BichoBot – A Chatbot to Assist in the Reception of Incoming University Students

• Sheiely do Ó Nascimento UFC
• Enyo Gonçalves UFC
• Marcos Oliveira UFC
• Erlânio Freire Barros UFC

DOI: https://doi.org/10.5753/eniac.2025.13665

Resumo

The beginning of the journey in a higher education course is often surrounded by doubts from incoming students about various topics such as scholarship policies, course characteristics, library use, university restaurant, among other aspects of university life. Information about these topics is often found on different websites and documents, which makes it difficult for incoming students to find. Given this difficulty, actions that centralize this information to help students identify it become necessary. Thus, in this context, this article presents BichoBot, a chatbot developed to support freshmen in accessing institutional information at the Federal University of Ceará (UFC) - Quixadá Campus. BichoBot involves the use of the Rasa and RAG frameworks, with a LLaMA 3 language model. BichoBot offers contextualized and reliable answers via Telegram. The proposed solution was evaluated by UFC freshmen, demonstrating good performance in addressing the most common questions from students.

Referências

AI, M. (2023). Mistral 7b. Accessed: 2025-05-23.

Ait-Mlouk, A. and Jiang, L. (2020). Kbot: A knowledge graph based chatbot for natural language understanding over linked data. In IEEE Access, volume 8, pages 149220–149230. IEEE.

Andriola, W. B. and Araújo, A. C. (2021). Adaptação de alunos ao ambiente universitário: estudo de caso em cursos de graduação da universidade federal do ceará. Ensaio: Avaliação e Políticas Públicas em Educação, 29(110):135–159.

Bender, E. M. and Koller, A. (2020). Climbing towards nlu: On meaning, form, and understanding in the age of data. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 5185–5198. ACL.

DeepMind, G. (2023). Gemini: Our most capable ai models. [link]. Accessed: 2025-05-23.

dos Anjos Afonso, D. L. (2024). Uso da Inteligência Artificial em Chatbot para Apoio aos Estudantes dos Cursos a Distância na Área da Saúde. Tese de doutorado, Universidade Federal de São Paulo (UNIFESP). Disponível em: OASISbr.

Gao, T., Zhang, J., Wang, J., Zhou, S., et al. (2024). Deepseek-vl: Scaling open-vocabulary vision-language models with vision-language instruction data.

GitHub and OpenAI (2023). Github copilot: Your ai pair programmer. [link]. Accessed: 2025-05-23.

Kitchenham, B. A. and Pfleeger, S. L. (2002). Principles of survey research: part 3: constructing a survey instrument. ACM SIGSOFT Software Engineering Notes, 27(2):20–24.

Kuratomi, G., Pirozelli, P., Cozman, F., and Peres, S. (2024). A rag-based institutional assistant. In Anais do XXI Encontro Nacional de Inteligência Artificial e Computacional, pages 755–766, Porto Alegre, RS, Brasil. SBC.

Lewis, M. et al. (2020). Retrieval-augmented generation for knowledge-intensive nlp tasks. In Proceedings of the 38th International Conference on Machine Learning (ICML). ICML.

Machado, G., Mello, G., Junior, W., and Alves, E. (2025). Siac: Sistema de apoio ao calouro com integração ao chatbot mica (módulo interativo de conteúdos acadêmicos). In Anais Estendidos do XXI Simpósio Brasileiro de Sistemas de Informação, pages 201–205, Porto Alegre, RS, Brasil. SBC.

Meta (2024). The llama 3 herd of models.

Neto, J. R., Miranda, P., Mello, R., and Nascimento, A. (2022). Chatbot to support frequently asked questions from students in higher education institutions. In Anais do XIX Encontro Nacional de Inteligência Artificial e Computacional, pages 591–601, Porto Alegre, RS, Brasil. SBC.

OpenAI (2023). Chatgpt: Optimizing language models for dialogue. [link]. Accessed: 2025-05-23.

PET Conexão dos Saberes (2025). Manual de sobrevivência do calouro. Material interno, Universidade Federal do Ceará, Campus Quixadá.

Rahman, A. M., Mamun, A. A., and Islam, A. (2017). Programming challenges of chat-bot: Current and future prospective. In 2017 IEEE Region 10 Humanitarian Technology Conference (R10-HTC), pages 75–78.

RASA TECHNOLOGIES (2025). Rasa: Open Source Conversational AI. Rasa Technologies. Disponível em: [link]. Acesso em: 26 jan. 2025.

Reimers, N. and Gurevych, I. (2019). Sentence-bert: Sentence embeddings using siamese bert-networks. CoRR, abs/1908.10084.

Rocho, R., Perez, A., Farias, G., and Panisson, A. (2024). Integrating llms and chatbots technologies - a case study on brazilian transit law. In Anais do XXI Encontro Nacional de Inteligência Artificial e Computacional, pages 731–742, Porto Alegre, RS, Brasil. SBC.

Sampaio, A. G., Silva, A., Oliveira, B., Silva, F. J., Nascimento, S., Brito, W., Menezes, V., and Tavares, W. (2024). Pet-recebe: Apresentando um campus universitário temático na Área de tecnologia da informação para estudantes de escolas públicas do interior do ceará. In Anais do XXX Workshop de Informática na Escola, pages 598–610, Porto Alegre, RS, Brasil. SBC.

Shawar, B. A. and Atwell, E. (2007). Chatbots: Are they really useful? In Language Engineering Conference. IEEE.

Sidhu, B. K. et al. (2013). Natural language processing. In International Journal of Computer Technology and Applications, volume 4, page 751. IJCTA.

Teixeira, M. A. P., Dias, A. C. G., Wottrich, S. H., and Oliveira, A. M. (2008). Adaptação à universidade em jovens calouros. Psicologia Escolar e Educacional, 12(1):185–202.

Venkatesh, V., Morris, M. G., Davis, G. B., and Davis, F. D. (2003). User acceptance of information technology: Toward a unified view. MIS Quarterly, 27(3):425–478.

Zeng, J. et al. (2023). The rise of conversational ai: A study of chatgpt, deepseek, and gemini. In Journal of Artificial Intelligence and Robotics. JAIR.