skip to main content
10.1145/3459637.3482481acmconferencesArticle/Chapter ViewAbstractPublication PagescikmConference Proceedingsconference-collections
research-article

Sparse Shield: Social Network Immunization vs. Harmful Speech

Published: 30 October 2021 Publication History

Abstract

With the rise of social media users and the general shift of communication from traditional media to online platforms, the spread of harmful content (e.g., hate speech, misinformation, fake news) has been exacerbated. Harmful content in the form of hate speech causes a person distress or harm, having a negative impact on the individual mental health, with even more detrimental effects on the psychology of children and teenagers. In this paper, we propose an end-to-end solution with real-time capabilities to detect harmful content in real-time and mitigate its spread over the network. Our main contribution is Sparse Shield, a novel method that out-scales existing state-of-the-art methods for network immunization. We also propose a novel architecture for harmful speech mitigation that maximizes the impact of immunization. Our solution aims to identify a set of users for which to move harmful content at the bottom of the user feed, rather than censoring users. By immunizing certain network nodes in this manner, we minimize the negative impact on the network and minimize the interference with and limitation of individual freedoms: the information is not hidden but rather not as easy to reach without an explicit search. Our analysis is based on graphs built on real-world data collected from Twitter; these graphs reflect real user behavior. We perform extensive scalability experiments to prove the superiority of our method over existing state-of-the-art network immunization techniques. We also perform extensive experiments to showcase that Sparse Shield outperforms existing techniques on the task of harmful speech mitigation on a real-world dataset.

