Integrating implicit and explicit linguistic phenomena via multi-task learning for offensive language detection
The analysis and detection of offensive content in textual information have become a great challenge for the Natural Language Processing community. Most of the research conducted so far on offensive language detection have addressed this task as a sole optimization objective. However, other linguist...
Uloženo v:
| Vydáno v: | Knowledge-based systems Ročník 258; s. 109965 |
|---|---|
| Hlavní autoři: | , , , |
| Médium: | Journal Article |
| Jazyk: | angličtina |
| Vydáno: |
Elsevier B.V
22.12.2022
|
| Témata: | |
| ISSN: | 0950-7051, 1872-7409 |
| On-line přístup: | Získat plný text |
| Tagy: |
Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
|
| Abstract | The analysis and detection of offensive content in textual information have become a great challenge for the Natural Language Processing community. Most of the research conducted so far on offensive language detection have addressed this task as a sole optimization objective. However, other linguistic phenomena that are arguably correlated with offensive language and therefore could be beneficial to recognize this type of problematic content on the Web, have not been explored in depth so far. Thus, the goal of this study is to investigate whether explicit and implicit concepts involved in the expression of offensive language help in the detection of this phenomenon and how to incorporate these concepts in a computational system. We propose a multi-task learning approach that includes such concepts according to the relevance shown by a feature selection method called mutual information. Our experiments show that some phenomena such as constructiveness, target group and person, figurative language (sarcasm and mockery), insults, improper language, and emotions combined together help to optimize the offensive language detection task, outperforming a state-of-the-art method (the transformer BETO) that we use as our baseline to compare the results.
•Addressing offensive language detection for Spanish texts.•Studying implicit and explicit linguistic phenomena for offensive language.•Assessing the impact of including phenomena via multi-task learning.•Performance comparison of multi-task learning models with a well-known Transformer.•Analyzing the knowledge transfer of the explored phenomena. |
|---|---|
| AbstractList | The analysis and detection of offensive content in textual information have become a great challenge for the Natural Language Processing community. Most of the research conducted so far on offensive language detection have addressed this task as a sole optimization objective. However, other linguistic phenomena that are arguably correlated with offensive language and therefore could be beneficial to recognize this type of problematic content on the Web, have not been explored in depth so far. Thus, the goal of this study is to investigate whether explicit and implicit concepts involved in the expression of offensive language help in the detection of this phenomenon and how to incorporate these concepts in a computational system. We propose a multi-task learning approach that includes such concepts according to the relevance shown by a feature selection method called mutual information. Our experiments show that some phenomena such as constructiveness, target group and person, figurative language (sarcasm and mockery), insults, improper language, and emotions combined together help to optimize the offensive language detection task, outperforming a state-of-the-art method (the transformer BETO) that we use as our baseline to compare the results.
•Addressing offensive language detection for Spanish texts.•Studying implicit and explicit linguistic phenomena for offensive language.•Assessing the impact of including phenomena via multi-task learning.•Performance comparison of multi-task learning models with a well-known Transformer.•Analyzing the knowledge transfer of the explored phenomena. |
| ArticleNumber | 109965 |
| Author | Plaza-del-Arco, Flor Miriam Ureña-López, L. Alfonso Martín-Valdivia, María-Teresa Molina-González, M. Dolores |
| Author_xml | – sequence: 1 givenname: Flor Miriam surname: Plaza-del-Arco fullname: Plaza-del-Arco, Flor Miriam email: fmplaza@ujaen.es – sequence: 2 givenname: M. Dolores orcidid: 0000-0002-8348-7154 surname: Molina-González fullname: Molina-González, M. Dolores email: mdmolina@ujaen.es – sequence: 3 givenname: L. Alfonso surname: Ureña-López fullname: Ureña-López, L. Alfonso email: laurena@ujaen.es – sequence: 4 givenname: María-Teresa surname: Martín-Valdivia fullname: Martín-Valdivia, María-Teresa email: maite@ujaen.es |
