-title: J. Inf. Sci.
– start-page: 4505
  year: 2022
  ident: 10.1016/j.is.2024.102378_b7
  article-title: Multimodal hate speech detection via cross-domain knowledge transfer
– start-page: 60
  year: 2020
  ident: 10.1016/j.is.2024.102378_b9
  article-title: Toward a better performance evaluation framework for fake news classification
– start-page: 586
  year: 2023
  ident: 10.1016/j.is.2024.102378_b8
  article-title: MemeFier: Dual-stage modality fusion for image meme classification
– volume: 219
  year: 2021
  ident: 10.1016/j.is.2024.102378_b44
  article-title: EDS-MEMBED: multi-sense embeddings based on enhanced distributional semantic structures via a graph walk over word senses
  publication-title: Knowl.-Based Syst.
  doi: 10.1016/j.knosys.2021.106902
– start-page: 849
  year: 2018
  ident: 10.1016/j.is.2024.102378_b15
  article-title: EANN: event adversarial neural networks for multi-modal fake news detection
– start-page: 186
  year: 2016
  ident: 10.1016/j.is.2024.102378_b26
  article-title: Prediction of cyberbullying incidents in a media-based social network
– start-page: 1739
  year: 2022
  ident: 10.1016/j.is.2024.102378_b29
  article-title: A multitask framework for sentiment, emotion and sarcasm aware cyberbullying detection from multi-modal code-mixed memes
– volume: 9
  start-page: 1735
  issue: 8
  year: 1997
  ident: 10.1016/j.is.2024.102378_b39
  article-title: Long short-term memory
  publication-title: Neural Comput.
  doi: 10.1162/neco.1997.9.8.1735
– start-page: 1412
  year: 2015
  ident: 10.1016/j.is.2024.102378_b42
  article-title: Effective approaches to attention-based neural machine translation
– start-page: 273
  year: 2013
  ident: 10.1016/j.is.2024.102378_b11
  article-title: Hybrid speech recognition with deep bidirectional LSTM
– volume: 93
  start-page: 150
  year: 2023
  ident: 10.1016/j.is.2024.102378_b25
  article-title: TRIMOON: two-round inconsistency-based multi-modal fusion network for fake news detection
  publication-title: Inf. Fusion
  doi: 10.1016/j.inffus.2022.12.016
– start-page: 101
  year: 2014
  ident: 10.1016/j.is.2024.102378_b13
  article-title: Challenges in multimodal data fusion
– start-page: 39
  year: 2019
  ident: 10.1016/j.is.2024.102378_b16
  article-title: SpotFake: A multi-modal framework for fake news detection
– volume: 15
  start-page: 455
  issue: 6
  year: 1982
  ident: 10.1016/j.is.2024.102378_b40
  article-title: Neocognitron: A new algorithm for pattern recognition tolerant of deformations and shifts in position
  publication-title: Pattern Recognit.
  doi: 10.1016/0031-3203(82)90024-3
– volume: vol. 12284
  start-page: 30
  year: 2020
  ident: 10.1016/j.is.2024.102378_b19
  article-title: Multimodal fake news detection with textual, visual and semantic information
– start-page: 4505
  year: 2022
  ident: 10.1016/j.is.2024.102378_b30
  article-title: Multimodal hate speech detection via cross-domain knowledge transfer
– volume: 426
  start-page: 195
  year: 2021
  ident: 10.1016/j.is.2024.102378_b10
  article-title: New ideas and trends in deep multimodal content understanding: A review
  publication-title: Neurocomputing
  doi: 10.1016/j.neucom.2020.10.042
– year: 2021
  ident: 10.1016/j.is.2024.102378_b2
– volume: 13
  start-page: 284
  issue: 6
  year: 2022
  ident: 10.1016/j.is.2024.102378_b12
  article-title: Multimodal fake news detection
  publication-title: Inf.
