Look Who’s Talking

Towards Engaging Long-Term Interactions with Conversational Agents

About Our Project

Look Who’s Talking is an interdisciplinary collaboration between three universities from the Netherlands, funded by the Dutch Research Council (NWO), working together to develop and test a new generation of conversational agents (chatbots) which can engage with humans in long-term motivational interactions. The ​ main aim of this project is to create and field-test chatbots designed to develop and foster long-term engaging and human-like conversations with humans for two technologically and linguistically diverse domains (smoking cessation and promotion of safe sex, respectively) based on recent insights from artificial intelligence, computational linguistics, humanities, and social sciences with expertise from our societal partners. Additionally, we will study if and how people build up a social relationship with such more advanced chatbots, and what the ethical implications of communication with such health chatbots are.

Chatbots

Roby the smoking cessation bot

Roby’s main function is getting to know smokers’ behaviour by a conversational assessment. It also provides personalized normative feedback and discusses with smokers potential reasons to quit smoking. We “trained” Roby with motivational interviewing techniques and skills, to be a helpful addition in motivating smokers to quit!

Read more »

MISH the sexual health bot

MISH is a text-based conversational agent that primarily makes use of motivational interviewing (MI) techniques to promote sexual health. This prototype has been designed to address condom use. While the intended target population is heterosexual couples in a steady relationship, initial testing will be conducted with individuals.

Read more »

HyLECA development framework

HyLECA is an open-source framework designed for the development of long-term engaging controlled conversational agents. HyLECA’s dialogue manager employs a hybrid architecture, combining rule-based methods for controlled dialogue flows with retrieval-based and generation-based approaches to enhance the utterance variability and flexibility.

Read more »

Publications

2024

Basar, E., Hendrickx, I., Krahmer, E., de Bruijn, G., & Bosse, T. (2024).  To What Extent Are Large Language Models Capable of Generating Substantial Reflections for Motivational Interviewing Counseling Chatbots? A Human Evaluation. In Proceedings of the 1st Human-Centered Large Language Modeling Workshop, pages 41-52. Association for Computational Linguistics.

He, L., Basar, E., Krahmer, E., Wiers, R., & Antheunis, M. (2024). Effectiveness and user experience of a smoking cessation chatbot: A mixed-methods study comparing motivational interviewing and confrontational counseling. In Journal of Medical Internet Research.

He, L., Braggar, A., Basar, E., Krahmer, E., Antheunis, M., & Bosse, T. (2024). Exploring User Engagement Through an Interaction Lens: What Textual Cues Can Tell Us about Human-Chatbot Interactions. In Proceedings of the 6th Conference on Conversational User Interfaces (CUI’24). ACM.

Balaji, D., de Bruijn, G. J., Bosse, T., Ischen, C., van der Goot, M., & Wiers, R. (2024). Designing a Couples-Based Conversational Agent to Promote Safe Sex in New, Young Couples: A User-Centred Design Approach. In Proceedings of the 6th Conference on Conversational User Interfaces (CUI’24). ACM.

2023

Basar, E., Balaji, D., He, L., Hendrickx, I., Krahmer, E., de Bruijn, G., & Bosse, T. (2023). HyLECA: A Framework for Developing Hybrid Long-term Engaging Controlled Conversational Agents. In Proceedings of the 5th Conference on Conversational User Interfaces (CUI’23). ACM.

2022

He, L., Balaji, D., Wiers, R. W., Antheunis, M. L., & Krahmer, E. (2022). Effectiveness and acceptability of conversational agents for smoking cessation: a systematic review and meta-analysis. In Nicotine & Tobacco Research, 25(7):1241–1250.

Balaji, D., He, L., Giani, S., Bosse, T., Wiers, R., & de Bruijn, G. J. (2022). Effectiveness and acceptability of conversational agents for sexual health promotion: a systematic review and meta-analysis. In Sexual health19(5), 391-405.

He, L., Basar, E., Wiers, R. W., Antheunis, M., & Krahmer, E. (2022). Can chatbots help to motivate smoking cessation? A study on the effectiveness of motivational interviewing on engagement and therapeutic alliance. In BMC Public Health, 22(1), 1-14.

Basar, E., Hendrickx, I., Krahmer, E., de Bruijn, G., & Bosse, T. (2022). Hints of Independence in a Pre-scripted World: On Controlled Usage of Open-domain Language Models for Chatbots in Highly Sensitive Domains.  In Proceedings of the 14th International Conference on Agents and Artificial Intelligence – Volume 1, pages 401-407.    

2021

Hendrickx, I., Cena, F., Basar, E., Di Caro, L., Kunneman, F., Musi, E., Musto, C., Rapp, A. & van Waterschoot, J. (2021). Towards a new generation of personalized intelligent conversational agents. In Adjunct Proceedings of the 29th ACM Conference on User Modeling, Adaptation and Personalization (pp. 373-374).

Our Team

Look Who’s Talking research group consists of many experts from multiple disciplines assuming different roles in our project.

Supervisory Team

Prof. Dr. Tibor Bosse

Radboud University

Social artificial intelligence,
theory of mind

Prof. Dr. Gert-Jan de Bruijn

University of Antwerp

Health technology,
behaviour change

Prof. Dr. Emiel Krahmer

Tilburg University

Human-machine interaction, natural language processing, conversational agents, evaluation

Prof. Dr. Marjolijn Antheunis

Tilburg University

Computer-mediated communication

Dr. Margot van der Goot

University of Amsterdam

Human-machine communication,
conversational agents

Dr. Iris Hendrickx

Radboud University

Natural language processing,
conversational agents

Prof. Dr. Reinout Wiers

University of Amsterdam

Developmental psychopathology,
cognitive processes in addiction, intervention development

Prof. Dr. Pim Haselager

Radboud University

Philosophy of mind,
applied ethics

PhD Candidates

Divyaa Balaji, M.Sc.

University of Amsterdam

Human Factors

Focus on communication about promoting safe sex behaviour

Erkan Basar, M.Sc.

Radboud University

Artificial Intelligence

Focus on computational dialogue modelling

Linwei He, M.Sc.

Tilburg University

Health Communication

Focus on communication about smoking cessation

Societal & Industrial Partners

Drs. Erwin Fisser

SOA Aids Nederland

Societal partner; safe sex promotion

Prof. Dr. Marc Willemsen

Trimbos Instituut

Societal partner; smoking cessation and public health

Dr. Sander Wubben

Flow.ai

Industrial partner; practical design of chatbots

Collaborating Experts

Prof. Dr. Elisabeth Andre

Augsburg University

Computational dialogue modelling

Prof. Dr. Ehud Reiter

University of Aberdeen

Natural language generation

Prof. Dr. Rob Ruiter

Maastricht University

Health communication and health promotion

Prof. Dr. Robert West

University College London

Addiction and behaviour change

Our Partners

This project is partly financed by the Dutch Research Council (NWO) with project number 406.DI.19.054

Get in touch

If you have any questions or just want to say hello, please don’t hesitate to contact us.