ABSTRACT
Content moderation systems are crucial in Online Social Networks (OSNs). Indeed, their role is to keep platforms and their users safe from malicious activities. However, there is an emerging consensus that such systems are unfair to fragile users and minorities. Furthermore, content moderation systems are difficult to personalize and lack effective communication between users and platforms. In this context, we propose an enhancement of the current framework of content moderation, integrating Large Language Models (LLMs) in the enforcing pipeline.
- Norah Abokhodair and Sarah Vieweg. 2016. Privacy & Social Media in the Context of the Arab Gulf. In Proceedings of the 2016 ACM Conference on Designing Interactive Systems (Brisbane, QLD, Australia) (DIS ’16). Association for Computing Machinery, New York, NY, USA, 672–683. https://doi.org/10.1145/2901790.2901873Google ScholarDigital Library
- Shiza Ali, Afsaneh Razi, Seunghyun Kim, Ashwaq Alsoubai, Chen Ling, Munmun De Choudhury, Pamela J. Wisniewski, and Gianluca Stringhini. 2023. Getting Meta: A Multimodal Approach for Detecting Unsafe Conversations within Instagram Direct Messages of Youth. Proc. ACM Hum.-Comput. Interact. 7, CSCW1, Article 132 (apr 2023), 30 pages. https://doi.org/10.1145/3579608Google ScholarDigital Library
- Arnav Arora, Preslav Nakov, Momchil Hardalov, Sheikh Muhammad Sarwar, Vibha Nayak, Yoan Dinkov, Dimitrina Zlatkova, Kyle Dent, Ameya Bhatawdekar, Guillaume Bouchard, and Isabelle Augenstein. 2023. Detecting Harmful Content on Online Platforms: What Platforms Need vs. Where Research Efforts Go. ACM Comput. Surv. (jun 2023). https://doi.org/10.1145/3603399 Just Accepted.Google ScholarDigital Library
- Katie Canales. 2021. Facebook’s AI moderation reportedly can’t interpret many languages, leaving users in some countries more susceptible to harmful posts. https://www.businessinsider.com/facebook-content-moderation-ai-cant-speak-all-languages-2021-9. Retrieved 19 June 2023.Google Scholar
- Scott Counts and Karen E. Fisher. 2010. Mobile social networking as information ground: A case study. Library & Information Science Research 32, 2 (2010), 98–115. https://doi.org/10.1016/j.lisr.2009.10.003Google ScholarCross Ref
- Rishi Bommasani et al.2022. On the Opportunities and Risks of Foundation Models. arxiv:2108.07258 [cs.LG]Google Scholar
- Tom B. Brown et al.2020. Language Models Are Few-Shot Learners. In Proceedings of the 34th International Conference on Neural Information Processing Systems (Vancouver, BC, Canada) (NIPS’20). Curran Associates Inc., Red Hook, NY, USA, Article 159, 25 pages.Google Scholar
- Mattia Falduti and Sergio Tessaris. 2022. On the Use of Chatbots to Report Non-Consensual Intimate Images Abuses: The Legal Expert Perspective. In Proceedings of the 2022 ACM Conference on Information Technology for Social Good (Limassol, Cyprus) (GoodIT ’22). Association for Computing Machinery, New York, NY, USA, 96–102. https://doi.org/10.1145/3524458.3547247Google ScholarDigital Library
- Mirko Franco, Salah A. Falyoun, Karen E. Fisher, Ombretta Gaggi, Yacine Ghamri-Doudane, Ayat J. Nashwan, Claudio E. Palazzi, and Mohammed Shwamra. 2022. A Technology Exploration towards Trustable and Safe Use of Social Media for Vulnerable Women Based on Islam and Arab Culture. In Proceedings of the 2022 ACM Conference on Information Technology for Social Good (Limassol, Cyprus) (GoodIT ’22). Association for Computing Machinery, New York, NY, USA, 138–145. https://doi.org/10.1145/3524458.3547259Google ScholarDigital Library
- Mirko Franco, Ombretta Gaggi, Barbara Guidi, Andrea Michienzi, and Claudio E. Palazzi. 2023. A decentralised messaging system robust against the unauthorised forwarding of private content. Future Generation Computer Systems 145 (2023), 211–222. https://doi.org/10.1016/j.future.2023.03.025Google ScholarDigital Library
