Vol. 1 No. 2 (2026)

Articles

Deliberation Quality under Argument Mining Features in Online Consultation Platforms: Model Audit

Published 2026-03-23

  • Ana Rezende Fernandes
    • ,
  • Matheus Pereira Rodrigues

Ana Rezende Fernandes
Department of Computer and Digital Systems Engineering, Polytechnic School, Universidade de São Paulo, São Paulo, Brazil

Matheus Pereira Rodrigues
Department of Computer and Digital Systems Engineering, Polytechnic School, Universidade de São Paulo, São Paulo, Brazil

Language, Knowledge and Intelligent Systems, Volume 1, Issue 2, 2026 cover

Abstract

The proliferation of digital democracy initiatives has resulted in an exponential increase in text data generated through online civic consultation platforms. To process and analyze these vast repositories of public input, researchers and policymakers increasingly rely on natural language processing techniques, particularly argument mining, to assess the quality of civic deliberation. However, the application of automated argument mining in the context of democratic participation raises critical questions about algorithmic bias, model validity, and the faithful representation of deliberative norms. This paper presents a comprehensive model audit of argument mining features and their alignment with deliberation quality in online consultation platforms. By systematically evaluating how machine learning models extract and interpret argument structures such as claims, premises, and backing evidence, we assess the capacity of these models to capture the nuanced realities of human discourse. The audit methodology focuses on examining potential biases in feature extraction, particularly concerning the structural formality and length of citizen contributions. Our findings indicate that while current models achieve high accuracy in identifying explicit structural components in formal language, they systematically undervalue informal, narrative-based argumentation often utilized by marginalized demographic groups. Furthermore, the reliance on explicit discourse markers creates a skewed representation of deliberation quality, heavily favoring verbose and highly structured text over substantive but implicitly reasoned arguments. The paper concludes by outlining recommendations for developing more robust, equitable, and context-aware argument mining systems capable of supporting inclusive digital democracy.

Keywords

Argument Mining, Deliberation Quality, Model Audit, Online Consultation, Algorithmic Fairness

PDF

References

  1. 1. Tardaguila, J.; Stoll, M.; Gutiérrez, S.; Proffitt, T.; Diago, M.P. Smart applications and digital technologies in viticulture: A review. Smart Agric. Technol. 2021, 1, 100005.
  2. 2. Rocha, E.D.S.; Chevtchenko, S.F.; Cambuim, L.F.S.; Macieira, R.M. Optimized Pallet Localization Using RGB-D Camera and Deep Learning Models. In Proceedings of the 2023 IEEE 19th International Conference on Intelligent Computer Communication and Processing (ICCP), Cluj-Napoca, Romania, 26–28 October 2023; pp. 155–162.
  3. 3. Paszke, A.; Gross, S.; Massa, F.; Lerer, A.; Bradbury, J.; Chanan, G.; Killeen, T.; Lin, Z.; Gimelshein, N.; Antiga, L.; et al. Pytorch: An imperative style, high-performance deep learning library. In Advances in Neural Information Processing Systems (NeurIPS); The MIT Press: Cambridge, MA, USA, 2019; Volume 32, pp. 8026–8037.
  4. 4. Zhu, W.; Guo, X.; Owaki, D.; Kutsuzawa, K.; Hayashibe, M. A Survey of Sim-to-Real Transfer Techniques Applied to Reinforcement Learning for Bioinspired Robots. IEEE Trans. Neural Netw. Learn. Syst. 2023, 34, 3444–3459.
  5. 5. Bohr, A.; Memarzadeh, K. The Rise of Artificial Intelligence in Healthcare Applications. In Artificial Intelligence in Healthcare; Academic Press: Cambridge, MA, USA, 2020; pp. 25–60.
  6. 6. Zhang, Z.; Meng, Q.; Cui, Z.; Yao, M.; Shao, Z.; Tao, B. Machine Learning Applications in Parallel Robots: A Brief Review. Machines 2025, 13, 565.
  7. 7. Kirillov, A.; Girshick, R.; He, K.; Dollár, P. Panoptic feature pyramid networks. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA, 15–20 June 2019; pp. 6392–6401.
  8. 8. Zhang, Y.; Lu, J.; Xia, G.; Khajepour, A. Enhancing Roll Stability of Counterbalance Forklift Trucks With a Novel Rollover Index and Hierarchical Adaptive Model Predictive Control. IEEE Trans. Veh. Technol. 2024, 73, 7925–7938.
  9. 9. Tan, M.; Le, Q. Efficientnetv2: Smaller models and faster training. In Proceedings of the International Conference on Machine Learning (ICML), PMLR, Virtual, 18–24 July 2021; pp. 10096–10106.
  10. 10. Hadwiger, S.; Kube, D.; Lavrik, V.; Meisen, T. Towards Precision in Motion: Investigating the Influences of Curriculum Learning based on a Multi-Purpose Performance Metric for Vision-Based Forklift Navigation. In Proceedings of the 2024 IEEE 20th International Conference on Automation Science and Engineering (CASE), Bari, Italy, 28 August–1 September 2024; pp. 796–803.
  11. 11. Mohammadpour, M.; Kelouwani, S. Energy-Optimal Trajectory Planning with Vehicle’s Dynamic Model Considerations. In Proceedings of the 2025 IEEE International Conference on Mechatronics (ICM), Wollongong, Australia, 28 February–2 March 2025; pp. 1–6.
  12. 12. Raineri, M.; Perri, S.; Lo Bianco, C.G. Online velocity planner for Laser Guided Vehicles subject to safety constraints. In Proceedings of the 2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Vancouver, BC, Canada, 24–28 September 2017; pp. 6178–6184.
  13. 13. Beleznai, C.; Zeilinger, M.; Huemer, J.; Pointner, W.; Wimmer, S.; Zips, P. Automated pallet handling via occlusion-robust recognition learned from synthetic data*. In Proceedings of the 2023 IEEE Conference on Artificial Intelligence (CAI), Santa Clara, CA, USA, 5–6 June 2023; pp. 74–75.
  14. 14. Maset, E.; Scalera, L.; Beinat, A.; Visintini, D.; Gasparetto, A. Performance investigation and repeatability assessment of a mobile robotic system for 3D mapping. Robotics 2022, 11, 54.
  15. 15. Villani, V.; Pini, F.; Leali, F.; Secchi, C. Survey on Human–Robot Collaboration in Industrial Settings: Safety, Intuitive Interfaces and Applications. Mechatronics 2018, 55, 248–266.
  16. 16. Katharopoulos, A.; Vyas, A.; Pappas, N.; Fleuret, F. Transformers are RNNs: Fast autoregressive transformers with linear attention. In Proceedings of the International Conference on Machine Learning (ICML), PMLR, Virtual, 13–18 July 2020; pp. 5156–5165.
  17. 17. Huang, J.; Xu, Y.; Wang, Q.; Wang, Q.; Liang, X.; Wang, F.; Zhang, Z.; Wei, W.; Zhang, B.; Huang, L.; et al. Foundation Models and Intelligent Decision-Making: Progress, Challenges, and Perspectives. Innovation 2025, 6, 100948.
  18. 18. Tu, K.Y.; Hung, C.P.; Lin, H.Y.; Lin, K.Y. Simulation and Implementation of the Modeling of Forklift with Tricycle in Warehouse Systems for ROS. Sensors 2025, 25, 5206.