| BookMark | eNqFkMtOAyEUhompiW31DVzwAlNhruDCxDRemjRx0z2hcKi0M9AAbezbO5Nx5UJXBA7fn_N_MzRx3gFC95QsKKH1w35xcD5e4iIned4_cV5XV2hKWZNnTUn4BE0Jr0jWkIreoFmMe0L6n5RNkV-5BLsgk3U7bLtja5VNWDqN4evn0vajk43JKnz8BOc7cBKfrcTdqU02SzIecAsyuCHC-IC9MeCiPQNuZY_KHWANCVSy3t2iayPbCHc_5xxtXl82y_ds_fG2Wj6vM1WQOmUajGR0q0tjlOKs0ExV2tAtVxS0bBgzXOe65hpKXmhQjBYFpaaqmKQgdTFH5Rirgo8xgBHHYDsZLoISMTgTezE6E4MzMTrrscdfWC9ADnunIG37H_w0wtD3OlsIIioLToG2oS8vtLd_B3wDrx6Rzw |
| CitedBy_id | crossref_primary_10_1007_s00521_024_10753_7 crossref_primary_10_1016_j_saa_2025_125866 crossref_primary_10_1515_lpp_2023_0019 crossref_primary_10_1016_j_eswa_2025_126705 crossref_primary_10_1109_ACCESS_2023_3310244 crossref_primary_10_3390_axioms13010006 crossref_primary_10_1145_3576913 crossref_primary_10_1515_lpp_2023_0012 crossref_primary_10_3390_bdcc8090113 crossref_primary_10_1007_s13042_025_02715_9 crossref_primary_10_1016_j_knosys_2023_111023 crossref_primary_10_1016_j_knosys_2024_112298 |
| Cites_doi | 10.1103/PhysRevE.69.066138 10.1561/1500000011 10.1145/3232676 10.1007/s11192-020-03737-6 10.1080/02699939208411068 10.3390/app11083610 10.1016/j.eswa.2021.116398 10.1037/h0074772 10.1109/TKDE.2009.191 10.1023/A:1007379606734 10.1609/icwsm.v12i1.14991 10.1080/0952813X.2017.1409284 10.1371/journal.pone.0221152 10.1145/2872427.2883062 10.1145/3041021.3054211 10.1145/3369869 10.1109/ACCESS.2021.3103697 10.1016/j.eswa.2020.114120 |
| ContentType | Journal Article |
| Copyright | 2022 Elsevier B.V. |
| Copyright_xml | – notice: 2022 Elsevier B.V. |
| DBID | AAYXX CITATION |
| DOI | 10.1016/j.knosys.2022.109965 |
| DatabaseName | CrossRef |
| DatabaseTitle | CrossRef |
| DatabaseTitleList | |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Computer Science |
| EISSN | 1872-7409 |
| ExternalDocumentID | 10_1016_j_knosys_2022_109965 S0950705122010589 |
| GroupedDBID | --K --M .DC .~1 0R~ 1B1 1~. 1~5 4.4 457 4G. 5VS 7-5 71M 77K 8P~ 9JN AACTN AAEDT AAEDW AAIAV AAIKJ AAKOC AALRI AAOAW AAQFI AAXUO AAYFN ABAOU ABBOA ABIVO ABJNI ABMAC ABYKQ ACAZW ACDAQ ACGFS ACRLP ACZNC ADBBV ADEZE ADGUI ADTZH AEBSH AECPX AEKER AENEX AFKWA AFTJW AGHFR AGUBO AGYEJ AHHHB AHJVU AHZHX AIALX AIEXJ AIKHN AITUG AJOXV ALMA_UNASSIGNED_HOLDINGS AMFUW AMRAJ AOUOD ARUGR AXJTR BJAXD BKOJK BLXMC CS3 DU5 EBS EFJIC EFLBG EO8 EO9 EP2 EP3 FDB FIRID FNPLU FYGXN G-Q GBLVA GBOLZ IHE J1W JJJVA KOM LG9 LY7 M41 MHUIS MO0 N9A O-L O9- OAUVE OZT P-8 P-9 P2P PC. PQQKQ Q38 ROL RPZ SDF SDG SDP SES SPC SPCBC SST SSV SSW SSZ T5K WH7 XPP ZMT ~02 ~G- 29L 77I 9DU AAQXK AATTM AAXKI AAYWO AAYXX ABDPE ABWVN ABXDB ACLOT ACNNM ACRPL ACVFH ADCNI ADJOM ADMUD ADNMO AEIPS AEUPX AFJKZ AFPUW AGQPQ AIGII AIIUN AKBMS AKRWK AKYEP ANKPU APXCP ASPBG AVWKF AZFZN CITATION EFKBS EJD FEDTE FGOYB G-2 HLZ HVGLF HZ~ R2- SBC SET SEW UHS WUQ ~HD |
| ID | FETCH-LOGICAL-c306t-defa81bd4ffcc983d8c5df1b9c1eda788f9d2d69de493dec813311f558a1ead3 |
| ISICitedReferencesCount | 15 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000880093300002&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 0950-7051 |
| IngestDate | Tue Nov 18 21:50:34 EST 2025 Sat Nov 29 07:06:16 EST 2025 Fri Feb 23 02:39:27 EST 2024 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Keywords | Linguistic phenomena Natural language processing Spanish Multi-task learning Offensive language |
| Language | English |
| LinkModel | OpenURL |
| MergedId | FETCHMERGED-LOGICAL-c306t-defa81bd4ffcc983d8c5df1b9c1eda788f9d2d69de493dec813311f558a1ead3 |
| ORCID | 0000-0002-8348-7154 |
| ParticipantIDs | crossref_primary_10_1016_j_knosys_2022_109965 crossref_citationtrail_10_1016_j_knosys_2022_109965 elsevier_sciencedirect_doi_10_1016_j_knosys_2022_109965 |
| PublicationCentury | 2000 |
| PublicationDate | 2022-12-22 |
| PublicationDateYYYYMMDD | 2022-12-22 |
| PublicationDate_xml | – month: 12 year: 2022 text: 2022-12-22 day: 22 |
| PublicationDecade | 2020 |
| PublicationTitle | Knowledge-based systems |
| PublicationYear | 2022 |
| Publisher | Elsevier B.V |
| Publisher_xml | – name: Elsevier B.V |
| References | Safi Samghabadi, Hatami, Shafaei, Kar, Solorio (b28) 2020 van Aken, Risch, Krestel, Löser (b31) 2018 R. Kumar, A.K. Ojha, S. Malmasi, M. Zampieri, Evaluating aggression identification in social media, in: Proceedings of the Second Workshop on Trolling, Aggression and Cyberbullying, 2020, pp. 1–5. Kolhatkar, Thain, Sorensen, Dixon, Taboada (b43) 2020 Taulé, Ariza, Nofre, Amigó, Rosso (b5) 2021; 67 Kraskov, Stögbauer, Grassberger (b59) 2004; 69 Elmadany, Zhang, Abdul-Mageed, Hashemi (b29) 2020 Ruder (b49) 2019 Zampieri, Malmasi, Nakov, Rosenthal, Farra, Kumar (b12) 2019 Cañete, Chaperon, Fuentes, Ho, Kang, Pérez (b52) 2020 Devlin, Chang, Lee, Toutanova (b21) 2018 Plaza-del-Arco, Strapparava, Ureña-López, Martín-Valdivia (b53) 2020 Plaza-del-Arco, Molina-González, Ureña-López, Martín-Valdivia (b32) 2020; 20 Paszke, Gross, Massa, Lerer, Bradbury, Chanan, Killeen, Lin, Gimelshein, Antiga (b58) 2019 Frenda, Cignarella, Basile, Bosco, Patti, Rosso (b33) 2022; 193 Plaza-del-Arco, Molina-González, Ureña-López, Martín-Valdivia (b2) 2021; 166 