SME-in-the-loop: Interaction Preferences when Supervising Bots in Human-AI Communities
Authors: 
Zahra Ashktorab, Michael Desmond, James M. Johnson, Qian Pan, Casey Dugan, Michelle Brachman, Carolina SpinaAuthors Info & Claims
Zahra Ashktorab, Michael Desmond, James M. Johnson, Qian Pan, Casey Dugan, Michelle Brachman, Carolina SpinaAuthors Info & ClaimsPages 2281 - 2303
Abstract
Subject matter experts play an important role in customer support communities by responding to user queries. Some communities have adopted chatbots in addition to SMEs to address commonly asked questions. Yet, SME-bot interactions, particularly teaching paradigms between SMEs and bots remain understudied. We investigate human-AI machine teaching interactions in a scenario-based study (n=48). Participants selected their preferred teaching method in simulated community interactions with a consumer, an SME, and an AI Bot. We investigated preferences across three interactions: demonstration (Showing), preference elicitation (Sorting), and labeling (Categorization). Participants preferred the Showing interaction, followed by Sorting and Categorizing. Participants changed their preferences from lower-effort interactions when considering downstream outcomes. Users considered the community’s perception of interactions between the bot and the SME, specifically transparency of learning outcome, orientation of the feedback, querying the bot and disruptiveness of the interaction. We discuss implications for our findings for teaching interactions in human-AI communities.
References
[1]
Pieter Abbeel and Andrew Y Ng. 2004. Apprenticeship learning via inverse reinforcement learning. In Proceedings of the twenty-first international conference on Machine learning. 1.
[2]
Ahmed Al Maimani and Anne Roudaut. 2017. Frozen Suit: Designing a Changeable Stiffness Suit and Its Application to Haptic Games. In Proceedings of the 2017 CHI Conference on Human Factors in Computing Systems (Denver, Colorado, USA) (CHI ’17). Association for Computing Machinery, New York, NY, USA, 2440–2448. https://doi.org/10.1145/3025453.3025655
[3]
Saeed Alahmari, Dmitry Goldgof, Lawrence Hall, Palak Dave, Hady Ahmady Phoulady, and Peter Mouton. 2018. Iterative deep learning based unbiased stereology with human-in-the-loop. In 2018 17th IEEE International Conference on Machine Learning and Applications (ICMLA). IEEE, 665–670.
[4]
Adam Alami and Andrzej Wąsowski. 2019. Affiliated participation in open source communities. In 2019 ACM/IEEE International Symposium on Empirical Software Engineering and Measurement (ESEM). IEEE, 1–11.
[5]
Sara Alqaidi, Waad Alharbi, and Omaima Almatrafi. 2021. A support system for formal college students: A case study of a community-based app augmented with a chatbot. In 2021 19th International Conference on Information Technology Based Higher Education and Training (ITHET). IEEE, 01–05.
[6]
Saleema Amershi, Dan Weld, Mihaela Vorvoreanu, Adam Fourney, Besmira Nushi, Penny Collisson, Jina Suh, Shamsi Iqbal, Paul N Bennett, Kori Inkpen, 2019. Guidelines for human-AI interaction. In Proceedings of the 2019 chi conference on human factors in computing systems. 1–13.
[7]
Kushal Arora, Kurt Shuster, Sainbayar Sukhbaatar, and Jason Weston. 2022. Director: Generator-classifiers for supervised language modeling. arXiv preprint arXiv:2206.07694 (2022).
[8]
Zahra Ashktorab, Mohit Jain, Q Vera Liao, and Justin D Weisz. 2019. Resilient chatbots: Repair strategy preferences for conversational breakdowns. In Proceedings of the 2019 CHI conference on human factors in computing systems. 1–12.
[9]
Sandeep Avula, Gordon Chadwick, Jaime Arguello, and Robert Capra. 2018. Searchbots: User engagement with chatbots during collaborative search. In Proceedings of the 2018 conference on human information interaction & retrieval. 52–61.
[10]
Dina Babushkina and Athanasios Votsis. 2022. Disruption, technology and the question of (artificial) identity. AI and Ethics 2, 4 (2022), 611–622.
[11]
Mehdi Bahrami and Wei-Peng Chen. 2019. WATAPI: composing web API specification from API documentations through an intelligent and interactive annotation tool. In 2019 IEEE International Conference on Big Data (Big Data). IEEE, 4573–4578.
