ARC-NLP at ClimateActivism 2024: Stance and Hate Speech Detection by Generative and Encoder Models Optimized with Tweet-Specific Elements
Open accessAbstract
Social media users often express hate speech towards specific targets and may either support or refuse activist movements.The automated detection of hate speech, which involves identifying both targets and stances, plays a critical role in event identification to mitigate its negative effects.In this paper, we present our methods for three subtasks of the Climate Activism Stance and Hate Event Detection Shared Task at CASE 2024.For each subtask (i) hate speech identification (ii) targets of hate speech identification (iii) stance detection, we experiment with optimized Transformer-based architectures that focus on tweet-specific features such as hashtags, URLs, and emojis.Furthermore, we investigate generative large language models, such as Llama2, using specific prompts for the first two subtasks.Our experiments demonstrate better performance of our models compared to baseline models in each subtask.Our solutions also achieve third, fourth, and first places respectively in the subtasks. Bias Statement:This paper discusses harmful content and hate speech stereotypes.The authors do not support the use of harmful language, nor any of the harmful representations quoted below.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
LLMs are capable of text mining tasks such as stance detection, sentiment analysis, hate speech, and sociopolitical affiliation of texts.
“recent studies suggest that LLMs are capable of text mining tasks such as stance detection (Lan et al. 2024), sentiment analysis (Lee et al. 2024), hate speech (Kaya, Ozcelik, and Toraman 2024), and sociopolitical affiliation of texts (Ghafouri et al. 2023).”
From Cross-Partisan Interactions on Twitter (2025) · cites this paper as Kaya, Ozcelik, and Toraman 2024
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
No references could be resolved yet.
Research works printed but not linked: 19
- Takuya Akiba, Shotaro Sano, Toshihiko Yanase, Takeru Ohta, and Masanori Koyama. 2019. Optuna: A next- generation hyperparameter optimization framework. In Proceedings of the 25th ACM SIGKDD interna- tional conference on knowledge discovery & data mining, pages 2623-2631.
- Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2018. Bert: Pre-training of deep bidirectional transformers for language understand- ing. arXiv preprint arXiv:1810.04805. · arXiv
- Pengcheng He, Jianfeng Gao, and Weizhu Chen. 2021. Debertav3: Improving deberta using electra-style pre- training with gradient-disentangled embedding shar- ing. arXiv preprint arXiv:2111.09543. · arXiv
- Albert Q Jiang, Alexandre Sablayrolles, Arthur Men- sch, Chris Bamford, Devendra Singh Chaplot, Diego de las Casas, Florian Bressand, Gianna Lengyel, Guil- laume Lample, Lucile Saulnier, et al. 2023. Mistral 7b. arXiv preprint arXiv:2310.06825. · arXiv
- Yinhan Liu, Myle Ott, Naman Goyal, Jingfei Du, Man- dar Joshi, Danqi Chen, Omer Levy, Mike Lewis, Luke Zettlemoyer, and Veselin Stoyanov. 2019. Roberta: A robustly optimized bert pretraining ap- proach. arXiv preprint arXiv:1907.11692. · arXiv
- Dat Quoc Nguyen, Thanh Vu, and Anh Tuan Nguyen. 2020. BERTweet: A pre-trained language model for English tweets. In Proceedings of the 2020 Con- ference on Empirical Methods in Natural Language Processing: System Demonstrations, pages 9-14, On- line. Association for Computational Linguistics.
- Oguzhan Ozcelik and Cagri Toraman. 2022. Named entity recognition in Turkish: A comparative study with detailed error analysis. Information Processing & Management, 59(6):103065.
- Anil Singh Parihar, Surendrabikram Thapa, and Sushruti Mishra. 2021. Hate speech detection using natural language processing: Applications and challenges. In 2021 5th International Conference on Trends in Electronics and Informatics (ICOEI), pages 1302- 1308.
- Umitcan Sahin, Izzet Emre Kucukkaya, Oguzhan Ozce- lik, and Cagri Toraman. 2023. ARC-NLP at multi- modal hate speech event detection 2023: Multimodal methods boosted by ensemble learning, syntactical and entity features. In Proceedings of the 6th Work- shop on Challenges and Applications of Automated Extraction of Socio-political Events from Text, pages 71-78, Varna, Bulgaria. INCOMA Ltd., Shoumen, Bulgaria.
