John Lee
ABSTRACT
Chatbots are increasingly used for delivering mental health assistance. As part of our effort to develop a chatbot on academic and social issues for Cantonese-speaking students, we have constructed a dataset of 1,028 post-reply pairs on test anxiety and loneliness. The posts, harvested from Cantonese social media, are manually classified to a symptom category drawn from counselling literature; the replies are human-crafted, offering brief advice for each post. For response selection, the chatbot predicts the quality of a candidate post-reply pair with a regression model. During training, the symptom categories were used as proxies of reply relevance. In experiments, this approach improved response selection accuracy over a binary classification model and a weakly supervised regression model. This result suggests that manual annotation of symptom category can help boost the performance of a counsellor chatbot.
- A. Bartl and G. Spanakis. 2017. A Retrieval-Based Dialogue System Utilizing Utterance and Context Embeddings. In 2017 16th IEEE International Conference on Machine Learning and Applications (ICMLA). 1120–1125.Google Scholar
- Yiming Cui, Wanxiang Che, Ting Liu, Bing Qin, Ziqing Yang, Shijin Wang, and Guoping Hu. 2019. Pre-Training with Whole Word Masking for Chinese BERT. In arXiv:1906.08101.Google Scholar
- Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. BERT: Pretraining of Deep Bidirectional Transformers for Language Understanding. In Proc. NAACL-HLT.Google Scholar
- K. K. Fitzpatrick, A. Darcy, and M. Vierhile. 2017. Delivering Cognitive Behavior Therapy to Young Adults with Symptoms of Depression and Anxiety using a Fully Automated Conversational Agent (Woebot): A Randomized Controlled Trial. JMIR Mental Health 4, 2 (2017), e19.Google ScholarCross Ref
- Xiang Gao, Yizhe Zhang, Sungjin Lee, Michel Galley, Chris Brockett, Jianfeng Gao, and Bill Dolan. 2019. Structuring Latent Spaces for Stylized Response Generation. In Proc. EMNLP.Google ScholarCross Ref
- Chulaka Gunasekara, Jonathan K. Kummerfeld, Lazaros Polymenakos, and Walter Lasecki. 2019. DSTC7 task 1: Noetic end-to-end response selection. In Proc. First Workshop on NLP for Conversational AI.Google ScholarCross Ref
- Matthew Henderson, Iñigo Casanueva, Nikola Mrksic, Pei-Hao Su, Tsung-Hsien Wen, and Ivan Vulic. 2019. ConveRT: Efficient and Accurate Conversational Representations from Transformers. CoRR abs/1911.03688(2019). arxiv:1911.03688http://arxiv.org/abs/1911.03688Google Scholar
- Matthew Henderson, Ivan Vulić, Daniela Gerz, I nigo Casanueva, Pawel Budzianowski, Sam Coope, Georgios Spithourakis, Tsung-Hsien Wen, Nikola Mrkšić, and Pei-Hao Su. 2019. Training Neural Response Selection for Task-Oriented Dialogue Systems. In Proc. 57th Annual Meeting of the Association for Computational Linguistics (ACL).Google ScholarCross Ref
- Jing Huang, Qi Li, Yuanyuan Xue, Taoran Cheng, Shuangqing Xu, Jia Jia, and Ling Feng. 2015. TeenChat: A Chatterbot System for Sensing and Releasing Adolescents’ Stress. LNCS 9085(2015), 133–145.Google Scholar
- Masashi Inoue, Ryoko Hanada, Nobuhiro Furuyama, Toshio Irino, Takako Ichinomiya, and Hiroyasu Massaki. 2012. Multimodal Corpus for Psychotherapeutic Situation. In Proc. LREC Workshop on Multimodal Corpora for Machine Learning. 18–21.Google Scholar
- Allen E. Ivey and Mary Bradford Ivey. 2003. Intentional Interviewing and Counseling: Facilitating Client Development in a Multicultural Society. Brooks Cole.Google Scholar
- John Lee, Tianyuan Cai, Wenxiu Xie, and Lam Xing. 2020. A Counselling Corpus in Cantonese. In Proc. Joint Workshop on Spoken Language Technologies for Under-resourced languages (SLTU) and Collaboration and Computing for Under-Resourced Languages (CCURL).Google Scholar
- Yuanchao Liu, Ming Liu, Xiaolong Wang, Limin Wang, and Jingjing Li. 2013. PAL: A Chatterbot System for Answering Domain-specific Questions. In Proc. 51st Annual Meeting of the Association for Computational Linguistics (ACL). 67–72.Google Scholar
- Yinhan Liu, Myle Ott, Naman Goyal, Jingfei Du, Mandar Joshi, Danqi Chen, Omer Levy, Mike Lewis, Luke Zettlemoyer, and Veselin Stoyanov. 2019. Roberta: A robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692(2019).Google Scholar