C. Nobata, J. Tetreault, A. Thomas, Y. Mehdad, Y. Chang, Abusive Language Detection in Online User Content, in: Proceedings of the 25th International Conference on World Wide Web, 2016, pp. 145–153. Plaza-del-Arco, Montejo-Ráez, Ureña-López, Martín-Valdivia (b15) 2021 Ranasinghe, Zampieri (b22) 2020 Plaza-del-Arco, Halat, Padó, Klinger (b37) 2021 Wiegand, Ruppenhofer, Eder (b30) 2021 Plaza-del-Arco, Molina-González, Ureña-López, Martín-Valdivia (b35) 2021; 9 Poletto, Basile, Sanguinetti, Bosco, Patti (b9) 2020 Patrick (b39) 1901; 8 Sarkar, Zampieri, Ranasinghe, Ororbia (b23) 2021 Tontodimamma, Nissi, Sarra, Fontanella (b26) 2021; 126 Cardwell (b44) 1996 S. Lamprinidis, F. Bianchi, D. Hardt, D. Hovy, Universal joy a data set and results for classifying emotions across languages, in: Proceedings of the Eleventh Workshop on Computational Approaches To Subjectivity, Sentiment and Social Media Analysis, 2021, pp. 62–75. Plaza-del-Arco, Casavantes, Escalante, Martín-Valdivia, Montejo-Ráez, Montes-y-Gómez, Jarquín-Vásquez, Villaseñor-Pineda (b14) 2021; 67 Warner, Hirschberg (b17) 2012 Pang, Lee (b47) 2008; 2 Rajamanickam, Mishra, Yannakoudakis, Shutova (b34) 2020 Rodríguez, Argueta, Chen (b41) 2019 Alorainy, Burnap, Liu, Javed, Williams (b40) 2018 Vaswani, Shazeer, Parmar, Uszkoreit, Jones, Gomez, Kaiser, Polosukhin (b57) 2017 Fortuna, Nunes (b24) 2018; 51 Martins, Gomes, Almeida, Novais, Henriques (b27) 2018 Davidson, Warmsley, Macy, Weber (b19) 2017 Malmasi, Zampieri (b20) 2018; 30 Sánchez-Junquera, Chulvi, Rosso, Ponzetto (b45) 2021; 11 Struß, Siegel, Ruppenhofer, Wiegand, Klenner (b11) 2019 Caruana (b50) 1997; 28 Awal, Cao, Lee, Mitrovic (b36) 2021 Kolhatkar, Taboada (b42) 2017 Zhang, Yang (b51) 2021 Pan, Yang (b48) 2010; 22 Ródriguez-Sánchez, de Albornoz, Plaza, Gonzalo, Rosso, Comet, Donoso (b16) 2021; 67 Caselli, Basile, Mitrović, Kartoziya, Granitzer (b46) 2020 Ekman (b38) 1992; 6 D. Chatzakou, N. Kourtellis, J. Blackburn, E. De Cristofaro, G. Stringhini, A. Vakali, Detecting aggressors and bullies on Twitter, in: Proceedings of the 26th International Conference on World Wide Web Companion, 2017, pp. 767–768. M. Wiegand, M. Siegel, J. Ruppenhofer, Overview of the GermEval 2018 Shared Task on the Identification of Offensive Language, in: Proceedings of GermEval 2018, 14th Conference on Natural Language Processing, KONVENS 2018, Vienna, Austria, 2018. Nobata, Tetreault, Thomas, Mehdad, Chang (b18) 2016 Kogilavani, Malliga, Jaiabinaya, Malini, Manisha Kokila (b1) 2021 M. Wiegand, J. Ruppenhofer, T. Kleinbauer, Detection of abusive language: the problem of biased datasets, in: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), 2019, pp. 602–608. Zampieri, Nakov, Rosenthal, Atanasova, Karadzhov, Mubarak, Derczynski, Pitenis, Çöltekin (b13) 2020 A.M. Founta, C. Djouvas, D. Chatzakou, I. Leontiadis, J. Blackburn, G. Stringhini, A. Vakali, M. Sirivianos, N. Kourtellis, Large scale crowdsourcing and characterization of twitter abusive behavior, in: Twelfth International AAAI Conference on Web and Social Media, 2018. C. Zimmerman, M.-K. Stein, D. Hardt, R. Vatrapu, Emergence of things felt: Harnessing the semantic space of Facebook feeling tags, in: Thirty Sixth International Conference on Information Systems, Fort Worth, 2015. Baziotis, Pelekis, Doulkeridis (b56) 2017 MacAvaney, Yao, Yang, Russell, Goharian, Frieder (b25) 2019; 14 Martins (10.1016/j.knosys.2022.109965_b27) 2018 Nobata (10.1016/j.knosys.2022.109965_b18) 2016 10.1016/j.knosys.2022.109965_b8 10.1016/j.knosys.2022.109965_b7 Baziotis (10.1016/j.knosys.2022.109965_b56) 2017 10.1016/j.knosys.2022.109965_b6 10.1016/j.knosys.2022.109965_b4 10.1016/j.knosys.2022.109965_b3 10.1016/j.knosys.2022.109965_b10 10.1016/j.knosys.2022.109965_b54 Poletto (10.1016/j.knosys.2022.109965_b9) 2020 Sánchez-Junquera (10.1016/j.knosys.2022.109965_b45) 2021; 11 Paszke (10.1016/j.knosys.2022.109965_b58) 2019 Plaza-del-Arco (10.1016/j.knosys.2022.109965_b32) 2020; 20 Fortuna (10.1016/j.knosys.2022.109965_b24) 2018; 51 Rodríguez (10.1016/j.knosys.2022.109965_b41) 2019 10.1016/j.knosys.2022.109965_b55 Kolhatkar (10.1016/j.knosys.2022.109965_b42) 2017 Kolhatkar (10.1016/j.knosys.2022.109965_b43) 2020 Ranasinghe (10.1016/j.knosys.2022.109965_b22) 2020 Patrick (10.1016/j.knosys.2022.109965_b39) 1901; 8 Pang (10.1016/j.knosys.2022.109965_b47) 2008; 2 Elmadany (10.1016/j.knosys.2022.109965_b29) 2020 Safi Samghabadi (10.1016/j.knosys.2022.109965_b28) 2020 Plaza-del-Arco (10.1016/j.knosys.2022.109965_b37) 2021 Ródriguez-Sánchez (10.1016/j.knosys.2022.109965_b16) 2021; 67 Caselli (10.1016/j.knosys.2022.109965_b46) 2020 Kogilavani (10.1016/j.knosys.2022.109965_b1) 2021 Devlin (10.1016/j.knosys.2022.109965_b21) 2018 Warner (10.1016/j.knosys.2022.109965_b17) 2012 Plaza-del-Arco (10.1016/j.knosys.2022.109965_b53) 2020 Cañete (10.1016/j.knosys.2022.109965_b52) 2020 Vaswani (10.1016/j.knosys.2022.109965_b57) 2017 