Browse > Article
http://dx.doi.org/10.9708/jksci.2021.26.12.053

A BERGPT-chatbot for mitigating negative emotions  

Song, Yun-Gyeong (Dept. of Computer and Electronics Convergence Engineering, Sunmoon University)
Jung, Kyung-Min (Dept. of Computer and Electronics Convergence Engineering, Sunmoon University)
Lee, Hyun (Division of Computer Science and Engineering, Sunmoon University)
Abstract
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.
Keywords
Deep Learning; Sentiment Analysis; AI Chatbot; KR-BERT; KoGPT2-chatbot;
Citations & Related Records
연도 인용수 순위
  • Reference
1 Radford, A., Narasimhan, K., Salimans, T., and Sutskever, I., "Improving language understanding by generative pre-training", 2018.
2 Radford, A., Wu, J., Child, R., Luan, D., Amodei, D., & Sutskever, I., "Language models are unsupervised multitask learners", OpenAI blog, 1(8), 9. 2019.
3 SKT Open Source, https://sktelecom.github.io/project/kogpt2/
4 Huggingface, https://huggingface.co/transformers/perplexity.html
5 AI-Hub, https://aihub.or.kr/aidata/7978/download
6 Naver sentiment movie corpus v1.0, https://github.com/e9t/nsmc
7 Hakim, F. Z. M.., Indrayani, L. M.., and Amalia, R. M., "A dialogic analysis of compliment strategies employed by replika chatbot", In Third International Conference of Arts, Language and Culture, Vol. 279, pp. 266-271, February 2019. DOI: https://doi.org/10.2991/icalc-18.2019.38
8 ETRI, AI API.DATA, https://aiopen.etri.re.kr/service_dataset.php
9 SKT Open Source, https://sktelecom.github.io/project/kobert/
10 AI-Hub, https://aihub.or.kr/opendata/keti-data/recognition-laguage/KETI-02-006
11 Sanghoun Song, "Phraseological Analysis of Learner Corpus Based on Language Model", LANGUAGE AND INFORMATION, Vol. 22, No. 1, pp. 123-152, February 2018.   DOI
12 Brown, T. B., Mann, B., Ryder, N., Subbiah, M., Kaplan, J., Dhariwal, P., ... & Amodei, D., "Language models are few-shot learners", arXiv preprint arXiv:2005.14165. 2020.
13 NIKL, https://corpus.korean.go.kr/#down
14 KoGPT2-chatbot, https://github.com/haven-jeon/KoGPT2-chatbot
15 Devlin, J., Chang, M. W., Lee, K., and Toutanova, K., "Bert: Pre-training of deep bidirectional transformers for language understanding", arXiv preprint arXiv:1810.04805. 2018.
16 The New York Times, https://www.nytimes.com/2021/06/01/health/artificial-intelligence-therapy-woebot.html
17 Doyoun Kim, ChoMinKi, Shin Heecheon, "The Application of Artificial Intelligence Technology in Counseling and Psychotherapy: Recent Foreign Cases", Korean Journal Of Counseling And Psychotherapy, Vol. 32, No. 2, pp. 821-847, May 2020.   DOI
18 Se Hun An, Ok Ran Jeong, "A Study on the Psychological Counseling AI Chatbot System based on Sentiment Analysis", Journal of Information Technology Services, Vol. 20, No. 3, pp. 75-86, June 2021. DOI: 10.9716/KITS.2021.20.3.075   DOI
19 Sangah Lee, HAN SOL JANG, Yunmee Baik, Suzi Park, Hyopil Shin, "A Small-Scale Korean-Specific BERT Language Model", Journal of KIISE, Vol. 47, No. 7, pp. 682-692, July 2020. DOI: 10.5626/JOK.2020.47.7.682   DOI
20 Jae-Ok Min, Jin-Woo Park, Yu-Jeong Jo, Bong-Gun Lee, "Korean Machine Reading Comprehension for Patent Consultation Using BERT", KIPS Transactions on Software and Data Engineering, Vol. 9, No. 4, pp. 145-152, April 2020.   DOI
21 AI-Hub, https://aihub.or.kr/opendata/keti-data/recognition-laguage/KETI-02-009
22 Trost, https://trost.co.kr/
23 Hellobot, https://thingsflow.kr/
24 Soo-jin Seol, Su-Hee Hong, Doh-yeon Kim, Yongtae Shin, "A Study on Factors Influencing the Intention to Use the Intelligent Mental Health Diagnosis System-Focused on a Diagnosis System for Firefighters", Jounal of The Korea Society of Information Technology Policy & Management, Vol. 12, No. 6, pp. 2207-2213, December 2020.