Opening Up Minds: Engaging Dialogue Generated From Argument Maps
Lead Research Organisation:
The Open University
Department Name: Faculty of Sci, Tech, Eng & Maths (STEM)
Abstract
The idea is to design a "dialogue system" interface to existing databases of the arguments surrounding controversial topics such as "Should the United Kingdom remain a member of the European Union?" or "Should all humans be vegan?". In particular, a user can have a "Moral Maze" style chat with the dialogue system.
"Moral Maze" is a longrunning popular BBC 4 Radio programme in which a panel discusses a controversial topic with the help of witnesses and a host who chairs the conversation. The dialogue system consists of a panel of Argumentation Bots (ArguBots) who present arguments for or against the topic under discussion (the pro and con ArguBots), a host ArguBot and a witness ArguBot (that can provide detailed evidence). The user is invited to join the panel and voice their views on the topic under discussion. Thus the user can explore what they thought and what others thought about the controversial topic.
An important part of the projects will be to evaluate the effects on people's appreciation of the complexity of debate and attendant ability to comprehend the world from other people's point of view or perspective.
"Moral Maze" is a longrunning popular BBC 4 Radio programme in which a panel discusses a controversial topic with the help of witnesses and a host who chairs the conversation. The dialogue system consists of a panel of Argumentation Bots (ArguBots) who present arguments for or against the topic under discussion (the pro and con ArguBots), a host ArguBot and a witness ArguBot (that can provide detailed evidence). The user is invited to join the panel and voice their views on the topic under discussion. Thus the user can explore what they thought and what others thought about the controversial topic.
An important part of the projects will be to evaluate the effects on people's appreciation of the complexity of debate and attendant ability to comprehend the world from other people's point of view or perspective.
Planned Impact
The impact plans for this project are described in detail in the Academic Beneficiaries part of this JeS form and the Pathways to impact document. Here we enumerate (1) the beneficiaries that are detailed in those sections and (2) how they will benefit:
- NLP research community: Answering this proposal's research questions will deliver insights into argumentative dialogue from real dialogue data, including ways to learn, from that data, dialogue strategies that facilitate global properties of the dialogue (such as stimulating open-mindedness).
- Argumentation and Debating technologies research community: The current research will offer new NLP-based technologies for enhancing human argumentation.
- XAI research community: Much of the work in this area is on technical tools for analysing the operation of Machine Learning-based systems. The current work could potentially contribute ways of communicating such analyses to human users.
- General public: The ArguBot demonstrator which will allow members of the public to explore controversial topics from a range of perspectives. Outreach events that take place during the project to receive discuss, with the public, the use,implications and ethics of the proposed ArguBot technology.
- Dialogue systems & NLP industry: Theories, tools and data sets for developing argumentation bots and relevant component NLP algorithms.
- NLP research community: Answering this proposal's research questions will deliver insights into argumentative dialogue from real dialogue data, including ways to learn, from that data, dialogue strategies that facilitate global properties of the dialogue (such as stimulating open-mindedness).
- Argumentation and Debating technologies research community: The current research will offer new NLP-based technologies for enhancing human argumentation.
- XAI research community: Much of the work in this area is on technical tools for analysing the operation of Machine Learning-based systems. The current work could potentially contribute ways of communicating such analyses to human users.
- General public: The ArguBot demonstrator which will allow members of the public to explore controversial topics from a range of perspectives. Outreach events that take place during the project to receive discuss, with the public, the use,implications and ethics of the proposed ArguBot technology.
- Dialogue systems & NLP industry: Theories, tools and data sets for developing argumentation bots and relevant component NLP algorithms.
People |
ORCID iD |
Paul Piwek (Principal Investigator) |
Publications
Amidei J.
(2021)
QTMM2012c+: A Queryable Empirically-grounded Resource of Dialogue with Argumentation
in CEUR Workshop Proceedings
Brand CO
(2022)
Using dialogues to increase positive attitudes towards COVID-19 vaccines in a vaccine-hesitant UK population.
in Royal Society open science
Farag Y
(2023)
Opening up Minds with Argumentative Dialogues
Farag Y
(2022)
Opening up Minds with Argumentative Dialogues
Farag Y.
(2022)
Opening up Minds with Argumentative Dialogues
in Findings of the Association for Computational Linguistics: EMNLP 2022
Farag Y.