Tontodimamma (10.1016/j.knosys.2022.109965_b26) 2021; 126 Rajamanickam (10.1016/j.knosys.2022.109965_b34) 2020 Wiegand (10.1016/j.knosys.2022.109965_b30) 2021 Cardwell (10.1016/j.knosys.2022.109965_b44) 1996 Caruana (10.1016/j.knosys.2022.109965_b50) 1997; 28 Plaza-del-Arco (10.1016/j.knosys.2022.109965_b15) 2021 Zampieri (10.1016/j.knosys.2022.109965_b12) 2019 Zhang (10.1016/j.knosys.2022.109965_b51) 2021 Plaza-del-Arco (10.1016/j.knosys.2022.109965_b14) 2021; 67 Awal (10.1016/j.knosys.2022.109965_b36) 2021 Malmasi (10.1016/j.knosys.2022.109965_b20) 2018; 30 Ekman (10.1016/j.knosys.2022.109965_b38) 1992; 6 Alorainy (10.1016/j.knosys.2022.109965_b40) 2018 Taulé (10.1016/j.knosys.2022.109965_b5) 2021; 67 Plaza-del-Arco (10.1016/j.knosys.2022.109965_b2) 2021; 166 Struß (10.1016/j.knosys.2022.109965_b11) 2019 Sarkar (10.1016/j.knosys.2022.109965_b23) 2021 Pan (10.1016/j.knosys.2022.109965_b48) 2010; 22 MacAvaney (10.1016/j.knosys.2022.109965_b25) 2019; 14 Zampieri (10.1016/j.knosys.2022.109965_b13) 2020 Frenda (10.1016/j.knosys.2022.109965_b33) 2022; 193 Davidson (10.1016/j.knosys.2022.109965_b19) 2017 Kraskov (10.1016/j.knosys.2022.109965_b59) 2004; 69 Ruder (10.1016/j.knosys.2022.109965_b49) 2019 van Aken (10.1016/j.knosys.2022.109965_b31) 2018 Plaza-del-Arco (10.1016/j.knosys.2022.109965_b35) 2021; 9 |
| References_xml | – start-page: 1 year: 2020 end-page: 47 ident: b9 article-title: Resources and benchmark corpora for hate speech detection: a systematic review publication-title: Lang. Res. Eval. – reference: M. Wiegand, J. Ruppenhofer, T. Kleinbauer, Detection of abusive language: the problem of biased datasets, in: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), 2019, pp. 602–608. – volume: 193 year: 2022 ident: b33 article-title: The unbearable hurtfulness of sarcasm publication-title: Expert Syst. Appl. – volume: 51 year: 2018 ident: b24 article-title: A survey on automatic detection of hate speech in text publication-title: ACM Comput. Surv. – start-page: 102 year: 2020 end-page: 108 ident: b29 article-title: Leveraging affective bidirectional transformers for offensive language detection publication-title: Proceedings of the 4th Workshop on Open-Source Arabic Corpora and Processing Tools, with a Shared Task on Offensive Language Detection – start-page: 747 year: 2017 end-page: 754 ident: b56 article-title: DataStories at SemEval-2017 task 4: Deep LSTM with attention for message-level and topic-based sentiment analysis publication-title: Proceedings of the 11th International Workshop on Semantic Evaluation – start-page: 6193 year: 2020 end-page: 6202 ident: b46 article-title: I feel offended, don’t be abusive! implicit/explicit messages in offensive and abusive language publication-title: Proceedings of the 12th Language Resources and Evaluation Conference – volume: 67 year: 2021 ident: b5 article-title: Overview of the DETOXIS task at IberLEF-2021: Detection of toxicity in comments in Spanish publication-title: Procesamiento Del Lenguaje Nat. – start-page: 1425 year: 2020 end-page: 1447 ident: b13 article-title: SemEval-2020 task 12: Multilingual offensive language identification in social media (OffensEval 2020) publication-title: Proceedings of the Fourteenth Workshop on Semantic Evaluation – start-page: 79 year: 2020 end-page: 88 ident: b28 article-title: Attending the emotions to detect online abusive language publication-title: Proceedings of the Fourth Workshop on Online Abuse and Harms – start-page: 1792 year: 2021 end-page: 1798 ident: b23 article-title: FBERT: A neural transformer for identifying offensive content publication-title: Findings of the Association for Computational Linguistics: EMNLP 2021 – reference: A.M. Founta, C. Djouvas, D. Chatzakou, I. Leontiadis, J. Blackburn, G. Stringhini, A. Vakali, M. Sirivianos, N. Kourtellis, Large scale crowdsourcing and characterization of twitter abusive behavior, in: Twelfth International AAAI Conference on Web and Social Media, 2018. – start-page: 576 year: 2021 end-page: 587 ident: b30 article-title: Implicitly abusive language – what does it actually look like and why are we not getting there? publication-title: Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies – start-page: 169 year: 2019 end-page: 174 ident: b41 article-title: Automatic detection of hate speech on facebook using sentiment and emotion analysis publication-title: 2019 International Conference on Artificial Intelligence in Information and Communication – year: 2018 ident: b21 article-title: BERT: Pre-training of deep bidirectional transformers for language understanding – start-page: 1492 year: 2020 end-page: 1498 ident: b53 article-title: EmoEvent: A multilingual emotion corpus based on different events publication-title: Proceedings of the 12th Language Resources and Evaluation Conference – year: 2021 ident: b1 article-title: Characterization and mechanical properties