- G. M. Lucas, J. Gratch, A. King, and L. P. Morency. 2014. It’s Only a Computer: Virtual Humans Increase Willingness to Disclose. Computers in Human Behavior 37 (2014), 94–100.Google ScholarDigital Library
- Yosi Mass, Boaz Carmeli, Haggai Roitman, and David Konopnicki. 2020. Unsupervised FAQ Retrieval with Question Generation and BERT. In Proc. 58th Annual Meeting of the Association for Computational Linguistics (ACL). 55–60.Google ScholarCross Ref
- S. Matthews and V. Yip. 2011. Cantonese: A Comprehensive Grammar. Routledge, New York.Google Scholar
- Clara H. McCreery, Namit Katariya, Anitha Kannan, Manish Chablani, and Xavier Amatriain. 2020. Effective Transfer Learning for Identifying Similar Questions: Matching User Questions to COVID-19 FAQs. In Proc. KDD (Health Day Paper).Google ScholarDigital Library
- Gustavo Penha and Claudia Hauff. 2020. What does BERT know about books, movies and music? Probing BERT for Conversational Recommendation. In Proc. RecSys.Google ScholarDigital Library
- Dan Russell, Letitia Anne Peplau, and Mary Lund Ferguson. 1978. Developing a Measure of Loneliness. Journal of Personality Assessment 42, 3 (1978), 290–294.Google ScholarCross Ref
- I. V. Serban, A. Sordoni, Y. Bengio, A. C. Courville, and J. Pineau. 2016. Building end-to-end dialogue systems using generative hierarchical neural network models. In Proc. AAAI.Google Scholar
- Oriol Vinyals and Quoc V. Le. 2015. A Neural Conversational Model. In Proc. Deep Learning Workshop.Google Scholar
- Taesun Whang, Dongyub Lee, Chanhee Lee, Kisu Yang, Dongsuk Oh, and Heuiseok Lim. 2020. An Effective Domain Adaptive Post-Training Method for BERT in Response Selection. In Proc. Interspeech.Google ScholarCross Ref
- Tak-Sum Wong and John Lee. 2018. Register-sensitive Translation: A Case Study of Mandarin and Cantonese. In Proc. Association for Machine Translation in the Americas (AMTA).Google Scholar
- Douglas G. Wren and Jeri Benson. 2004. Measuring Test Anxiety in Children: Scale Development and Internal Construct Validation. Anxiety, Stress, & Coping: An international Journal 17, 3 (2004), 227–240.Google ScholarCross Ref
- Yu Wu, Wei Wu, Zhoujun Li, and Ming Zhou. 2018. Learning Matching Models with Weak Supervision for Response Selection in Retrieval-based Chatbots. In Proc. 56th Annual Meeting of the Association for Computational Linguistics (ACL).Google ScholarCross Ref
- Yizhe Zhang, Siqi Sun, Michel Galley, Yen-Chun Chen, Chris Brockett, Xiang Gao, Jianfeng Gao, Jingjing Liu, and Bill Dolan. 2019. Dialogpt: Large-scale generative pre-training for conversational response generation. arXiv preprint arXiv:1911.00536(2019).Google Scholar
- Li Zhou, Jianfeng Gao, Di Li, and Heung-Yeung Shum. 2020. The Design and Implementation of XiaoIce, an Empathetic Social Chatbot. Computational Linguistics 46, 1 (2020), 53–93.Google ScholarDigital Library
- Xiangyang Zhou, Lu Li, Daxiang Dong, Yi Liu, Ying Chen, Wayne Xin Zhao, Dianhai Yu, and Hua Wu. 2018. Multi-Turn Response Selection for Chatbots with Deep Attention Matching Network. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). Association for Computational Linguistics, Melbourne, Australia, 1118–1127. https://doi.org/10.18653/v1/P18-1103Google ScholarCross Ref
Recommendations
Loneliness and Anxiety Among Chinese Medical Students: The Mediating Role of Mobile Phone Addiction and the Moderating Role of Gender
The purpose of this study was to explore the relationship between loneliness and anxiety, and the mediating role of mobile phone addiction in this relationship, and whether this mediating role was moderated by gender among Chinese medical students. A ...
Loneliness, parent-child communication and cyberbullying victimization among Spanish youths
Cyberbullying has been recognized as an important risk factor for mental health. Few studies have analyzed relationships between family variables and cyberbullying victimization. This ex post facto study analyze the relationships between loneliness, ...
Cyberbullying, self-esteem, empathy and loneliness
Highlights- Low self-esteem predicts greater cyberbullying victimisation and perpetration.
- ...
AbstractCyberbullying is a unique phenomenon, distinguished from traditional bullying by the speed at which information is distributed, permanence of material and availability of victims. There is however a paucity of research in this area, ...
Comments