– volume: vol. 37
  start-page: 448
  year: 2015
  ident: 10.1016/j.is.2024.102378_b49
  article-title: Batch normalization: Accelerating deep network training by reducing internal covariate shift
– start-page: 533
  year: 2022
  ident: 10.1016/j.is.2024.102378_b31
  article-title: SemEval-2022 task 5: Multimedia automatic misogyny identification
– ident: 10.1016/j.is.2024.102378_b28
– volume: vol. 13141
  start-page: 599
  year: 2022
  ident: 10.1016/j.is.2024.102378_b35
  article-title: Combining knowledge and multi-modal fusion for meme classification
– start-page: 1459
  year: 2020
  ident: 10.1016/j.is.2024.102378_b6
  article-title: Exploring hate speech detection in multimodal publications
– start-page: 4439
  year: 2021
  ident: 10.1016/j.is.2024.102378_b34
  article-title: MOMENTA: A multimodal framework for detecting harmful memes and their targets
– start-page: 6625
  year: 2022
  ident: 10.1016/j.is.2024.102378_b14
  article-title: A survey on multimodal disinformation detection
– volume: 15
  start-page: 1929
  issue: 1
  year: 2014
  ident: 10.1016/j.is.2024.102378_b48
  article-title: Dropout: A simple way to prevent neural networks from overfitting
  publication-title: J. Mach. Learn. Res.
– start-page: 1746
  year: 2014
  ident: 10.1016/j.is.2024.102378_b41
  article-title: Convolutional neural networks for sentence classification
– start-page: 3503
  year: 2020
  ident: 10.1016/j.is.2024.102378_b1
  article-title: The battle against online harmful information: The cases of fake news and hate speech
– ident: 10.1016/j.is.2024.102378_b18
– year: 2022
  ident: 10.1016/j.is.2024.102378_b36
– volume: 252
  year: 2022
  ident: 10.1016/j.is.2024.102378_b43
  article-title: Attention-based aspect sentiment classification using enhanced learning through CNN-BiLSTM networks
  publication-title: Knowl.-Based Syst.
  doi: 10.1016/j.knosys.2022.109409
– volume: 8
  start-page: 171
  issue: 3
  year: 2020
  ident: 10.1016/j.is.2024.102378_b45
  article-title: FakeNewsNet: A data repository with news content, social context, and spatiotemporal information for studying fake news on social media
  publication-title: Big Data
  doi: 10.1089/big.2020.0062
– volume: 12085
  start-page: 354
  year: 2020
  ident: 10.1016/j.is.2024.102378_b5
  article-title: SAFE: similarity-aware multi-modal fake news detection
– start-page: 4171
  year: 2019
  ident: 10.1016/j.is.2024.102378_b17
  article-title: BERT: pre-training of deep bidirectional transformers for language understanding
– volume: ACL/IJCNLP 2021
  start-page: 2560
  year: 2021
  ident: 10.1016/j.is.2024.102378_b22
  article-title: Multimodal fusion with co-attention networks for fake news detection
– start-page: 2915
  year: 2019
  ident: 10.1016/j.is.2024.102378_b3
  article-title: MVAE: multimodal variational autoencoder for fake news detection
– volume: 58
  issue: 5
  year: 2021
  ident: 10.1016/j.is.2024.102378_b21
  article-title: Detecting fake news by exploring the consistency of multimodal data
  publication-title: Inf. Process. Manag.
  doi: 10.1016/j.ipm.2021.102610
– ident: 10.1016/j.is.2024.102378_b50
– start-page: 32
  year: 2020
  ident: 10.1016/j.is.2024.102378_b4
  article-title: Multimodal meme dataset (multiOFF) for identifying offensive content in image and text
– start-page: 1532
  year: 2014
  ident: 10.1016/j.is.2024.102378_b46
  article-title: Glove: Global vectors for word representation
– volume: 60
  issue: 5
  year: 2023
  ident: 10.1016/j.is.2024.102378_b32
  article-title: Recognizing misogynous memes: Biased models and tricky archetypes
  publication-title: Inf. Process. Manag.
  doi: 10.1016/j.ipm.2023.103474
– volume: vol. 139
  start-page: 8748
  year: 2021
  ident: 10.1016/j.is.2024.102378_b37
  article-title: Learning transferable visual models from natural language supervision
– start-page: 647
  year: 2020
  ident: 10.1016/j.is.2024.102378_b20
  article-title: Multimodal multi-image fake news detection
– ident: 10.1016/j.is.2024.102378_b47
– start-page: 11
  year: 2019
  ident: 10.1016/j.is.2024.102378_b27
  article-title: Exploring deep multimodal fusion of text and photo for hate speech classification
SSID ssj0002599
Score 2.476748
Snippet Fake news, hate speech and offensive language are related evil triplets currently affecting modern societies. Text modality for the computational detection of...