of offensive language taxonomy and detection techniques publication-title: Mater. Today: Proc. – reference: R. Kumar, A.K. Ojha, S. Malmasi, M. Zampieri, Evaluating aggression identification in social media, in: Proceedings of the Second Workshop on Trolling, Aggression and Cyberbullying, 2020, pp. 1–5. – start-page: 8026 year: 2019 end-page: 8037 ident: b58 article-title: Pytorch: An imperative style, high-performance deep learning library publication-title: Advances in Neural Information Processing Systems – start-page: 297 year: 2021 end-page: 318 ident: b37 article-title: Multi-task learning with sentiment, emotion, and target detection to recognize hate speech and offensive language publication-title: FIRE 2021 Working Notes – reference: M. Wiegand, M. Siegel, J. Ruppenhofer, Overview of the GermEval 2018 Shared Task on the Identification of Offensive Language, in: Proceedings of GermEval 2018, 14th Conference on Natural Language Processing, KONVENS 2018, Vienna, Austria, 2018. – volume: 11 start-page: 3610 year: 2021 ident: b45 article-title: How do you speak about immigrants? Taxonomy and StereoImmigrants dataset for identifying stereotypes about immigrants publication-title: Appl. Sci. – reference: D. Chatzakou, N. Kourtellis, J. Blackburn, E. De Cristofaro, G. Stringhini, A. Vakali, Detecting aggressors and bullies on Twitter, in: Proceedings of the 26th International Conference on World Wide Web Companion, 2017, pp. 767–768. – start-page: 19 year: 2012 end-page: 26 ident: b17 article-title: Detecting hate speech on the world wide web publication-title: Proceedings of the Second Workshop on Language in Social Media – year: 2021 ident: b36 article-title: Angrybert: Joint learning target and emotion for hate speech detection – year: 2020 ident: b43 article-title: Classifying constructive comments – volume: 67 year: 2021 ident: b16 article-title: Overview of EXIST 2021: sEXism identification in social networks publication-title: Procesamiento Del Lenguaje Nat. – year: 2020 ident: b52 article-title: Spanish pre-trained BERT model and evaluation data publication-title: PML4DC At ICLR 2020 – volume: 9 start-page: 112478 year: 2021 end-page: 112489 ident: b35 article-title: A multi-task learning approach to hate speech detection leveraging sentiment analysis publication-title: IEEE Access – start-page: 1096 year: 2021 end-page: 1108 ident: b15 article-title: OffendES: A new corpus in spanish for offensive language research publication-title: Proceedings of the International Conference on Recent Advances in Natural Language Processing – start-page: 5838 year: 2020 end-page: 5844 ident: b22 article-title: Multilingual offensive language identification with cross-lingual embeddings publication-title: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing – volume: 28 start-page: 41 year: 1997 end-page: 75 ident: b50 article-title: Multitask learning publication-title: Mach. Learn. – year: 1996 ident: b44 article-title: Dictionary of Psychology – volume: 126 start-page: 157 year: 2021 end-page: 179 ident: b26 article-title: Thirty years of research into hate speech: topics of interest and their evolution publication-title: Scientometrics – start-page: 5998 year: 2017 end-page: 6008 ident: b57 article-title: Attention is all you need publication-title: Advances in Neural Information Processing Systems – year: 2019 ident: b49 article-title: Neural transfer learning for natural language processing – reference: C. Zimmerman, M.-K. Stein, D. Hardt, R. Vatrapu, Emergence of things felt: Harnessing the semantic space of Facebook feeling tags, in: Thirty Sixth International Conference on Information Systems, Fort Worth, 2015. – start-page: 33 year: 2018 end-page: 42 ident: b31 article-title: Challenges for toxic comment classification: An in-depth error analysis publication-title: Proceedings of the 2nd Workshop on Abusive Language Online – volume: 6 start-page: 169 year: 1992 end-page: 200 ident: b38 article-title: An argument for basic emotions publication-title: Cogn. Emot. – volume: 166 year: 2021 ident: b2 article-title: Comparing pre-trained language models for spanish hate speech detection publication-title: Expert Syst. Appl. – reference: S. Lamprinidis, F. Bianchi, D. Hardt, D. Hovy, Universal joy a data set and results for classifying emotions across languages, in: Proceedings of the Eleventh Workshop on Computational Approaches To Subjectivity, Sentiment and Social Media Analysis, 2021, pp. 62–75. – start-page: 1 year: 2021 ident: b51 article-title: A survey on multi-task learning publication-title: IEEE Trans. Knowl. Data Eng. – start-page: 581 year: 2018 end-page: 586 ident: b40 article-title: Suspended accounts: A source of tweets with disgust and anger emotions for augmenting hate speech data sample publication-title: 2018 International Conference on Machine Learning and Cybernetics, Vol. 2 – volume: 67 