- Umitcan Sahin, Oguzhan Ozcelik, Izzet Emre Ku- cukkaya, and Cagri Toraman. 2022. ARC-NLP at CASE 2022 task 1: Ensemble learning for multilin- gual protest event detection. In Proceedings of the 5th Workshop on Challenges and Applications of Au- tomated Extraction of Socio-political Events from Text (CASE), pages 175-183, Abu Dhabi, United Arab Emirates (Hybrid). Association for Computa- tional Linguistics.
- Victor Sanh, Lysandre Debut, Julien Chaumond, and Thomas Wolf. 2019. Distilbert, a distilled version of bert: smaller, faster, cheaper and lighter. arXiv preprint arXiv:1910.01108. · arXiv
- Shuvam Shiwakoti, Surendrabikram Thapa, Kritesh Rauniyar, Akshyat Shah, Aashish Bhandari, and Us- man Naseem. 2024. Analyzing the dynamics of cli- mate change discourse on twitter: A new annotated corpus and multi-aspect classification. Preprint.
- Mohammad Shoeybi, Mostofa Patwary, Raul Puri, Patrick LeGresley, Jared Casper, and Bryan Catan- zaro. 2019. Megatron-lm: Training multi-billion parameter language models using model parallelism. arXiv preprint arXiv:1909.08053. · arXiv
- Surendrabikram Thapa, Farhan Ahmad Jafri, Ali Hür- riyetoglu, Francielle Vargas, Roy Ka-Wei Lee, and Usman Naseem. 2023. Multimodal hate speech event detection -shared task 4, case 2023. In Proceedings of the 6th Workshop on Challenges and Applications of Automated Extraction of Socio-political Events from Text (CASE).
- Surendrabikram Thapa, Kritesh Rauniyar, Farhan Ah- mad Jafri, Shuvam Shiwakoti, Hariram Veeramani, Raghav Jain, Guneet Singh Kohli, Ali Hürriyetoglu, and Usman Naseem. 2024. Stance and hate event detection in tweets related to climate activism - shared task at case 2024. In Proceedings of the 7th Workshop on Challenges and Applications of Auto- mated Extraction of Socio-political Events from Text (CASE).
- Hugo Touvron, Louis Martin, Kevin Stone, Peter Al- bert, Amjad Almahairi, Yasmine Babaei, Nikolay Bashlykov, Soumya Batra, Prajjwal Bhargava, Shruti Bhosale, et al. 2023. Llama 2: Open founda- tion and fine-tuned chat models. arXiv preprint arXiv:2307.09288. · arXiv
- Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Łukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. Advances in neural information processing systems, 30.
- Nicolas Webersinke, Mathias Kraus, Julia Anna Bin- gler, and Markus Leippold. 2021. Climatebert: A pretrained language model for climate-related text. arXiv preprint arXiv:2110.12010. · arXiv
- Thomas Wolf, Lysandre Debut, Victor Sanh, Julien Chaumond, Clement Delangue, Anthony Moi, Pier- ric Cistac, Tim Rault, Rémi Louf, Morgan Funtowicz, et al. 2019. Huggingface's transformers: State-of- the-art natural language processing. arXiv preprint arXiv:1910.03771. · arXiv
Cited by
Sorted by citations
Cross-Partisan Interactions on Twitter
Çetinkaya, Y. M., Ghafouri, V., Suarez-Tangil, G., Such, J., & Elmas, T. (2025) · Proceedings of the International AAAI Conference on Web and Social Media · doi:10.1609/icwsm.v19i1.35819 · Cited by 2 · see citing works
- Authors
- Kaya, A., Ozcelik, O., & Toraman, C.
- Affiliations
- Aselsan (Turkey) (TR)
- ORCID
- Ozcelik, Oguzhan
- Venue
- Proceedings of the 7th Workshop on Challenges and Applications of Automated Extraction of Socio-political Events from Text (CASE 2024)
- Published
- 2024
- Pages
- 111-117
- OpenAlex
- W7126414360
- Cited by
- 0
- References
- 0
- FWCI
- 0.00
- Type
- conference paper
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- cc-by
- Locations
- Workshop on Challenges and Applications of Automated Extraction of Socio-political Events from Text (CASE) (publishedVersion, cc-by)
- OpenMETU (Middle East Technical University) (submittedVersion, cc-by-nc-nd)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Hate Speech and Cyberbullying Detection
- Physical Sciences › Computer Science › Artificial Intelligence › Sentiment Analysis and Opinion Mining
- Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
- Keywords
- hate speech detection, stance detection, climate activism, target identification, social media, tweets, hashtags, URLs, emojis, generative large language models, Llama 2, transformer models
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