[12]
Gilles Bailly, Antti Oulasvirta, Timo Kötzing, and Sabrina Hoppe. 2013. Menuoptimizer: Interactive optimization of menu systems. In Proceedings of the 26th annual ACM symposium on User interface software and technology. 331–342.
[13]
Michael Bain and Claude Sammut. 1995. A Framework for Behavioural Cloning. In Machine Intelligence 15. 103–129.
[14]
Erdem Bıyık, Malayandi Palan, Nicholas C Landolfi, Dylan P Losey, and Dorsa Sadigh. 2019. Asking easy questions: A user-friendly approach to active reward learning. arXiv preprint arXiv:1910.04365 (2019).
[15]
Maya Cakmak and Andrea L Thomaz. 2012. Designing robot learners that ask good questions. In 2012 7th ACM/IEEE International Conference on Human-Robot Interaction (HRI). IEEE, 17–24.
[16]
Heloisa Candello, Claudio Pinhanez, Mauro Pichiliani, Paulo Cavalin, Flavio Figueiredo, Marisa Vasconcelos, and Haylla Do Carmo. 2019. The effect of audiences on the user experience with conversational interfaces in physical spaces. In Proceedings of the 2019 CHI Conference on Human Factors in Computing Systems. 1–13.
[17]
Heloisa Candello, Mairieli Wessel, and Claudio Pinhanez. 2020. Unveiling Practices and Challenges of Machine Teachers of Customer Service Conversational Systems. In Proceedings of the 2nd Conference on Conversational User Interfaces (Bilbao, Spain) (CUI ’20). Association for Computing Machinery, New York, NY, USA, Article 32, 2 pages. https://doi.org/10.1145/3405755.3406173
[18]
Liwei Chan, Yi-Chi Liao, George B Mo, John J Dudley, Chun-Lien Cheng, Per Ola Kristensson, and Antti Oulasvirta. 2022. Investigating Positive and Negative Qualities of Human-in-the-Loop Optimization for Designing Interaction Techniques. In CHI Conference on Human Factors in Computing Systems. 1–14.
[19]
Preetha Chatterjee, Kostadin Damevski, Lori Pollock, Vinay Augustine, and Nicholas A Kraft. 2019. Exploratory study of slack q&a chats as a mining source for software engineering tools. In 2019 IEEE/ACM 16th International Conference on Mining Software Repositories (MSR). IEEE, 490–501.
[20]
Paul F Christiano, Jan Leike, Tom Brown, Miljan Martic, Shane Legg, and Dario Amodei. 2017. Deep reinforcement learning from human preferences. Advances in neural information processing systems 30 (2017).
[21]
Kevin Crowston and James Howison. 2006. Assessing the health of open source communities. Computer 39, 5 (2006), 89–91.
[22]
Regina Dittrich, Brian Francis, Reinhold Hatzinger, and Walter Katzenbeisser. 2007. A paired comparison approach for the analysis of sets of Likert-scale responses. Statistical Modelling 7, 1 (2007), 3–28.
[23]
Nicolas Ducheneaut. 2005. Socialization in an open source software community: A socio-technical analysis. Computer Supported Cooperative Work (CSCW) 14, 4 (2005), 323–368.
[24]
Jerry Alan Fails and D Olsen. 2003. Image processing with crayons. Ph.D. Dissertation. Brigham Young University. Department of Computer Science.
[25]
Amir Feder, Danny Vainstein, Roni Rosenfeld, Tzvika Hartman, Avinatan Hassidim, and Yossi Matias. 2020. Active deep learning to detect demographic traits in free-form clinical notes. Journal of Biomedical Informatics 107 (2020), 103436.
[26]
Jasper Feine, Stefan Morana, and Alexander Maedche. 2020. Designing Interactive Chatbot Development Systems. In ICIS.
[27]
Donghui Feng, Erin Shaw, Jihie Kim, and Eduard Hovy. 2006. An intelligent discussion-bot for answering student queries in threaded discussions. In Proceedings of the 11th international conference on Intelligent user interfaces. 171–177.
[28]
Rebecca Fiebrink and Perry R Cook. 2010. The Wekinator: a system for real-time, interactive machine learning in music. In Proceedings of The Eleventh International Society for Music Information Retrieval Conference (ISMIR 2010)(Utrecht), Vol. 3.
[29]
Spence Green, Jeffrey Heer, and Christopher D Manning. 2015. Natural language translation at the intersection of AI and HCI. Commun. ACM 58, 9 (2015), 46–53.