year: 2021 ident: b14 article-title: Overview of the MeOffendEs task on offensive text detection at IberLEF 2021 publication-title: Procesamiento Del Lenguaje Nat. – start-page: 354 year: 2019 end-page: 365 ident: b11 article-title: Overview of GermEval task 2, 2019 shared task on the identification of offensive language publication-title: Proceedings of the 15th Conference on Natural Language Processing – volume: 8 start-page: 113 year: 1901 end-page: 127 ident: b39 article-title: The psychology of profanity publication-title: Psychol. Rev. – volume: 2 start-page: 1 year: 2008 end-page: 135 ident: b47 article-title: Foundations and trends in information retrieval publication-title: Found. Trends Inf. Retrieval – reference: C. Nobata, J. Tetreault, A. Thomas, Y. Mehdad, Y. Chang, Abusive Language Detection in Online User Content, in: Proceedings of the 25th International Conference on World Wide Web, 2016, pp. 145–153. – start-page: 512 year: 2017 end-page: 515 ident: b19 article-title: Automated hate speech detection and the problem of offensive language publication-title: Proceedings of the Eleventh International Conference on Web and Social Media – start-page: 145 year: 2016 end-page: 153 ident: b18 article-title: Abusive language detection in online user content publication-title: Proceedings of the 25th International Conference on World Wide Web – volume: 69 year: 2004 ident: b59 article-title: Estimating mutual information publication-title: Phys. Rev. E – start-page: 75 year: 2019 end-page: 86 ident: b12 article-title: SemEval-2019 task 6: Identifying and categorizing offensive language in social media (OffensEval) publication-title: Proceedings of the 13th International Workshop on Semantic Evaluation – start-page: 11 year: 2017 end-page: 17 ident: b42 article-title: Constructive language in news comments publication-title: Proceedings of the First Workshop on Abusive Language Online – start-page: 4270 year: 2020 end-page: 4279 ident: b34 article-title: Joint modelling of emotion and abusive language detection publication-title: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics – volume: 14 start-page: 1 year: 2019 end-page: 16 ident: b25 article-title: Hate speech detection: Challenges and solutions publication-title: PLOS ONE – volume: 22 start-page: 1345 year: 2010 end-page: 1359 ident: b48 article-title: A survey on transfer learning publication-title: IEEE Trans. Knowl. Data Eng. – start-page: 61 year: 2018 end-page: 66 ident: b27 article-title: Hate speech classification in social media using emotional analysis publication-title: 2018 7th Brazilian Conference on Intelligent Systems – volume: 30 start-page: 187 year: 2018 end-page: 202 ident: b20 article-title: Challenges in discriminating profanity from hate speech publication-title: J. Exp. Theor. Artif. Intell. – volume: 20 year: 2020 ident: b32 article-title: Detecting misogyny and xenophobia in spanish tweets using language technologies publication-title: ACM Trans. Internet Technol. – year: 2021 ident: 10.1016/j.knosys.2022.109965_b36 – start-page: 5838 year: 2020 ident: 10.1016/j.knosys.2022.109965_b22 article-title: Multilingual offensive language identification with cross-lingual embeddings – volume: 69 year: 2004 ident: 10.1016/j.knosys.2022.109965_b59 article-title: Estimating mutual information publication-title: Phys. Rev. E doi: 10.1103/PhysRevE.69.066138 – volume: 2 start-page: 1 issue: 1–2 year: 2008 ident: 10.1016/j.knosys.2022.109965_b47 article-title: Foundations and trends in information retrieval publication-title: Found. Trends Inf. Retrieval doi: 10.1561/1500000011 – start-page: 1 year: 2021 ident: 10.1016/j.knosys.2022.109965_b51 article-title: A survey on multi-task learning publication-title: IEEE Trans. Knowl. Data Eng. – ident: 10.1016/j.knosys.2022.109965_b7 – ident: 10.1016/j.knosys.2022.109965_b55 – start-page: 8026 year: 2019 ident: 10.1016/j.knosys.2022.109965_b58 article-title: Pytorch: An imperative style, high-performance deep learning library – year: 2019 ident: 10.1016/j.knosys.2022.109965_b49 – start-page: 1 year: 2020 ident: 10.1016/j.knosys.2022.109965_b9 article-title: Resources and benchmark corpora for hate speech detection: a systematic review publication-title: Lang. Res. Eval. – start-page: 145 year: 2016 ident: 10.1016/j.knosys.2022.109965_b18 article-title: Abusive language detection in online user content – start-page: 576 year: 2021 ident: 10.1016/j.knosys.2022.109965_b30 article-title: Implicitly abusive language – what does it actually look like and why are we not getting there? – start-page: 4270 year: 2020 ident: 10.1016/j.knosys.2022.109965_b34 article-title: Joint modelling of emotion and abusive language detection – volume: 67 year: 2021 ident: 10.1016/j.knosys.2022.109965_b16 article-title: Overview of EXIST 2021: sEXism identification in social networks publication-title: Procesamiento