A Framework for Explainable Multi-purpose Virtual Assistants: A Nutrition-Focused Case Study
Authors: 
Berk Buzcu, Yvan Pannatier, Reyhan Aydoğan, Michael Ignaz Schumacher, Jean-Paul Calbimonte, Davide CalvaresiAuthors Info & Claims
Pages 58 - 78
Abstract
Existing agent-based chatbot frameworks need seamless mechanisms to include explainable dialogic engines within the contextual flow. To this end, this paper presents a set of novel modules within the EREBOTS agent-based framework for chatbot development, including dialog-based plug-and-play custom algorithms, agnostic back/front ends, and embedded interactive explainable engines that can manage human feedback at run time. The framework has been employed to implement an explainable agent-based interactive food recommender system. The latter has been tested with 44 participants, who followed a nutrition recommendation interaction series, generating explained recommendations and suggestions, which were, in general, well received. Additionally, the participants provided important insights to be included in future work.
References
[1]
Adamopoulou, E., Moussiades, L.: An overview of chatbot technology, pp. 373–383 (2020).
[2]
Anjomshoae, S., Najjar, A., Calvaresi, D., Främling, K.: Explainable agents and robots: results from a systematic literature review. In: AAMAS, Montreal, Canada, 13–17 May 2019, pp. 1078–1088 (2019)
[3]
Arsenijevic, U., Jovic, M.: Artificial intelligence marketing: chatbots. In: 2019 International Conference on Artificial Intelligence: Applications and Innovations (IC-AIAI), pp. 19–193 (2019).
[4]
AWS, A.: Amazon lex. https://aws.amazon.com/lex/. Accessed Mar 2024
[5]
Aydoğan R and Jonker CM Hadfi R, Aydoğan R, Ito T, and Arisaka R A survey of decision support mechanisms for negotiation Recent Advances in Agent-Based Negotiation: Applications and Competition Challenges 2023 Singapore Springer Nature Singapore 30-51
[6]
Ayub, M., Ghazanfar, M.A., Maqsood, M., Saleem, A.: A Jaccard base similarity measure to improve performance of CF based recommender systems, pp. 1–6 (2018)
[7]
Bondevik, J.N., Bennin, K.E., Önder Babur, Ersch, C.: A systematic review on food recommender systems. Expert Syst. Appl. 238, 122166 (2024)., https://www.sciencedirect.com/science/article/pii/S0957417423026684
[8]
Buzcu B et al. Towards interactive explanation-based nutrition virtual coaching systems Auton. Agent. Multi-Agent Syst. 2024 38 1 5
[9]
Calvaresi, D., et al.: EREBOTS: privacy-compliant agent-based platform for multi-scenario personalized health-assistant chatbots. Electronics 10(6) (2021)., https://www.mdpi.com/2079-9292/10/6/666
[10]
Calvaresi D et al. Ethical and legal considerations for nutrition virtual coaches AI and ethics 2023 3 4 1313-1340
[11]
Calvaresi D et al. Calvaresi D, Najjar A, Winikoff M, Främling K, et al. Expectation: personalized explainable artificial intelligence for decentralized agents with heterogeneous knowledge Explainable and Transparent AI and Multi-Agent Systems 2021 Cham Springer 331-343
[12]
Calvaresi, D., Eggenschwiler, S., Calbimonte, J.P., Manzo, G., Schumacher, M.: A personalized agent-based chatbot for nutritional coaching. In: IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology, pp. 682–687. WI-IAT 2021, Association for Computing Machinery, New York, NY, USA (2022)., https://doi.org/10.1145/3486622.3493992
[13]
Chung K and Park RC Chatbot-based heathcare service with a knowledge base for cloud computing Cluster Comput. 2018 22 1 1925-1937
[14]
Contreras, V., et al.: A dexire for extracting propositional rules from neural networks via binarization. Electronics 11(24) (2022)., https://www.mdpi.com/2079-9292/11/24/4171
[15]
Felfernig, A., Burke, R.: Constraint-based recommender systems: echnologies and research issues. In: ACM International Conference Proceeding Series, p. 3 (2008).
[16]
Følstad A, Nordheim CB, and Bjørkli CA Bodrunova SS What makes users trust a chatbot for customer service? an exploratory interview study Internet Science 2018 Cham Springer 194-208
[17]
Freyne, J., Berkovsky, S.: Intelligent food planning: personalized recipe recommendation. In: Proceedings of the 15th International Conference on Intelligent User Interfaces, pp. 321–324. IUI 2010, Association for Computing Machinery, New York, NY, USA (2010).
[18]
Google: Google dialogflow. https://www.citedrive.com/overleaf. Accessed Mar 2024
[19]
Harbola, A.: Design and implementation of an AI chatbot for customer service. Math. Stat. Eng. Appl. 70, 1295–1303 (2021).
[20]
Hoffman, R.R., Mueller, S.T., Klein, G., Litman, o.: Metrics for explainable AI: challenges and prospects. arXiv:1812.04608 (2018)
[21]
Hulstijn, J., Tchappi, I., Najjar, A., Aydoğan, R.: Metrics for evaluating explainable recommender systems. In: AAMAS, EXTRAAMAS 2023, London, England, 29 May 2023. Springer (2023).
[22]
Belen Saglam R, Nurse JRC, and Hodges D Stephanidis C, Antona M, and Ntoa S Privacy concerns in chatbot interactions: when to trust and when to worry HCI International 2021 - Posters 2021 Cham Springer 391-399
[23]
Lee, H., Kang, J., Yeo, J.: Medical specialty recommendations by an artificial intelligence chatbot on a smartphone: development and deployment (preprint). J. Med. Internet Res. 23 (2021).