References

[1]
Muhammad Ahmad, Sarwan Ali, Juvaria Tariq, Imdadullah Khan, Mudassir Shabbir, and Arif Zaman. 2020. Combinatorial trace method for network immunization. Information Sciences 519 (2020), 215--228. https://doi.org/10.1016/j.ins.2020.01.037
[2]
Muhammad Ahmad, Juvaria Tariq, Mudassir Shabbir, and Imdadullah Khan. 2017. Spectral Methods for Immunization of Large Networks. Australasian Journal of Information Systems 21 (2017), 1--18. https://doi.org/10.3127/ajis.v21i0.1563
[3]
Pedro Alonso, Rajkumar Saini, and György Kovacs. 2020. TheNorth at SemEval- 2020 Task 12: Hate Speech Detection Using RoBERTa. In The 14th Workshop on Semantic Evaluation. ICCL, 2197--2202.
[4]
Uttara M. Ananthakrishnan and Catherine E. Tucker. 2021. The Drivers and Virality of Hate Speech Online. SSRN Electronic Journal (2021), 1--32. https://doi.org/10.2139/ssrn.3793801
[5]
Pinkesh Badjatiya, Shashank Gupta, Manish Gupta, and Vasudeva Varma. 2017. Deep Learning for Hate Speech Detection in Tweets. In The 26th International Conference on World Wide Web Companion. ACM, 759--760. https://doi.org/10.1145/3041021.3054223
[6]
Jack Bandy and Nicholas Diakopoulos. 2021. More Accounts, Fewer Links. In The ACM Conference on Human-Computer Interaction, Vol. 5. ACM, 1--28. https://doi.org/10.1145/3449152
[7]
Michele Banko, Brendon MacKeen, and Laurie Ray. 2020. A Unified Taxonomy of Harmful Content. In The 14th Workshop on Online Abuse and Harms. ACL, 125--137. https://doi.org/10.18653/v1/2020.alw-1.16
[8]
Michaŀ Bilewicz and Wiktor Soral. 2020. Hate Speech Epidemic. The Dynamic Ef- fects of Derogatory Language on Intergroup Relations and Political Radicalization. Political Psychology 41, S1 (2020), 3--33. https://doi.org/10.1111/pops.12670
[9]
Piotr Bojanowski, Edouard Grave, Armand Joulin, and Tomas Mikolov. 2017. Enriching Word Vectors with Subword Information. Transactions of the Association for Computational Linguistics 5 (2017), 135--146. https://doi.org/10.1162/tacl_a_ 00051
[10]
David M. Chan, Roshan Rao, Forrest Huang, and John F. Canny. 2018. T-SNE-CUDA: GPU-Accelerated T-SNE and its Applications to Modern Data. In The 30th International Symposium on Computer Architecture and High Performance Computing. IEEE, 330--338. https://doi.org/10.1109/CAHPC.2018.8645912
[11]
Chen Chen, Hanghang Tong, B. Aditya Prakash, Charalampos E. Tsourakakis, Tina Eliassi-Rad, Christos Faloutsos, and Duen Horng Chau. 2015. Node Immunization on Large Graphs: Theory and Algorithms. IEEE Transactions on Knowledge and Data Engineering 28, 1 (2015), 113--126. https://doi.org/10.1109/TKDE.2015.2465378
[12]
Reuven Cohen, Shlomo Havlin, and Daniel ben Avraham. 2003. Efficient Immunization Strategies for Computer Networks and Populations. Physical Review Letters 91, 24 (2003), 247901. https://doi.org/10.1103/PhysRevLett.91.247901
[13]
Alexis Conneau, Kartikay Khandelwal, Naman Goyal, Vishrav Chaudhary, Guillaume Wenzek, Francisco Guzmán, Edouard Grave, Myle Ott, Luke Zettlemoyer, and Veselin Stoyanov. 2020. Unsupervised Cross-lingual Representation Learning at Scale. In The 58th Annual Meeting of the Association for Computational Linguistics. ACL, 8440--8451. https://doi.org/10.18653/v1/2020.acl-main.747
[14]
Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2018. Bert: Pre-training of deep bidirectional transformers for language understanding. In The 2019 Conference of the North American Chapter of the Association for Computational Linguistics. ACL, 4171--4186. https://doi.org/10.18653/v1/N19-1423
[15]
Paula Fortuna, Juan Soler, and Leo Wanner. 2020. Toxic, Hateful, Offensive or Abusive? What Are We Really Classifying? An Empirical Analysis of Hate Speech Datasets. In The 12th Language Resources and Evaluation Conference. ERLA, 6786--6794.
[16]
Zakariya Ghalmane, Mohammed El Hassouni, and Hocine Cherifi. 2019. Immunization of networks with non-overlapping community structure. Social Network Analysis and Mining 9, 1 (2019), 45:1--45:22. https://doi.org/10.1007/s13278-019-0591-9
[17]
Sergei Ivanov, Konstantinos Theocharidis, Manolis Terrovitis, and Panagiotis Karras. 2017. Content Recommendation for Viral Social Influence. In The 40th International ACM SIGIR Conference on Research and Development in Information Retrieval. ACM, 565--574. https://doi.org/10.1145/3077136.3080788
[18]
David Kempe, Jon Kleinberg, and Eva Tardos. 2015. Maximizing the Spread of Influence through a Social Network. Theory of Computing 11, 1 (2015), 105--147. https://doi.org/10.4086/toc.2015.v011a004
[19]
Diederik P. Kingma and Max Welling. 2014. Auto-Encoding Variational Bayes. In International Conference on Learning Representations. 1--14.
[20]
Jens Lemmens, Ilia Markov, and Walter Daelemans. 2021. Improving Hate Speech Type and Target Detection with Hateful Metaphor Features. In The 4th Workshop on NLP for Internet Freedom: Censorship, Disinformation, and Propaganda. ACL, 7--16. https://doi.org/10.18653/v1/2021.nlp4if-1.2
[21]
Xianghua Li, Jingyi Guo, Chao Gao, Leyan Zhang, and Zili Zhang. 2018. A hybrid strategy for network immunization. Chaos, Solitons & Fractals 106 (2018), 214--219. https://doi.org/10.1016/j.chaos.2017.11.029
[22]
Yinhan Liu, Myle Ott, Naman Goyal, Jingfei Du, Mandar Joshi, Danqi Chen, Omer Levy, Mike Lewis, Luke Zettlemoyer, and Veselin Stoyanov. 2019. Roberta: A robustly optimized bert pretraining approach. arXiv:1907.11692
[23]
Alvis Logins and Panagiotis Karras. 2019. An Experimental Study on Network Immunization. In The 22nd International Conference on Extending Database Technology. OpenProceedings, 726--729. https://doi.org/10.5441/002/edbt.2019.97