Del Lenguaje Nat. – volume: 67 year: 2021 ident: 10.1016/j.knosys.2022.109965_b5 article-title: Overview of the DETOXIS task at IberLEF-2021: Detection of toxicity in comments in Spanish publication-title: Procesamiento Del Lenguaje Nat. – volume: 51 issue: 4 year: 2018 ident: 10.1016/j.knosys.2022.109965_b24 article-title: A survey on automatic detection of hate speech in text publication-title: ACM Comput. Surv. doi: 10.1145/3232676 – volume: 67 year: 2021 ident: 10.1016/j.knosys.2022.109965_b14 article-title: Overview of the MeOffendEs task on offensive text detection at IberLEF 2021 publication-title: Procesamiento Del Lenguaje Nat. – start-page: 33 year: 2018 ident: 10.1016/j.knosys.2022.109965_b31 article-title: Challenges for toxic comment classification: An in-depth error analysis – volume: 126 start-page: 157 issue: 1 year: 2021 ident: 10.1016/j.knosys.2022.109965_b26 article-title: Thirty years of research into hate speech: topics of interest and their evolution publication-title: Scientometrics doi: 10.1007/s11192-020-03737-6 – volume: 6 start-page: 169 issue: 3–4 year: 1992 ident: 10.1016/j.knosys.2022.109965_b38 article-title: An argument for basic emotions publication-title: Cogn. Emot. doi: 10.1080/02699939208411068 – volume: 11 start-page: 3610 issue: 8 year: 2021 ident: 10.1016/j.knosys.2022.109965_b45 article-title: How do you speak about immigrants? Taxonomy and StereoImmigrants dataset for identifying stereotypes about immigrants publication-title: Appl. Sci. doi: 10.3390/app11083610 – start-page: 61 year: 2018 ident: 10.1016/j.knosys.2022.109965_b27 article-title: Hate speech classification in social media using emotional analysis – start-page: 297 year: 2021 ident: 10.1016/j.knosys.2022.109965_b37 article-title: Multi-task learning with sentiment, emotion, and target detection to recognize hate speech and offensive language – volume: 193 year: 2022 ident: 10.1016/j.knosys.2022.109965_b33 article-title: The unbearable hurtfulness of sarcasm publication-title: Expert Syst. Appl. doi: 10.1016/j.eswa.2021.116398 – ident: 10.1016/j.knosys.2022.109965_b10 – year: 2020 ident: 10.1016/j.knosys.2022.109965_b43 – start-page: 79 year: 2020 ident: 10.1016/j.knosys.2022.109965_b28 article-title: Attending the emotions to detect online abusive language – volume: 8 start-page: 113 issue: 2 year: 1901 ident: 10.1016/j.knosys.2022.109965_b39 article-title: The psychology of profanity publication-title: Psychol. Rev. doi: 10.1037/h0074772 – volume: 22 start-page: 1345 issue: 10 year: 2010 ident: 10.1016/j.knosys.2022.109965_b48 article-title: A survey on transfer learning publication-title: IEEE Trans. Knowl. Data Eng. doi: 10.1109/TKDE.2009.191 – year: 2020 ident: 10.1016/j.knosys.2022.109965_b52 article-title: Spanish pre-trained BERT model and evaluation data – start-page: 6193 year: 2020 ident: 10.1016/j.knosys.2022.109965_b46 article-title: I feel offended, don’t be abusive! implicit/explicit messages in offensive and abusive language – volume: 28 start-page: 41 issue: 1 year: 1997 ident: 10.1016/j.knosys.2022.109965_b50 article-title: Multitask learning publication-title: Mach. Learn. doi: 10.1023/A:1007379606734 – year: 2018 ident: 10.1016/j.knosys.2022.109965_b21 – start-page: 19 year: 2012 ident: 10.1016/j.knosys.2022.109965_b17 article-title: Detecting hate speech on the world wide web – ident: 10.1016/j.knosys.2022.109965_b8 doi: 10.1609/icwsm.v12i1.14991 – start-page: 75 year: 2019 ident: 10.1016/j.knosys.2022.109965_b12 article-title: SemEval-2019 task 6: Identifying and categorizing offensive language in social media (OffensEval) – start-page: 169 year: 2019 ident: 10.1016/j.knosys.2022.109965_b41 article-title: Automatic detection of hate speech on facebook using sentiment and emotion analysis – start-page: 5998 year: 2017 ident: 10.1016/j.knosys.2022.109965_b57 article-title: Attention is all you need – start-page: 1425 year: 2020 ident: 10.1016/j.knosys.2022.109965_b13 article-title: SemEval-2020 task 12: Multilingual offensive language identification in social media (OffensEval 2020) – year: 2021 ident: 10.1016/j.knosys.2022.109965_b1 article-title: Characterization and mechanical properties of offensive language taxonomy and detection techniques publication-title: Mater. Today: Proc. – start-page: 581 year: 2018 ident: 10.1016/j.knosys.2022.109965_b40 article-title: Suspended accounts: A source of tweets with disgust and anger emotions for augmenting hate speech data sample – start-page: 512 year: 2017 ident: 10.1016/j.knosys.2022.109965_b19 article-title: Automated hate speech detection and the problem of offensive language – volume: 30 start-page: 187 issue: 2 year: 2018 ident: 10.1016/j.knosys.2022.109965_b20 article-title: Challenges in discriminating profanity from hate speech publication-title: J. Exp. Theor. Artif. Intell. doi: 10.1080/0952813X.2017.1409284 – start-page: 102 year: 