[30]
Braden Hancock, Antoine Bordes, Pierre-Emmanuel Mazare, and Jason Weston. 2019. Learning from dialogue after deployment: Feed yourself, chatbot!arXiv preprint arXiv:1901.05415 (2019).
[31]
Jeffrey T Hancock, Mor Naaman, and Karen Levy. 2020. AI-mediated communication: Definition, research agenda, and ethical considerations. Journal of Computer-Mediated Communication 25, 1 (2020), 89–100.
[32]
Geert Hofstede. 2009. Geert Hofstede cultural dimensions. (2009).
[33]
Gert Jan Hofstede, Catholijn M Jonker, and Tim Verwaart. 2008. Long-term orientation in trade. In Complexity and Artificial Markets. Springer, 107–119.
[34]
Marie-Claire Jenkins, Richard Churchill, Stephen Cox, and Dan Smith. 2007. Analysis of user interaction with service oriented chatbot systems. In International conference on human-computer interaction. Springer, 76–83.
[35]
Ashish Kapoor, Bongshin Lee, Desney Tan, and Eric Horvitz. 2012. Performance and preferences: Interactive refinement of machine learning procedures. In Twenty-Sixth AAAI Conference on Artificial Intelligence.
[36]
Beomsu Kim, Seokjun Seo, Seungju Han, Enkhbayar Erdenee, and Buru Chang. 2021. Distilling the knowledge of large-scale generative models into retrieval models for efficient open-domain conversation. arXiv preprint arXiv:2108.12582 (2021).
[37]
Soomin Kim, Jinsu Eun, Changhoon Oh, Bongwon Suh, and Joonhwan Lee. 2020. Bot in the bunch: Facilitating group chat discussion by improving efficiency and participation with a chatbot. In Proceedings of the 2020 CHI Conference on Human Factors in Computing Systems. 1–13.
[38]
Pallavi Koppol, Henny Admoni, and Reid G Simmons. 2021. Interaction Considerations in Learning from Humans. In IJCAI. 283–291.
[39]
Carlene Lebeuf, Margaret-Anne Storey, and Alexey Zagalsky. 2017. How software developers mitigate collaboration friction with chatbots. arXiv preprint arXiv:1702.07011 (2017).
[40]
Minha Lee, Sander Ackermans, Nena Van As, Hanwen Chang, Enzo Lucas, and Wijnand IJsselsteijn. 2019. Caring for Vincent: a chatbot for self-compassion. In Proceedings of the 2019 CHI Conference on Human Factors in Computing Systems. 1–13.
[41]
Min Kyung Lee, Sara Kiesler, Jodi Forlizzi, Siddhartha Srinivasa, and Paul Rybski. 2010. Gracefully mitigating breakdowns in robotic services. In Human-Robot Interaction (HRI), 2010 5th ACM/IEEE International Conference on. IEEE, 203–210.
[42]
Adam Eric Leeper, Kaijen Hsiao, Matei Ciocarlie, Leila Takayama, and David Gossow. 2012. Strategies for human-in-the-loop robotic grasping. In Proceedings of the seventh annual ACM/IEEE international conference on Human-Robot Interaction. 1–8.
[43]
Q Vera Liao, Muhammed Mas-ud Hussain, Praveen Chandar, Matthew Davis, Yasaman Khazaeni, Marco Patricio Crasso, Dakuo Wang, Michael Muller, N Sadat Shami, and Werner Geyer. 2018. All work and no play?. In Proceedings of the 2018 CHI Conference on Human Factors in Computing Systems. 1–13.
[44]
Bing Liu and Sahisnu Mazumder. 2021. Lifelong and continual learning dialogue systems: learning during conversation. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 35. 15058–15063.
[45]
Mansoureh Maadi, Hadi Akbarzadeh Khorshidi, and Uwe Aickelin. 2021. A review on human–AI interaction in machine learning and insights for medical applications. International journal of environmental research and public health 18, 4 (2021), 2121.
[46]
Winter Mason and Siddharth Suri. 2012. Conducting behavioral research on Amazon’s Mechanical Turk. Behavior research methods 44, 1 (2012), 1–23.
[47]
Alexander Tobias Neumann, Peter de Lange, and Ralf Klamma. 2019. Collaborative creation and training of social bots in learning communities. In 2019 IEEE 5th International Conference on Collaboration and Internet Computing (CIC). IEEE, 11–19.