(2022)
Opening up Minds with Argumentative Dialogues
Description | The project is still ongoing with the final main study currently being completed, however, preliminary results so far, reported in Farag et al. (2022), suggests that conversations with a chatbot on controversial topics can positively affect open-mindedness of the human interlocutor. Where open-mindedness concerns the ability to understand the arguments and claims that around a debate, including those one doesn't agree with. |
Exploitation Route | Tools and activities that can help people with developing an open-minded mindset. |
Sectors | Digital/Communication/Information Technologies (including Software),Education |
URL | http://mcs.open.ac.uk/pp2464/Opening_Up_Minds/ |
Description | EPSRC CASE (DTP conversion) studentship |
Amount | £35,000 (GBP) |
Funding ID | Project reference 2646305 of EP/T518165/1 |
Organisation | Toshiba Research Europe Ltd |
Sector | Private |
Country | United Kingdom |
Start | 02/2022 |
End | 01/2026 |
Title | Supplementary-material-A-Queryable-Empirically-grounded-Resource-of-Dialogue-with-Argumentation |
Description | This repository contains the supplementary material for the paper: Jacopo Amidei, Paul Piwek and Svetlana Stoyanchev, QTMM2012c+: A Queryable Empirically-grounded Resource of Dialogue with Argumentation, 5th Workshop on Advances in Argumentation in Artificial Intelligence, November 29, 2021. |
Type Of Material | Database/Collection of data |
Year Produced | 2021 |
Provided To Others? | Yes |
Impact | The dataset is being used to develop models for an argumentative chatbot, or ArguBot. |
URL | https://github.com/jacopoamidei/Supplementary-material-A-Queryable-Empirically-grounded-Resource-of-... |
Description | Cambridge CS Opening Up Minds project partner |
Organisation | University of Cambridge |
Department | Faculty of Computer Science and Technology |
Country | United Kingdom |
Sector | Academic/University |
PI Contribution | The Open University is lead partner of the project. |
Collaborator Contribution | The team at Cambridge is responsible for the linked project https://gow.epsrc.ukri.org/NGBOViewGrant.aspx?GrantRef=EP/T023414/1 |
Impact | Farag et al. (2022) |
Start Year | 2021 |
Description | Sheffield Psychology Opening Up Minds project partner |
Organisation | University of Sheffield |
Department | Department of Psychology |
Country | United Kingdom |
Sector | Academic/University |
PI Contribution | The Open University is lead research organisation for the project. |
Collaborator Contribution | The linked project at the University of Sheffield in the Department of Psychology is https://gow.epsrc.ukri.org/NGBOViewGrant.aspx?GrantRef=EP/T023554/1 |
Impact | Farag et al. (2022) |
Start Year | 2021 |
Description | Toshiba - Industry partner of the Opening Up Minds project |
Organisation | Toshiba Research Europe Ltd |
Department | Cambridge Research Laboratory - Toshiba |
Country | United Kingdom |
Sector | Private |
PI Contribution | The project is led by the Open University and the team at the Open University is responsible for Work Package 1 - Creating resources for coherent multi-party argumentative dialogue. |
Collaborator Contribution | Time of research engineer to actively support the project by co-supervising project PDRA (weekly, 2 hours), collaboration on publications, conferences and outreach events as well as hiring of contractor to develop and support platform for Wizard-of-Oz data collection. |
Impact | Amidei et al. (2021); Farag et al. (2022) |
Start Year | 2021 |
Description | ArguBots: A brief introduction video for also for the BT STEM in Action: Robotics day (British Science Week 2022) |
Form Of Engagement Activity | Engagement focused website, blog or social media channel |
Part Of Official Scheme? | No |
Geographic Reach | International |
Primary Audience | Public/other audiences |
Results and Impact | The world is getting more polarised. This video explores how ArguBots may help open up our minds to different points of view. |
Year(s) Of Engagement Activity | 2022 |
URL | https://atadastral.co.uk/bsw/video/ou-argubots/ |
Description | Interview for Episode 39 of the Boundless podcast |
Form Of Engagement Activity | A broadcast e.g. TV/radio/film/podcast (other than news/press) |
Part Of Official Scheme? | No |
Geographic Reach | International |
Primary Audience | Public/other audiences |
Results and Impact | Paul Piwek talked with Richard Foster-Fletcher about the Opening Up Minds project in Episode 39 of the Boundless podcast. |
Year(s) Of Engagement Activity | 2020 |
URL | https://boundlesspodcast.co.uk/episode/ep37-dr-paul-piwek-senior-lecturer-in-computing-open-universi... |
Description | Poster presentation at Royal Society event on Cognitive artificial intelligence. |
Form Of Engagement Activity | Participation in an activity, workshop or similar |
Part Of Official Scheme? | No |
Geographic Reach | International |
Primary Audience | Other audiences |
Results and Impact | Poster presentation which led to contacts and follow-up discussion with event participants. |
Year(s) Of Engagement Activity | 2022 |
URL | http://mcs.open.ac.uk/pp2464/Opening_Up_Minds/OUM%20-%20Cognitive%20AI%20event%20-%20poster%20-%20on... |
Description | Project presentation at the Deliberation for Good (D4G) workshop in Cambridge |
Form Of Engagement Activity | A talk or presentation |
Part Of Official Scheme? | No |
Geographic Reach | International |
Primary Audience | Professional Practitioners |
Results and Impact | The first edition of the Deliberation4Good workshop brought together experts in existing and emerging technologies of argumentative communication, to explore how the old can inform the new and how the new can augment the old. We are gathering people from psychology, social, political and computer science to provide a platform for them to collaborate and share their research, towards answering the moonshot question: "How can people with diverging views be supported to successfully communicate and negotiate?" The programme including a project presentation of the Opening Up Minds project. The workshop was also supported organisationally by the Opening Up Minds team. |
Year(s) Of Engagement Activity | 2022 |
URL | https://www.delibot.xyz/deliberation4good/ |
Description | Virtual Live Q&A session at the BT British Science Week Robotics event |
Form Of Engagement Activity | Engagement focused website, blog or social media channel |
Part Of Official Scheme? | No |
Geographic Reach | International |
Primary Audience | Schools |
Results and Impact | Participation in British Science Week 'STEM in Action: Robotics' live Q/A (which was also made available as recording), hosted by BT, engaging with questions from school children/classes across the UK about questions related to AI in General and ArguBots in particular. The event to took place in March and that month alone there were >4000 visitors. There was enthusiastic engagement from the schools during the Q&A as well as follow up questions that were answered later offline. |
Year(s) Of Engagement Activity | 2022 |
URL | https://atadastral.co.uk/bsw/robotics/ |