2020 ident: 10.1016/j.knosys.2022.109965_b29 article-title: Leveraging affective bidirectional transformers for offensive language detection – volume: 14 start-page: 1 issue: 8 year: 2019 ident: 10.1016/j.knosys.2022.109965_b25 article-title: Hate speech detection: Challenges and solutions publication-title: PLOS ONE doi: 10.1371/journal.pone.0221152 – ident: 10.1016/j.knosys.2022.109965_b3 doi: 10.1145/2872427.2883062 – ident: 10.1016/j.knosys.2022.109965_b6 doi: 10.1145/3041021.3054211 – start-page: 747 year: 2017 ident: 10.1016/j.knosys.2022.109965_b56 article-title: DataStories at SemEval-2017 task 4: Deep LSTM with attention for message-level and topic-based sentiment analysis – ident: 10.1016/j.knosys.2022.109965_b4 – volume: 20 issue: 2 year: 2020 ident: 10.1016/j.knosys.2022.109965_b32 article-title: Detecting misogyny and xenophobia in spanish tweets using language technologies publication-title: ACM Trans. Internet Technol. doi: 10.1145/3369869 – start-page: 11 year: 2017 ident: 10.1016/j.knosys.2022.109965_b42 article-title: Constructive language in news comments – year: 1996 ident: 10.1016/j.knosys.2022.109965_b44 – start-page: 354 year: 2019 ident: 10.1016/j.knosys.2022.109965_b11 article-title: Overview of GermEval task 2, 2019 shared task on the identification of offensive language – start-page: 1096 year: 2021 ident: 10.1016/j.knosys.2022.109965_b15 article-title: OffendES: A new corpus in spanish for offensive language research – start-page: 1492 year: 2020 ident: 10.1016/j.knosys.2022.109965_b53 article-title: EmoEvent: A multilingual emotion corpus based on different events – ident: 10.1016/j.knosys.2022.109965_b54 – start-page: 1792 year: 2021 ident: 10.1016/j.knosys.2022.109965_b23 article-title: FBERT: A neural transformer for identifying offensive content – volume: 9 start-page: 112478 year: 2021 ident: 10.1016/j.knosys.2022.109965_b35 article-title: A multi-task learning approach to hate speech detection leveraging sentiment analysis publication-title: IEEE Access doi: 10.1109/ACCESS.2021.3103697 – volume: 166 year: 2021 ident: 10.1016/j.knosys.2022.109965_b2 article-title: Comparing pre-trained language models for spanish hate speech detection publication-title: Expert Syst. Appl. doi: 10.1016/j.eswa.2020.114120 |
| SSID | ssj0002218 |
| Score | 2.4301798 |
| Snippet | The analysis and detection of offensive content in textual information have become a great challenge for the Natural Language Processing community. Most of the... |
| SourceID | crossref elsevier |
| SourceType | Enrichment Source Index Database Publisher |
| StartPage | 109965 |
| SubjectTerms | Linguistic phenomena Multi-task learning Natural language processing Offensive language Spanish |
| Title | Integrating implicit and explicit linguistic phenomena via multi-task learning for offensive language detection |
| URI | https://dx.doi.org/10.1016/j.knosys.2022.109965 |
| Volume | 258 |
| WOSCitedRecordID | wos000880093300002&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: 1872-7409 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0002218 issn: 0950-7051 databaseCode: AIEXJ dateStart: 19950201 isFulltext: true titleUrlDefault: https://www.sciencedirect.com providerName: Elsevier |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1LbxMxELZCy4EL5amWAvKBW-Ron1n7GKCFQltVIqDcVt61LaVddqN0G0X9m_whxq_diCBeEpfVxvIjmvlijyffzCD0SsYsGYtYEDnOFEkKWRAWRZzovDBZEdCCysIUm8jOz-lsxi4Gg28-FmZVZXVN12u2-K-qhjZQtg6d_Qt1d5NCA7yD0uEJaofnHyn-xCWAMMEqhi8-tyxyuXYfdAT6jUnQPNQML52DgQ9Xc27ZhaTl11e-moRlWTZKOZ67d28OhWwNiavetG4_egcd0YejcGmiO6v9ouK3nAhZkcmyNC7aY13f42wOUvnaad5UESLvmvrW_IkfVtbHfTYCYx-695zHz0upe7wOOTk1L_HCdj0dDSeVAvk2vb992ZrZ3tbkC690DBp3kUq2mZOphKn5phMkMvVYov7KvB2d41ycAckCl9BW2g2eZnCjSAK2eQJENnv81mliHRuXo6u6AYGN9MI6_Raz1S1-yNP9SS-nV4s0wSCl7A7ajbKUwVa7Ozk5mn3oDIQoMm7n7uv5iE5DO9xe6-cW04YVNH2A7rvrC55Y2D1EA1k_Qnu-NAh2J8Vj1GygEHsUYkAh9ijEPQpxh0IMesE9CrFHIQYU4g6F2KMQdyh8gqbHR9M374mr7UFKuKS2gDXF4cYkEqXKktFY0DIVKixYGUrBM0oVE5EYMyETFgtZ0jCOw1ClKeUhbH7xU7RTN7XcRziTfBzwgqZlqRKhRGGoALDzRGmRxkFygGIvvrx0ee91-ZUq9wTHy9wKPddCz63QDxDpRi1s3pff9M-8ZnJnu1qbNAcw_XLks38eeYju9b-F52inXd7IF-huuWrn18uXDnXfAe4kxbk |
| 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=Integrating+implicit+and+explicit+linguistic+phenomena+via+multi-task+learning+for+offensive+language+detection&rft.jtitle=Knowledge-based+systems&rft.au=Plaza-del-Arco%2C+Flor+Miriam&rft.au=Molina-Gonz%C3%A1lez%2C+M.+Dolores&rft.au=Ure%C3%B1a-L%C3%B3pez%2C+L.+Alfonso&rft.au=Mart%C3%ADn-Valdivia%2C+Mar%C3%ADa-Teresa&rft.date=2022-12-22&rft.pub=Elsevier+B.V&rft.issn=0950-7051&rft.eissn=1872-7409&rft.volume=258&rft_id=info:doi/10.1016%2Fj.knosys.2022.109965&rft.externalDocID=S0950705122010589 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0950-7051&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0950-7051&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0950-7051&client=summon |