- Mirko Franco, Ombretta Gaggi, and Claudio E. Palazzi. 2022. Improving Sexting Safety through Media Forwarding Control. In 2022 IEEE 19th Annual Consumer Communications & Networking Conference (CCNC). 1–6. https://doi.org/10.1109/CCNC49033.2022.9700555Google ScholarDigital Library
- Mirko Franco, Ombretta Gaggi, and Claudio E. Palazzi. 2023. Can Messaging Applications Prevent Sexting Abuse? A Technology Analysis. IEEE Transactions on Mobile Computing (2023), 1–14. https://doi.org/10.1109/TMC.2023.3238189Google ScholarDigital Library
- Barbara Guidi. 2020. When Blockchain meets Online Social Networks. Pervasive and Mobile Computing 62 (2020), 101131. https://doi.org/10.1016/j.pmcj.2020.101131Google ScholarDigital Library
- Barbara Guidi, Andrea Michienzi, and Andrea De Salve. 2020. Community evaluation in Facebook groups. Multimedia Tools and Applications 79 (2020), 19. https://doi.org/10.1007/s11042-019-08494-0Google ScholarDigital Library
- Oliver L. Haimson, Daniel Delmonaco, Peipei Nie, and Andrea Wegner. 2021. Disproportionate Removals and Differing Content Moderation Experiences for Conservative, Transgender, and Black Social Media Users: Marginalization and Moderation Gray Areas. Proc. ACM Hum.-Comput. Interact. 5, CSCW2, Article 466 (oct 2021), 35 pages. https://doi.org/10.1145/3479610Google ScholarDigital Library
- Alon Halevy, Cristian Canton-Ferrer, Hao Ma, Umut Ozertem, Patrick Pantel, Marzieh Saeidi, Fabrizio Silvestri, and Ves Stoyanov. 2022. Preserving Integrity in Online Social Networks. Commun. ACM 65, 2 (jan 2022), 92–98. https://doi.org/10.1145/3462671Google ScholarDigital Library
- Yifang Li, Nishant Vishwamitra, Hongxin Hu, and Kelly Caine. 2020. Towards A Taxonomy of Content Sensitivity and Sharing Preferences for Photos. In Proceedings of the 2020 CHI Conference on Human Factors in Computing Systems (Honolulu, HI, USA) (CHI ’20). Association for Computing Machinery, New York, NY, USA, 1–14. https://doi.org/10.1145/3313831.3376498Google ScholarDigital Library
- Chi Liu, Tianqing Zhu, Jun Zhang, and Wanlei Zhou. 2022. Privacy Intelligence: A Survey on Image Privacy in Online Social Networks. ACM Comput. Surv. 55, 8, Article 161 (dec 2022), 35 pages. https://doi.org/10.1145/3547299Google ScholarDigital Library
- Judith S. Olson, Jonathan Grudin, and Eric Horvitz. 2005. A Study of Preferences for Sharing and Privacy. In CHI ’05 Extended Abstracts on Human Factors in Computing Systems (Portland, OR, USA) (CHI EA ’05). Association for Computing Machinery, New York, NY, USA, 1985–1988. https://doi.org/10.1145/1056808.1057073Google ScholarDigital Library
- OpenAI. 2023. GPT-4 Technical Report. arxiv:2303.08774 [cs.CL]Google Scholar
- Wei Qin, Zetong Chen, Lei Wang, Yunshi Lan, Weijieying Ren, and Richang Hong. 2023. Read, Diagnose and Chat: Towards Explainable and Interactive LLMs-Augmented Depression Detection in Social Media. arxiv:2305.05138 [cs.CL]Google Scholar
- Elisa Rubegni, Monica Landoni, Antonella De Angeli, and Letizia Jaccheri. 2019. Detecting Gender Stereotypes in Children Digital StoryTelling. In Proceedings of the 18th ACM International Conference on Interaction Design and Children (Boise, ID, USA) (IDC ’19). Association for Computing Machinery, New York, NY, USA, 386–393. https://doi.org/10.1145/3311927.3323156Google ScholarDigital Library
- Farhana Shahid and Aditya Vashistha. 2023. Decolonizing Content Moderation: Does Uniform Global Community Standard Resemble Utopian Equality or Western Power Hegemony?. In Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems (Hamburg, Germany) (CHI ’23). Association for Computing Machinery, New York, NY, USA, Article 391, 18 pages. https://doi.org/10.1145/3544548.3581538Google ScholarDigital Library