[24]
Magnini, M., Ciatto, G., Omicini, A.: On the design of PSyKI: a platform for symbolic knowledge injection into sub-symbolic predictors. In: Explainable and Transparent AI and Multi-Agent Systems: 4th International Workshop, EXTRAAMAS 2022, Virtual Event, 9–10 May 2022, Revised Selected Papers, pp. 90–108. Springer-Verlag, Berlin, Heidelberg (2022).
[25]
Majumder, B.P., Li, S., Ni, J., McAuley, J.J.: Generating personalized recipes from historical user preferences. CoRR abs/1909.00105 arXiv:1909.00105 (2019)
[26]
Mendes Samagaio Á, Lopes Cardoso H, and Ribeiro D Marreiros G, Melo FS, Lau N, Lopes Cardoso H, and Reis LP A Chatbot for recipe recommendation and preference modeling Progress in Artificial Intelligence 2021 Cham Springer 389-402
[27]
Meyer, J.G., et al.: ChatGpt and large language models in academia: opportunities and challenges. BioData Min. 16(1), 20 (2023).
[28]
Montagna, S., Mariani, S., Pengo, M.F.: A chatbot-based recommendation framework for hypertensive patients. In: 2023 IEEE 36th International Symposium on Computer-Based Medical Systems (CBMS), pp. 730–733 (2023).
[29]
Nadarzynski, T., Miles, O., Cowie, A., Ridge, D.: Acceptability of artificial intelligence (AI)-led chatbot services in healthcare: a mixed-methods study. Digital Health 5, 2055207619871808 (2019). 31467682
[30]
OpenAI: Chatgpt. https://chat.openai.com/. ADccessed Mar 2024
[31]
Ornab AM, Chowdhury S, and Toa SB Jain LC, E. Balas V, and Johri P An empirical analysis of collaborative filtering algorithms for building a food recommender system Data and Communication Networks 2019 Singapore Springer 147-157
[32]
Prasetyo, P.K., Achananuparp, P., Lim, E.P.: Foodbot: a goal-oriented just-in-time healthy eating interventions chatbot. In: Proceedings of the 14th EAI International Conference on Pervasive Computing Technologies for Healthcare, p. 436–439. PervasiveHealth 2020, Association for Computing Machinery, New York, NY, USA (2021).
[33]
Shinde, N.V., Akhade, A., Bagad, P., Bhavsar, H., Wagh, S., Kamble, A.: Healthcare Chatbot system using artificial intelligence. In: 2021 5th International Conference on Trends in Electronics and Informatics (ICOEI), pp. 1–8 (2021).
[34]
Singh, J., Joesph, M., Abdul Jabbar, K.: Rule-based Chabot for student enquiries. J. Phys. Conf. Ser. 1228, 012060 (2019).
[35]
Singh, S., Beniwal, H.: A survey on near-human conversational agents. J. King Saud Univ. Comput. Inform. Sci. 34 (2021).
[36]
Teng, C.Y., Lin, Y.R., Adamic, L.A.: Recipe recommendation using ingredient networks. In: Proceedings of the 4th Annual ACM Web Science Conference, pp. 298–307. WebSci 2012, Association for Computing Machinery, New York, NY, USA (2012).
[37]
Thongyoo P, Anantapanya P, Jamsri P, and Chotipant S Luo Y A personalized food recommendation chatbot system for diabetes patients Cooperative Design, Visualization, and Engineering 2020 Cham Springer 19-28
[38]
van der Waa J, Nieuwburg E, Cremers A, and Neerincx M Evaluating XAI: a comparison of rule-based and example-based explanations Artif. Intell. 2021 291
[39]
Wei, C., Yu, Z., Fong, S.: How to build a chatbot: chatbot framework and its capabilities. In: Proceedings of the 2018 10th International Conference on Machine Learning and Computing, p. 369–373. ICMLC 2018, Association for Computing Machinery, New York, NY, USA (2018)., https://doi.org/10.1145/3195106.3195169
Index Terms
- A Framework for Explainable Multi-purpose Virtual Assistants: A Nutrition-Focused Case Study
Index terms have been assigned to the content through auto-classification.
Recommendations
A Grounded Interaction Protocol for Explainable Artificial Intelligence
AAMAS '19: Proceedings of the 18th International Conference on Autonomous Agents and MultiAgent SystemsExplainable Artificial Intelligence (XAI) systems need to include an explanation model to communicate the internal decisions, behaviours and actions to the interacting humans. Successful explanation involves both cognitive and social processes. In this ...
An Argumentative Framework for Generating Explainable Group Recommendations
UMAP '23 Adjunct: Adjunct Proceedings of the 31st ACM Conference on User Modeling, Adaptation and PersonalizationIn the context of group recommender systems, explanations strategies have been proposed to improve recommendations perceived fairness, consensus, satisfaction, and to help the group members in the decision-making process. In general, such explanations ...
Counterfactual Explainable Recommendation
CIKM '21: Proceedings of the 30th ACM International Conference on Information & Knowledge ManagementBy providing explanations for users and system designers to facilitate better understanding and decision making, explainable recommendation has been an important research problem. In this paper, we propose Counterfactual Explainable Recommendation (...
Comments
Please enable JavaScript to view thecomments powered by Disqus.Information & Contributors
Information
Published In
May 2024
246 pages
ISBN:978-3-031-70073-6
DOI:10.1007/978-3-031-70074-3
© The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.
Publisher
Springer-Verlag
Berlin, Heidelberg
Publication History
Published: 25 September 2024
Author Tags
Qualifiers
- Article
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 0Total Downloads
- Downloads (Last 12 months)0
- Downloads (Last 6 weeks)0
Reflects downloads up to 25 Nov 2024
Other Metrics
Citations
View Options
View options
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign in