@article{ART002789877},
author={Song Yun-Gyeong and Kyung-Min Jung and Hyun Lee},
title={A BERGPT-chatbot for mitigating negative emotions},
journal={Journal of The Korea Society of Computer and Information},
issn={1598-849X},
year={2021},
volume={26},
number={12},
pages={53-59},
doi={10.9708/jksci.2021.26.12.053}
TY - JOUR
AU - Song Yun-Gyeong
AU - Kyung-Min Jung
AU - Hyun Lee
TI - A BERGPT-chatbot for mitigating negative emotions
JO - Journal of The Korea Society of Computer and Information
PY - 2021
VL - 26
IS - 12
PB - The Korean Society Of Computer And Information
SP - 53
EP - 59
SN - 1598-849X
AB - In this paper, we propose a BERGPT-chatbot, a domestic AI chatbot that can alleviate negative emotions based on text input such as ‘Replika’. We made BERGPT-chatbot into a chatbot capable of mitigating negative emotions by pipelined two models, KR-BERT and KoGPT2-chatbot. We applied a creative method of giving emotions to unrefined everyday datasets through KR-BERT, and learning additional datasets through KoGPT2-chatbot. The development background of BERGPT-chatbot is as follows. Currently, the number of people with depression is increasing all over the world. This phenomenon is emerging as a more serious problem due to COVID-19, which causes people to increase long-term indoor living or limit interpersonal relationships. Overseas artificial intelligence chatbots aimed at relieving negative emotions or taking care of mental health care, have increased in use due to the pandemic. In Korea, Psychological diagnosis chatbots similar to those of overseas cases are being operated. However, as the domestic chatbot is a system that outputs a button-based answer rather than a text input-based answer, when compared to overseas chatbots, domestic chatbots remain at a low level of diagnosing human psychology. Therefore, we proposed a chatbot that helps mitigating negative emotions through BERGPT-chatbot. Finally, we compared BERGPT-chatbot and KoGPT2-chatbot through ‘Perplexity’, an internal evaluation metric for evaluating language models, and showed the superity of BERGPT-chatbot.
KW - Deep Learning;Sentiment Analysis;AI Chatbot;KR-BERT;KoGPT2-chatbot
DO - 10.9708/jksci.2021.26.12.053
ER -
Song Yun-Gyeong, Kyung-Min Jung and Hyun Lee. (2021). A BERGPT-chatbot for mitigating negative emotions. Journal of The Korea Society of Computer and Information, 26(12), 53-59.
Song Yun-Gyeong, Kyung-Min Jung and Hyun Lee. 2021, "A BERGPT-chatbot for mitigating negative emotions", Journal of The Korea Society of Computer and Information, vol.26, no.12 pp.53-59. Available from: doi:10.9708/jksci.2021.26.12.053
Song Yun-Gyeong, Kyung-Min Jung, Hyun Lee "A BERGPT-chatbot for mitigating negative emotions" Journal of The Korea Society of Computer and Information 26.12 pp.53-59 (2021) : 53.
Song Yun-Gyeong, Kyung-Min Jung, Hyun Lee. A BERGPT-chatbot for mitigating negative emotions. 2021; 26(12), 53-59. Available from: doi:10.9708/jksci.2021.26.12.053
Song Yun-Gyeong, Kyung-Min Jung and Hyun Lee. "A BERGPT-chatbot for mitigating negative emotions" Journal of The Korea Society of Computer and Information 26, no.12 (2021) : 53-59.doi: 10.9708/jksci.2021.26.12.053
Song Yun-Gyeong; Kyung-Min Jung; Hyun Lee. A BERGPT-chatbot for mitigating negative emotions. Journal of The Korea Society of Computer and Information, 26(12), 53-59. doi: 10.9708/jksci.2021.26.12.053
Song Yun-Gyeong; Kyung-Min Jung; Hyun Lee. A BERGPT-chatbot for mitigating negative emotions. Journal of The Korea Society of Computer and Information. 2021; 26(12) 53-59. doi: 10.9708/jksci.2021.26.12.053
Song Yun-Gyeong, Kyung-Min Jung, Hyun Lee. A BERGPT-chatbot for mitigating negative emotions. 2021; 26(12), 53-59. Available from: doi:10.9708/jksci.2021.26.12.053
Song Yun-Gyeong, Kyung-Min Jung and Hyun Lee. "A BERGPT-chatbot for mitigating negative emotions" Journal of The Korea Society of Computer and Information 26, no.12 (2021) : 53-59.doi: 10.9708/jksci.2021.26.12.053
