Open Access Open Access  Restricted Access Subscription or Fee Access

Developing a Python-based Chatbot Library SansArLIB for Advanced Communication: A Comparative Study with Baseline Chatbots

Prafull Pandey, Ashish Dwivedi, Sanskar Khanna, Arvind Kumar Sahu

Abstract


The purpose of this study was to develop and evaluate a Python-based library called "SansArLIB" for improving chatbot technology. The library was designed to provide developers with a comprehensive set of tools and resources for creating more advanced chatbots that can better understand and respond to user queries. The study involved developing the library and testing it across three different chatbot scenarios. The results showed that the SansArLIB library had an average accuracy of 92.0%, with a standard deviation of 2.3%, and a mean user satisfaction score of 87.5%, with a standard deviation of 2.2%. The average response time was found to be 1.9 seconds, with a standard deviation of 0.5 seconds, while the mean turn-taking time and dialog duration were found to be 1.5 seconds and 6.4 seconds, respectively. These results demonstrate that the SansArLIB library can significantly improve the performance of chatbots and enhance the user experience. This research contributes to the ongoing efforts to advance chatbot technology and provides a valuable resource for developers seeking to create more sophisticated and user-friendly chatbots. Chatbots are becoming increasingly popular in various industries, from customer service to e-commerce. However, designing and developing an effective chatbot can be a challenging task, especially when it comes to handling complex communication scenarios. In this paper, we present SansArLIB, a Python library that provides a comprehensive set of tools for chatbot developers. The library includes various data related to chatbot communication, such as pre-built chatbot templates, conversation models, and AI algorithms. We demonstrate the effectiveness of SansArLIB through a case study where we use it to build a chatbot for a customer support service.


Full Text:

PDF

References


Gao, J., Su, D., & Zhang, Z. (2019). A review of chatbot technology.Journal of Computer Research and Development, 56(11), 2349-2361.

Wang, Y., & Lu, X. (2018). Chatbot design: A review and future directions. Proceedings of the IEEE International Conference on Software Quality, Reliability and Security Companion, 205-211.

Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., ... & Polosukhin, I. (2017). Attention is all you need. In Advances in neural information processing systems (pp. 5998-6008).

Zhang, Y., & Wallace, B. C. (2019). A sensitivity analysis of (and practitioners’ guide to) convolutional neural networks for sentence classification. arXiv preprint arXiv:1510.03820.

Sutskever, I., Vinyals, O., & Le, Q. V. (2014). Sequence to sequence learning with neural networks. Advances in neural information processing systems, 3104-3112.

Bengio, Y., Courville, A., & Vincent, P. (2013). Representation learning: A review and new perspectives. IEEE transactions on pattern analysis and machine intelligence, 35(8), 1798-1828.

Brown, T. B., Mann, B., Ryder, N., Subbiah, M., Kaplan, J., Dhariwal, P., ... & Amodei, D. (2020). Language models are few-shot learners. Advances in Neural Information Processing Systems, 33.

Chollet, F. (2018). Deep learning with Python. Manning Publications Co.

Devlin, J., Chang, M. W., Lee, K., & Toutanova, K. (2019). BERT: Pre-training of deep bidirectional transformers for language understanding. Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), 4171- 4186.

Radford, A., Wu, J., Child, R., Luan, D., Amodei, D., & Sutskever, I. (2019).

Mikolov, T., Sutskever, I., Chen, K., Corrado, G. S., & Dean, J. (2013). Distributed representations of words and phrases and their compositionality. Advances in neural information processing systems, 26, 3111-3119.

Peters, M. E., Neumann, M., Iyyer, M., Gardner, M., Clark, C., Lee, K., & Zettlemoyer, L. (2018). Deep contextualized word representations. Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers), 2227-2237.

Lewis, M., Liu, Y., Goyal, N., Ghazvininejad, M., Mohamed, A., Levy, O., ... & Zettlemoyer, L. (2020). BART: Denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension. arXiv preprint arXiv:1910.13461.

Li, J., Galley, M., Brockett, C., Gao, J., & Dolan, B. (2016). A diversity-promoting objective function for neural conversation models. Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, 110-119.

Roller, S., Dinan, E., Goyal, N., & Weston, J. (2020). Recipes for building an opendomain chatbot. arXiv preprint arXiv:2004.13637.




DOI: https://doi.org/10.37628/ijtet.v9i1.1857

Refbacks

  • There are currently no refbacks.