[48]
Long Ouyang, Jeffrey Wu, Xu Jiang, Diogo Almeida, Carroll Wainwright, Pamela Mishkin, Chong Zhang, Sandhini Agarwal, Katarina Slama, Alex Ray, 2022. Training language models to follow instructions with human feedback. Advances in Neural Information Processing Systems 35 (2022), 27730–27744.
[49]
Nataliya Pankratova and Nadezhda Nedashkovskaya. 2015. Methods of evaluation and improvement of consistency of expert pairwise comparison judgements. International Journal «Information Theories and Applications 22, 3 (2015), 203–223.
[50]
Brandon J Perry, Yanlin Guo, Rebecca Atadero, and John W van de Lindt. 2020. Streamlined bridge inspection system utilizing unmanned aerial vehicles (UAVs) and machine learning. Measurement 164 (2020), 108048.
[51]
Marco Roccetti, Giovanni Delnevo, Luca Casini, and Paola Salomoni. 2020. A cautionary tale for machine learning design: why we still need human-assisted big data analysis. Mobile Networks and Applications 25, 3 (2020), 1075–1083.
[52]
Dorsa Sadigh, Anca D Dragan, Shankar Sastry, and Sanjit A Seshia. 2017. Active preference-based learning of reward functions.
[53]
Saiph Savage, Andres Monroy-Hernandez, and Tobias Höllerer. 2016. Botivist: Calling volunteers to action using online bots. In Proceedings of the 19th ACM Conference on Computer-Supported Cooperative Work & Social Computing. 813–822.
[54]
Joseph Seering, Juan Pablo Flores, Saiph Savage, and Jessica Hammer. 2018. The social roles of bots: evaluating impact of bots on discussions in online communities. Proceedings of the ACM on Human-Computer Interaction 2, CSCW (2018), 1–29.
[55]
Joseph Seering, Michal Luria, Geoff Kaufman, and Jessica Hammer. 2019. Beyond dyadic interactions: Considering chatbots as community members. In Proceedings of the 2019 CHI Conference on Human Factors in Computing Systems. 1–13.
[56]
Joseph Seering, Michal Luria, Connie Ye, Geoff Kaufman, and Jessica Hammer. 2020. It takes a village: integrating an adaptive chatbot into an online gaming community. In Proceedings of the 2020 chi conference on human factors in computing systems. 1–13.
[57]
Marcos Serrano, Anne Roudaut, and Pourang Irani. 2017. Visual Composition of Graphical Elements on Non-Rectangular Displays. In Proceedings of the 2017 CHI Conference on Human Factors in Computing Systems (Denver, Colorado, USA) (CHI ’17). Association for Computing Machinery, New York, NY, USA, 4405–4416. https://doi.org/10.1145/3025453.3025677
[58]
Burr Settles. 2009. Active learning literature survey. (2009).
[59]
Muhammad Yusril Helmi Setyawan, Rolly Maulana Awangga, and Safif Rafi Efendi. 2018. Comparison of multinomial naive bayes algorithm and logistic regression for intent classification in chatbot. In 2018 International Conference on Applied Engineering (ICAE). IEEE, 1–5.
[60]
Kurt Shuster, Jing Xu, Mojtaba Komeili, Da Ju, Eric Michael Smith, Stephen Roller, Megan Ung, Moya Chen, Kushal Arora, Joshua Lane, 2022. Blenderbot 3: a deployed conversational agent that continually learns to responsibly engage. arXiv preprint arXiv:2208.03188 (2022).
[61]
Emanuel Stoeckli, Christian Dremel, Falk Uebernickel, and Walter Brenner. 2020. How affordances of chatbots cross the chasm between social and traditional enterprise systems. Electronic Markets 30, 2 (2020), 369–403.
[62]
Emanuel Stoeckli, Falk Uebernickel, and Walter Brenner. 2018. Exploring affordances of slack integrations and their actualization within enterprises-towards an understanding of how chatbots create value. (2018).
[63]
Sylvie Studente and Stephen Ellis. 2020. Enhancing the Online Student Experience Through Creating Learning Communities—The Benefits of Chatbots in Higher Education. In Tertiary Online Teaching and Learning. Springer, 25–33.
[64]
Ed Summers and Ricardo Punzalan. 2017. Bots, seeds and people: Web archives as infrastructure. In Proceedings of the 2017 ACM conference on computer supported cooperative work and social computing. 821–834.