[24]
Ilia Markov and Walter Daelemans. 2021. Improving Cross-Domain Hate Speech Detection by Reducing the False Positive Rate. In The 4th Workshop on NLP for Internet Freedom: Censorship, Disinformation, and Propaganda. ACL, 17--22. https://doi.org/10.18653/v1/2021.nlp4if-1.3
[25]
Ilia Markov, Nikola Ljube?ić, Darja Fier, and Walter Daelemans. 2021. Exploring Stylometric and Emotion-Based Features for Multilingual Cross-Domain Hate Speech Detection. In The 11th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis. ACL, 149--159.
[26]
Edoardo Mosca, Maximilian Wich, and Georg Groh. 2021. Understanding and Interpreting the Impact of User Context in Hate Speech Detection. In The 9th International Workshop on Natural Language Processing for Social Media. ACL, 91--102. https://doi.org/10.18653/v1/2021.socialnlp-1.8
[27]
Mariam Orabi, Djedjiga Mouheb, Zaher Al Aghbari, and Ibrahim Kamel. 2020. Detection of Bots in Social Media: A Systematic Review. Information Processing & Management 57, 4 (2020), 102250. https://doi.org/10.1016/j.ipm.2020.102250
[28]
Jose L. Part and Oliver Lemon. 2017. Incremental online learning of objects for robots operating in real environments. In 2017 Joint IEEE International Conference on Development and Learning and Epigenetic Robotics. IEEE, 304--310. https://doi.org/10.1109/DEVLRN.2017.8329822
[29]
Andra? Pelicon, Ravi Shekhar, Matej Martinc, Bla? ?krlj, Matthew Purver, and Senja Pollak. 2021. Zero-shot Cross-lingual Content Filtering: Offensive Language and Hate Speech Detection. In The EACL Hackashop on News Media Content Analysis and Automated Report Generation. ACL, 30--34.
[30]
Sancheng Peng, Guojun Wang, Yongmei Zhou, Cong Wan, Cong Wang, Shui Yu, and Jianwei Niu. 2019. An Immunization Framework for Social Networks Through Big Data Based Influence Modeling. IEEE Transactions on Dependable and Secure Computing 16, 6 (2019), 984--995. https://doi.org/10.1109/TDSC.2017.2731844
[31]
Jeffrey Pennington, Richard Socher, and Christopher Manning. 2014. GloVe: Global Vectors for Word Representation. In The 2014 Conference on Empirical Methods in Natural Language Processing. ACL, 1532--1543. https://doi.org/10.3115/v1/D14-1162
[32]
Alexandru Petrescu, Ciprian-Octavian Truica, and Elena-Simona Apostol. 2019. Sentiment analysis of events in social media. In The 15th International Conference on Intelligent Computer Communication and Processing. IEEE, 143--149. https://doi.org/10.1109/ICCP48234.2019.8959677
[33]
Jing Qian, Hong Wang, Mai ElSherief, and Xifeng Yan. 2021. Lifelong Learning of Hate Speech Classification on Social Media. In The 2021 Conference of the North American Chapter of the Association for Computational Linguistics. ACL, 2304--2314. https://doi.org/10.18653/v1/2021.naacl-main.183
[34]
Yizhi Ren, Mengjin Jiang, Ye Yao, Ting Wu, Zhen Wang, Mengkun Li, and Kim-Kwang Raymond Choo. 2018. Node Immunization in Networks with Uncertainty. In 2018 17th IEEE International Conference On Trust, Security And Privacy In Computing and Communications / 12th IEEE International Conference On Big Data Science And Engineering. IEEE, 1392--1397. https://doi.org/10.1109/TrustCom/BigDataSE.2018.00193
[35]
Devendra Singh Sachan, Manzil Zaheer, and Ruslan Salakhutdinov. 2019. Revisiting LSTM Networks for Semi-Supervised Text Classification via Mixed Objective Function. In The 2019aAAI Conference on Artificial Intelligence, Vol. 33. AAAI, 6940--6948. https://doi.org/10.1609/aaai.v33i01.33016940
[36]
Koustuv Saha, Eshwar Chandrasekharan, and Munmun De Choudhury. 2019. Prevalence and Psychological Effects of Hateful Speech in Online College Communities. In The 10th ACM Conference on Web Science. ACM, 255--264. https://doi.org/10.1145/3292522.3326032
[37]
Maarten Sap, Dallas Card, Saadia Gabriel, Yejin Choi, and Noah A. Smith. 2019. The Risk of Racial Bias in Hate Speech Detection. In The 57th Annual Meeting of the Association for Computational Linguistics. ACL, 1668--1678. https://doi.org/10.18653/v1/P19--1163
[38]
Sanjana Sharma, Saksham Agrawal, and Manish Shrivastava. 2018. Degree based Classification of Harmful Speech using Twitter Data. In The 1st Workshop on Trolling, Aggression and Cyberbullying. ACL, 106--112.
[39]
Laurens Van der Maaten and Geoffrey Hinton. 2008. Visualizing data using t-SNE. Journal of Machine Learning Research 9, 11 (2008), 2579--2605.
[40]
Zeerak Waseem, Thomas Davidson, Dana Warmsley, and Ingmar Weber. 2017. Understanding Abuse: A Typology of Abusive Language Detection Subtasks. In The 1st Workshop on Abusive Language Online. ACL, 78--84. https://doi.org/10.18653/v1/W17-3012
[41]
Zeerak Waseem and Dirk Hovy. 2016. Hateful Symbols or Hateful People? Predictive Features for Hate Speech Detection on Twitter. In Proceedings of the NAACL Student Research Workshop. ACL, 88--93. https://doi.org/10.18653/v1/N16-2013
[42]
Tetsuya Yoshida and Yuu Yamada. 2017. A Community Structure-Based Approach for Network Immunization. Computational Intelligence 33, 1 (2017), 77--98. https://doi.org/10.1111/coin.12082
[43]
Marcos Zampieri, Shervin Malmasi, Preslav Nakov, Sara Rosenthal, Noura Farra, and Ritesh Kumar. 2019. SemEval-2019 Task 6: Identifying and Categorizing Of- fensive Language in Social Media (OffensEval). In The 13th International Workshop on Semantic Evaluation. ACL, 75--86. https://doi.org/10.18653/v1/S19--2010
[44]
Yao Zhang and B. Aditya Prakash. 2015. Data-Aware Vaccine Allocation Over Large Networks. ACM Transactions on Knowledge Discovery from Data 10, 2 (2015), 1--32. https://doi.org/10.1145/2803176

