Even if the feedback mentioned in Section Richness are a step towards good guidance, they are static, which can be problematic. Beginners and professionals in argumentation do not need the same amount of feedback. A child and an adult have different levels of understanding and knowledge. Therefore, it is essential that a model knows to whom it should explain the errors and hence how to adapt its output by providing personalized explanations.
In this section, you can find works showing how different users' proficiency levels in argumentation can be discretized into a small number of categories (Levels of explanations). Other studies chose to allow users to make their custom tags or to choose their preferences among a set of rubrics in order to make the feedback more personal (Self-personalization). Finally we underlined some potentials next directions by redirecting to other references.
| Subsection | Title | Date | Author | Reference |
|---|---|---|---|---|
| Next directions | Personalized gamification for learning: A reactive chatbot architecture proposal | 2023 | Carina González-González, Vanesa Muñoz-Cruz, Pedro Antonio Toledo-Delgado, and Eduardo Nacimiento-García | Sensors, 23(1). |
| Self-personalization | Towards computational persuasion via natural language argumentation dialogues. | 2019 | Anthony Hunter, Lisa Chalaguine, Tomasz Czernuszenko, Emmanuel Hadoux, and Sylwia Polberg | In KI 2019: Advances in Artificial Intelligence, pages 18--33, Cham. Springer International Publishing. |
| Next directions | Survey of personalized learning software systems: A taxonomy of environments, learning content, and user models | 2023 | Heba Ismail, Nada Hussein, Saad Harous, and Ashraf Khalil | Education Sciences, 13(7). |
| Next directions | Personalized multimodal feedback generation in education | 2020 | Haochen Liu, Zitao Liu, Zhongqin Wu, and Jiliang Tang | In Proceedings of the 28th International Conference on Computational Linguistics, pages 1826--1840, Barcelona, Spain (Online). International Committee on Computational Linguistics. |
| Next directions | One chatbot per person: Creating personalized chatbots based on implicit user profiles | 2021 | Zhengyi Ma, Zhicheng Dou, Yutao Zhu, Hanxun Zhong, and Ji-Rong Wen | In Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR 2021). ACM. |
| Next directions | Pchatbot: A large-scale dataset for personalized chatbot | 2021 | Hongjin Qian, Xiaohe Li, Hanxun Zhong, Yu Guo, Yueyuan Ma, Yutao Zhu, Zhanliang Liu, Zhicheng Dou, and Ji-Rong Wen | In Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR 2021) |
| Levels of explanations | "mama always had a way of explaining things so I could understand": A dialogue corpus for learning to construct explanations | 2022 | Henning Wachsmuth and Milad Alshomary | In Proceedings of the 29th International Conference on Computational Linguistics, pages 344--354, Gyeongju, Republic of Korea. International Committee on Computational Linguistics. |
| Next directions | A review of ai-driven conversational chatbots implementation methodologies and challenges (1999–2022) | 2023 | Chien-Chang Lin, Anna Huang, and Stephen Yang | Sustainability, 15:4012. |
| Self-personalization | TIARA: A tool for annotating discourse relations and sentence reordering | 2020 | Jan Wira Gotama Putra, Simone Teufel, Kana Matsumura, and Takenobu Tokunaga | In Proceedings of the 12th Language Resources and Evaluation Conference, pages 6912--6920, Marseille, France. European Language Resources Association. |
| Levels of explanations | ALEN app: Argumentative writing support to foster English language learning | 2022 | Thiemo Wambsganß, Andrew Caines, and Paula Buttery | In Proceedings of the 17th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2022), pages 134--140, Seattle, Washington. Association for Computational Linguistics. |
| Levels of explanations | Al: An adaptive learning support system for argumentation skills | 2020 | Thiemo Wambsganß, Christina Niklaus, Matthias Cetto, Matthias Söllner, Siegfried Handschuh, and Jan Marco Leimeister | In Proceedings of the 2021 CHI Conference on Human Factors in Computing Systems (CHI 2020). |