Md. Samin Rahman1, Rafid Mahboob1, Abu Sayed Chowdhury1, Abu Saleh Mohammad Fahim1
Keywords: Feed Forward Neural Network, Natural Language Processing (NLP), Word Embedding, Word Stemming, Seq2Seq Model.
Abstract: In the era of machine intelligence, a chatbot has become popular and several intelligent chatbots are designed which replaced the traditional chatbots. A Chatbot is artificial intelligence (AI) software that uses key pre-calculated user phrases and auditory or text-based signals to simulate interactive human conversation. Chatbots rise as a key area for Human-Computer Interaction (HCI) community. Empathy is the ability to understand human emotions. Empathy in a chatbot is a new topic for the chatbot interface. With the help of Empathy, a chatbot can detect the human emotion or state of condition and talk accordingly with the user. Recent efforts are also aimed at creating more responsive chatbots for deeper and emotional talks. This can also help enhance chatbot use by making users feel better. Few chatbots are available in the Bangla language but none are available that can detect human empathy and act according. The empathetic chatbot can have a conversation with the user and can extract the feelings from the text using some method. The generation of empathic responses will detect and convey appropriate emotional responses more dynamically. This paper aims to discuss ways and methods of using empathy to introduce a Bangla Chatbot.
References
[1] Dewan, T. (2017, April 1). Implementation of a Bangla chatbot.
[2] Mashreky, Saidur & Rahman, Fazlur & Rahman, Aminur. (2013). Suicide Kills More Than 10,000 People Every Year in Bangladesh. Archives of suicide research: official journal of the International Academy for Suicide Research. 17. 387-96. 10.1080/13811118.2013.801809.
[3] T. Young, D. Hazarika, S. Poria and E. Cambria, “Recent Trends in Deep Learning Based Natural Language Processing [Review Article],” in IEEE Computational Intelligence Magazine, vol. 13, no. 3, pp. 55-75, Aug. 2018.
[4] Augello A., Gentile M., Weideveld L., Dignum F. (2016) A Model of a Social Chatbot. In: Pietro G., Gallo L., Howlett R., Jain L. (eds) Intelligent Interactive Multimedia Systems and Services 2016. Smart Innovation, Systems and Technologies, vol 55. Springer, Cham.
[5] MedhiThies, N. Menon, S. Magapu, M. Subramony and J. O’Neill, “How Do You Want Your Chatbot? An Exploratory Wizard-of-Oz Study with Young, Urban Indians”, Human-Computer Interaction – INTERACT 2017, pp. 441-459, 2017.
[6] Islam, Syed & Houya, Most & Islam, Syed & Islam, Salekul & Hossain, Nahid. (2019). Adheetee: A Comprehensive Bangla Virtual Assistant. 10.1109/ICASERT.2019.8934903.
[7] Chowdhury, Shammur & Alam, Firoj & Khan, Naira. (2018). Towards Bangla Named Entity Recognition. 10.1109/ICCITECHN.2018.8631931.
[8] AnbangXu, Zhe Liu, YufanGuo, VibhaSinha, and Rama Akkiraju. 2017. A New Chatbot for Customer Service on Social Media. In Proceedings of the 2017 CHI Conference on Human Factors in Computing Systems (CHI ’17). ACM, New York, NY, USA, 3506-3510. DOI: https://doi.org/10.1145/3025453.3025496
[9] Shum, H.-Y., He, X.-D., & Li, D. (2018). From Eliza to XiaoIce: challenges and opportunities with social chatbots. Frontiers of Information Technology & Electronic Engineering, 19(1), 10–26. doi: 10.1631/fitee.1700826
[10] O. Vinyals and V. Le. 2015. A neural conversational model. arXiv preprint arXiv:1506.05869.
[11] Chad Edwards, Autumn Edwards, Patric R. Spence & Xialing Lin (2018) I, teacher: using artificial intelligence (AI) and social robots in communication and instruction, Communication Education, 67:4, 473480.