- Ather Sharif, Aedan Liam McCall, and Kianna Roces Bolante. 2022. Should I Say “Disabled People” or “People with Disabilities”? Language Preferences of Disabled People Between Identity- and Person-First Language. In Proceedings of the 24th International ACM SIGACCESS Conference on Computers and Accessibility (Athens, Greece) (ASSETS ’22). Association for Computing Machinery, New York, NY, USA, Article 10, 18 pages. https://doi.org/10.1145/3517428.3544813Google ScholarDigital Library
- Manuka Stratta, Julia Park, and Cooper deNicola. 2020. Automated Content Warnings for Sensitive Posts. In Extended Abstracts of the 2020 CHI Conference on Human Factors in Computing Systems (Honolulu, HI, USA) (CHI EA ’20). Association for Computing Machinery, New York, NY, USA, 1–8. https://doi.org/10.1145/3334480.3383029Google ScholarDigital Library
- Hugo Touvron, Thibaut Lavril, Gautier Izacard, Xavier Martinet, Marie-Anne Lachaux, Timothée Lacroix, Baptiste Rozière, Naman Goyal, Eric Hambro, Faisal Azhar, Aurelien Rodriguez, Armand Joulin, Edouard Grave, and Guillaume Lample. 2023. LLaMA: Open and Efficient Foundation Language Models. arxiv:2302.13971 [cs.CL]Google Scholar
- Kristen Vaccaro, Ziang Xiao, Kevin Hamilton, and Karrie Karahalios. 2021. Contestability For Content Moderation. Proc. ACM Hum.-Comput. Interact. 5, CSCW2, Article 318 (oct 2021), 28 pages. https://doi.org/10.1145/3476059Google ScholarDigital Library
- Nishant Vishwamitra, Yifang Li, Hongxin Hu, Kelly Caine, Long Cheng, Ziming Zhao, and Gail-Joon Ahn. 2022. Towards Automated Content-Based Photo Privacy Control in User-Centered Social Networks. In Proceedings of the Twelfth ACM Conference on Data and Application Security and Privacy (Baltimore, MD, USA) (CODASPY ’22). Association for Computing Machinery, New York, NY, USA, 65–76. https://doi.org/10.1145/3508398.3511517Google ScholarDigital Library
- Wayne Xin Zhao, Kun Zhou, Junyi Li, Tianyi Tang, Xiaolei Wang, Yupeng Hou, Yingqian Min, Beichen Zhang, Junjie Zhang, Zican Dong, Yifan Du, Chen Yang, Yushuo Chen, Zhipeng Chen, Jinhao Jiang, Ruiyang Ren, Yifan Li, Xinyu Tang, Zikang Liu, Peiyu Liu, Jian-Yun Nie, and Ji-Rong Wen. 2023. A Survey of Large Language Models. arxiv:2303.18223 [cs.CL]Google Scholar
Index Terms
- Analyzing the Use of Large Language Models for Content Moderation with ChatGPT Examples
Recommendations
A Trade-off-centered Framework of Content Moderation
Content moderation research typically prioritizes representing and addressing challenges for one group of stakeholders or communities in one type of context. While taking a focused approach is reasonable or even favorable for empirical case studies, it ...
Content Moderation Folk Theories and Perceptions of Platform Spirit among Marginalized Social Media Users
Social media users create folk theories to help explain how elements of social media operate. Marginalized social media users face disproportionate content moderation and removal on social media platforms. We conducted a qualitative interview study (n = ...
Implications of Revenue Models and Technology for Content Moderation Strategies
This paper develops a theoretical model to study how the revenue model and technology of a social media platform affect its content-moderation strategy.
This paper develops a theoretical model to study the economic incentives for a social media platform to moderate user-generated content. We show that a self-interested platform can use content moderation as an effective marketing tool to expand its ...
Comments