SourceID crossref
elsevier
SourceType Enrichment Source
Index Database
Publisher
StartPage 102378
SubjectTerms BiLSTM-CNN
Fake news
Hate speech
Inter-modal attention
Multimodal content understanding
Multimodal fusion
Offensive language
Unified modality
Title An inter-modal attention-based deep learning framework using unified modality for multimodal fake news, hate speech and offensive language detection
URI https://dx.doi.org/10.1016/j.is.2024.102378
Volume 123
WOSCitedRecordID wos001217561900001&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: PRVESC
  databaseName: Elsevier SD Freedom Collection Journals 2021
  customDbUrl:
  eissn: 1873-6076
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0002599
  issn: 0306-4379
  databaseCode: AIEXJ
  dateStart: 19950301
  isFulltext: true
  titleUrlDefault: https://www.sciencedirect.com
  providerName: Elsevier
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV3JbhNBEG2ZhAM5sAQQYVMduCAzMItnOxqUCDhESATJt1F3T1cywYwtexwlfAdHPpbqbWzCIkDiMrZavYxcz13V1a-qGHsSYZimnKeBkjUdUKK0CISI0yAuOYaY68LT0hSbyA8Pi8mkfDcYfPWxMGfTvG2L8_Ny_l9FTW0kbB06-xfi7ielBvpOQqcniZ2efyT4cWtyQCyCT7NaJwLoOstoDLTCqoe1UnNfK-J4iJ6bNVwZp8GqbVAbpWZs49ichnRoZ0P-UZkq5Fo0J2SnDpdzpaQNj5shOjq894LSap3herWbRrALgTLIs5mkjevXxi5uuiYuVNcsuCs20nBUwwNSYqv-GKBv-cvs87H-fJkJZXZ21zh1Pmnn0YhHPfvVudl8qM2a12TCu8Is0MkTreKyu3WRJ0EW2gIy_XZu45d_UA3WS3FKsz3Xi5qcFbZ60KWE2-_1UnolTa8lBT-5wrbjPC1pz9wev9mfvO01PR0dS3tLZV_NXYNb_uD36_zc7NkwZY5usuvuDAJji51bbKDaXXbD1_cAt93vsp2NZJW32ZdxCxvAgkvAAg0s8MCCHlhggAUOWOCBBSRrWAMLNLBAA-sZaFiBhRUQrKCHFXhYQQ-rO-zDwf7Rq9eBq-kRyCTJukCEKFQZiZxLjjGm9YiLPFThKEIlYxlHinpIJbKI-owEV9QjQgwLrJEsV0zusq121qp7DGTCsyzPVZEj9ZSJwJpnBaIoFdnYNd9jL_xPXkmX8F7XXZlWntl4WjXLSgupskLaY0_7EXOb7OU3fRMvxcoZq9YIrQhwvxx1_59GPWDX1v-Th2yrW6zUI3ZVnnXNcvHYofIb8ne97Q
linkProvider Elsevier
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=An+inter-modal+attention-based+deep+learning+framework+using+unified+modality+for+multimodal+fake+news%2C+hate+speech+and+offensive+language+detection&rft.jtitle=Information+systems+%28Oxford%29&rft.au=Ayetiran%2C+Eniafe+Festus&rft.au=%C3%96zg%C3%B6bek%2C+%C3%96zlem&rft.date=2024-07-01&rft.pub=Elsevier+Ltd&rft.issn=0306-4379&rft.eissn=1873-6076&rft.volume=123&rft_id=info:doi/10.1016%2Fj.is.2024.102378&rft.externalDocID=S030643792400036X
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0306-4379&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0306-4379&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0306-4379&client=summon