Proceedings of the International Conference on Smart Systems and Social Management (ICSSSM-2 2025)

<Previous Article In Volume
Next Article In Volume>

Dyslexia Chatbot Architecture Using Reinforcement Learning Based Seq2Seq Model integrated with K-Fold Cross-validation

Authors
Adarsh Pradhan1, 2, *, Mirzanur Rahman2, Sazzadur Rahman1, Kukil Bharadwaj1, Manash Kar1
1Department of Computer Science and Engineering, Girijananda Chowdhury Institute of Management and Technology, Girijananda Chowdhury University, Guwahati, Assam, 781017, India
2Department of Information Technology, Gauhati University, Guwahati, Assam, 781014, India
*Corresponding author. Email: adarsh@gauhati.ac.in Email: adarsh_cse@gcuniversity.ac.in
Corresponding Author
Adarsh Pradhan
Available Online 31 December 2025.
DOI
10.2991/978-2-38476-533-1_9How to use a DOI?
Keywords
Dyslexia; Chatbot; Reinforcement Learning; Seq2Seq; K-Fold cross-validation; BLEU score
Abstract

When it comes to the dissemination of information and ease of receiving answers to queries about dyslexia, the prevalence of a dyslexia-specific chatbot is sparse. Our effort here is to create a chatbot model that anyone with queries about dyslexia can use. In this study, we propose a Reinforcement Learning based Seq2Seq model, merged with K-Fold cross-validation. Using the BLEU score as the reward mechanism, iterative updates are made to the Reinforcement Learning parameters so that the model learns to adjust its predictions based on the rewards it receives. We have also created a dyslexia-centric conversational dataset with the help of some reliable online resources like the British Dyslexia Association and the International Dyslexia Association. The diversity and coverage scores of our dataset are 0.8541 and 0.9172, respectively. Our proposed model could achieve an accuracy of 0.9678, an F1 score of 0.9570, and a BLEU score of 0.9473.

Copyright
© 2025 The Author(s)
Open Access
Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

<Previous Article In Volume
Next Article In Volume>
Volume Title
Proceedings of the International Conference on Smart Systems and Social Management (ICSSSM-2 2025)
Series
Advances in Social Science, Education and Humanities Research
Publication Date
31 December 2025
ISBN
978-2-38476-533-1
ISSN
2352-5398
DOI
10.2991/978-2-38476-533-1_9How to use a DOI?
Copyright
© 2025 The Author(s)
Open Access
Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Cite this article

risenwbib
TY  - CONF
AU  - Adarsh Pradhan
AU  - Mirzanur Rahman
AU  - Sazzadur Rahman
AU  - Kukil Bharadwaj
AU  - Manash Kar
PY  - 2025
DA  - 2025/12/31
TI  - Dyslexia Chatbot Architecture Using Reinforcement Learning Based Seq2Seq Model integrated with K-Fold Cross-validation
BT  - Proceedings of the International Conference on Smart Systems and Social Management (ICSSSM-2 2025)
PB  - Atlantis Press
SP  - 117
EP  - 136
SN  - 2352-5398
UR  - https://doi.org/10.2991/978-2-38476-533-1_9
DO  - 10.2991/978-2-38476-533-1_9
ID  - Pradhan2025
ER  -