Cited By

View all
  • (2024)Comparative Analysis of Graph Neural Networks and Transformers for Robust Fake News Detection: A Verification and Reimplementation StudyElectronics10.3390/electronics1323478413:23(4784)Online publication date: 4-Dec-2024
  • (2024)Multimodal Social Media Fake News Detection Based on 1D-CCNet Attention MechanismElectronics10.3390/electronics1318370013:18(3700)Online publication date: 18-Sep-2024
  • (2024)Large-Scale Graphs Community Detection using Spark GraphFrames2024 23rd International Symposium on Parallel and Distributed Computing (ISPDC)10.1109/ISPDC62236.2024.10705389(1-5)Online publication date: 8-Jul-2024
  • Show More Cited By

Recommendations

Comments

Information & Contributors

Information

Published In

cover image ACM Conferences
CIKM '21: Proceedings of the 30th ACM International Conference on Information & Knowledge Management
October 2021
4966 pages
ISBN:9781450384469
DOI:10.1145/3459637
Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected].

Sponsors

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 30 October 2021

Permissions

Request permissions for this article.

Check for updates

Author Tags

  1. counteractive immunization
  2. harmful speech detection
  3. network immunization
  4. preventive immunization

Qualifiers

  • Research-article

Conference

CIKM '21
Sponsor:

Acceptance Rates

Overall Acceptance Rate 1,861 of 8,427 submissions, 22%

Upcoming Conference

CIKM '25

Contributors

Other Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

  • Downloads (Last 12 months)38
  • Downloads (Last 6 weeks)7
Reflects downloads up to 01 Jan 2025

Other Metrics

Citations

Cited By

View all
  • (2024)Comparative Analysis of Graph Neural Networks and Transformers for Robust Fake News Detection: A Verification and Reimplementation StudyElectronics10.3390/electronics1323478413:23(4784)Online publication date: 4-Dec-2024
  • (2024)Multimodal Social Media Fake News Detection Based on 1D-CCNet Attention MechanismElectronics10.3390/electronics1318370013:18(3700)Online publication date: 18-Sep-2024
  • (2024)Large-Scale Graphs Community Detection using Spark GraphFrames2024 23rd International Symposium on Parallel and Distributed Computing (ISPDC)10.1109/ISPDC62236.2024.10705389(1-5)Online publication date: 8-Jul-2024
  • (2024)Leveraging Transfer Learning for Hate Speech Detection in Portuguese Social Media PostsIEEE Access10.1109/ACCESS.2024.343084812(101374-101389)Online publication date: 2024
  • (2024)Modelling the Association Between Social Media Flow Experience and Fake News Sharing: Testing the Mediating Role of Social Media Flow Experience and the Moderating Role of Social Media ScepticismInternational Journal of Human–Computer Interaction10.1080/10447318.2024.2369426(1-14)Online publication date: Jul-2024
  • (2024)A majority-based learning system for detecting misinformationBehaviour & Information Technology10.1080/0144929X.2024.2326562(1-15)Online publication date: 6-Mar-2024
  • (2024)DANESKnowledge-Based Systems10.1016/j.knosys.2024.111715294:COnline publication date: 21-Jun-2024
  • (2023)Noticias falsas y su efecto en la salud mentalRevista Punto Cero10.35319/puntocero.20234619728:46(25-34)Online publication date: 2-Jul-2023
  • (2023)Sustainable Development of Information Dissemination: A Review of Current Fake News Detection Research and PracticeSystems10.3390/systems1109045811:9(458)Online publication date: 4-Sep-2023
  • (2023)The Role of Gossiping in Information Dissemination over a Network of AgentsEntropy10.3390/e2601000926:1(9)Online publication date: 21-Dec-2023
  • Show More Cited By

View Options

Login options

View options

PDF

View or Download as a PDF file.

PDF

eReader

View online with eReader.

eReader

Media

Figures

Other

Tables

Share

Share

Share this Publication link

Share on social media