[65]
Andrea L Thomaz and Cynthia Breazeal. 2008. Teachable robots: Understanding human teaching behavior to build more effective robot learners. Artificial Intelligence 172, 6-7 (2008), 716–737.
[66]
Kashyap Todi, Daryl Weir, and Antti Oulasvirta. 2016. Sketchplore: Sketch and explore with a layout optimiser. In Proceedings of the 2016 ACM Conference on Designing Interactive Systems. 543–555.
[67]
Heather Turner and David Firth. 2012. Bradley-Terry models in R: the BradleyTerry2 package. Journal of Statistical Software 48 (2012), 1–21.
[68]
R Vedapradha, Ravi Hariharan, Rajan Shivakami, 2019. Artificial intelligence: A technological prototype in recruitment. Journal of Service Science and Management 12, 03 (2019), 382.
[69]
Jing Wang, Anindya Ghose, and Panos Ipeirotis. 2012. Bonus, disclosure, and choice: what motivates the creation of high-quality paid reviews?. In ICIS. Citeseer.
[70]
Xupeng Wen, Yifeng Niu, Chang Wang, Lizhen Wu, Yuting Zhu, and Dong Yin. 2018. Human-in-the-loop multi-task tracking improved by interactive learning. In 2018 Chinese Automation Congress (CAC). IEEE, 2289–2294.
[71]
Mairieli Wessel, Bruno Mendes De Souza, Igor Steinmacher, Igor S Wiese, Ivanilton Polato, Ana Paula Chaves, and Marco A Gerosa. 2018. The power of bots: Characterizing and understanding bots in oss projects. Proceedings of the ACM on Human-Computer Interaction 2, CSCW (2018), 1–19.
[72]
Jason E Weston. 2016. Dialog-based language learning. Advances in Neural Information Processing Systems 29 (2016).
[73]
Yiwei Yang, Eser Kandogan, Yunyao Li, Prithviraj Sen, and Walter S Lasecki. 2019. A study on interaction in human-in-the-loop machine learning for text analytics. In IUI Workshops.
[74]
Beste F Yuksel, Soo Jung Kim, Seung Jung Jin, Joshua Junhee Lee, Pooyan Fazli, Umang Mathur, Vaishali Bisht, Ilmi Yoon, Yue-Ting Siu, and Joshua A Miele. 2020. Increasing video accessibility for visually impaired users with human-in-the-loop machine learning. In Extended Abstracts of the 2020 CHI Conference on Human Factors in Computing Systems. 1–9.
Index Terms
- SME-in-the-loop: Interaction Preferences when Supervising Bots in Human-AI Communities
Recommendations
Guidelines for Human-AI Interaction
CHI '19: Proceedings of the 2019 CHI Conference on Human Factors in Computing SystemsAdvances in artificial intelligence (AI) frame opportunities and challenges for user interface design. Principles for human-AI interaction have been discussed in the human-computer interaction community for over two decades, but more study and ...
Explainable Active Learning (XAL): Toward AI Explanations as Interfaces for Machine Teachers
CSCWThe wide adoption of Machine Learning (ML) technologies has created a growing demand for people who can train ML models. Some advocated the term "machine teacher'' to refer to the role of people who inject domain knowledge into ML models. This "teaching''...
Human-AI Interaction and AI Avatars
HCI International 2023 – Late Breaking PapersAbstractHuman-Computer Interaction has been evolving rapidly with the advancement of artificial intelligence and metaverse. Human-AI Interaction is a new area in Human-Computer Interaction. In this paper, we look at AI avatars, which are human-like ...
Comments
Information & Contributors
Information
Published In
July 2023
2717 pages
ISBN:9781450398930
DOI:10.1145/3563657
Copyright © 2023 Owner/Author.
This work is licensed under a Creative Commons Attribution International 4.0 License.
Sponsors
Publisher
Association for Computing Machinery
New York, NY, United States
Publication History
Published: 10 July 2023
Check for updates
Author Tags
Qualifiers
- Research-article
- Research
- Refereed limited
Conference
DIS '23
Sponsor:
Acceptance Rates
Overall Acceptance Rate 1,158 of 4,684 submissions, 25%
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 508Total Downloads
- Downloads (Last 12 months)375
- Downloads (Last 6 weeks)48
Reflects downloads up to 03 Sep 2024
Other Metrics
Citations
View Options
View options
View or Download as a PDF file.
PDFeReader
View online with eReader.
eReaderHTML Format
View this article in HTML Format.
HTML FormatGet Access
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign in