SlideShare a Scribd company logo
1 of 12
Download to read offline
UTS CRICOS 00099F
Could Generative AI Augment
Reflection, Deliberation and
Argumentation?
Simon Buckingham Shum
Professor of Learning Informatics &
Director, Connected Intelligence Centre
https://cic.uts.edu.au
15th May 2023
Critical Deliberative Democracy Tech Workshop • 11th Int. Conf. Communities & Technologies
How to support the analysis of these arguments?
https://futureoflife.org/open-letter/pause-giant-ai-experiments/ https://www.dair-institute.org/blog/letter-statement-March2023
challenges
Generate the ArgDown syntax description for the key arguments
Paste the GPT-generated code into the ArgDown web app à Argument Map
GPT-generated Argument Map
(green) Elements classified
by Argumentation Scheme
article à GPT analysis à code à visualization
Claim in the original letter
which is not contested
(green supporting premises)
(white) Claims
and Premises
Questioning GPT on why it added (unrequested)
Argumentation Scheme classifications to (green) nodes
GPT inserts the Critical
Questions in the Argument Tree
(an alternative view in ArgDown to the graph)
Additional step:
Hide the Critical Questions as
an example student activity
Evaluating the Argument Map
X
i
X
X
Correct summary of authors
Hallucination
https://www.reasoninglab.com/patterns-of-argument/argumentation-schemes/waltons-argumentation-schemes/
Fallacy of Fallacy of omission
X
Incorrect term
i
Ad hominem
i “commentary” from Bing
When challenged about a node in the Argument Map, Bing Chat
fabricates a quote from the article, and refuses to back down!
Conclusions (1/2)
Bing Chat (a version of GPT-4) showed the capability to analyse an argumentative article:
• extracted the key claim and underlying premises, summarising them in own words
• generated markdown (ArgDown) showing supporting/challenging relationships
• (without being asked to) attempted to classify some nodes using Walton’s Argumentation Schemes.
Bing Chat also introduced:
• fallacious nodes (incorrect summaries of the authors, and incorrect commentary nodes), links, and
argument classifications (inventing argument types, and/or misclassifying nodes)
This is an exploratory example, and more systematic Argument Mining evaluations are required
Conclusions (2/2)
We’ve argued that embracing imperfection* in tech can be productive if it promotes deeper critical
thinking in learners, e.g., learning by correcting the automated output, or reflecting on questions it asks,
or why it seems wrong. Students can be directed and scaffolded to engage in such activity.
This is permissible in formal education, but may be less attractive to citizens engaged in a policy
deliberation, many of whom lack the internal or external motivation to think that hard.
But assuming future tools give more accurate argument maps/outlines, perhaps we can see use-cases
including:
• assisting facilitators/educators to prepare learning resources for civic deliberations
• assisting very engaged citizens to dissect complex arguments, and perhaps lowering the entry
threshold for others who might otherwise not engage with such structured, critical deliberation
• an article is very different to a multi-author conversation, but we can envisage summarising online
discussions (NB: Teams is starting to summarise topics and actions in meeting transcripts)
For this analysis see https://simon.buckinghamshum.net/2023/05/conversational-genai-for-argument-analysis
* Kitto, K., Buckingham Shum, S., & Gibson, A. (2018). Embracing imperfection in learning analytics. Proceedings 8th International
Conference on Learning Analytics and Knowledge (LAK18), Sydney, AUS. ACM, NY, pp. 451–460. https://doi.org/10.1145/3170358.3170413

More Related Content

Similar to Could Generative AI Augment Reflection, Deliberation and Argumentation?

Guatemala small groups 2 11-01-11
Guatemala small groups 2 11-01-11Guatemala small groups 2 11-01-11
Guatemala small groups 2 11-01-11
marorussell
 
Capstone Project Report GuidelinesThe Capstone Project represent.docx
Capstone Project Report GuidelinesThe Capstone Project represent.docxCapstone Project Report GuidelinesThe Capstone Project represent.docx
Capstone Project Report GuidelinesThe Capstone Project represent.docx
annandleola
 
ATTRIBUTES AND EVALUATION OF DISCUSSION CONTRIBUTIONSDue Date E.docx
ATTRIBUTES AND EVALUATION OF DISCUSSION CONTRIBUTIONSDue Date E.docxATTRIBUTES AND EVALUATION OF DISCUSSION CONTRIBUTIONSDue Date E.docx
ATTRIBUTES AND EVALUATION OF DISCUSSION CONTRIBUTIONSDue Date E.docx
rosemaryralphs52525
 
Discussion And Social Networking Presentation
Discussion And Social Networking PresentationDiscussion And Social Networking Presentation
Discussion And Social Networking Presentation
beth brunk-chavez
 

Similar to Could Generative AI Augment Reflection, Deliberation and Argumentation? (20)

USING CHATGPT TO GENERATE COMPUTER SCIENCE PROBLEM SETS
USING CHATGPT TO GENERATE COMPUTER SCIENCE PROBLEM SETSUSING CHATGPT TO GENERATE COMPUTER SCIENCE PROBLEM SETS
USING CHATGPT TO GENERATE COMPUTER SCIENCE PROBLEM SETS
 
Guatemala small groups 2 11-01-11
Guatemala small groups 2 11-01-11Guatemala small groups 2 11-01-11
Guatemala small groups 2 11-01-11
 
Capstone Project Report GuidelinesThe Capstone Project represent.docx
Capstone Project Report GuidelinesThe Capstone Project represent.docxCapstone Project Report GuidelinesThe Capstone Project represent.docx
Capstone Project Report GuidelinesThe Capstone Project represent.docx
 
anon-technicalintroductiontochatgpt-seda-230214083138-f7be0088.pdf
anon-technicalintroductiontochatgpt-seda-230214083138-f7be0088.pdfanon-technicalintroductiontochatgpt-seda-230214083138-f7be0088.pdf
anon-technicalintroductiontochatgpt-seda-230214083138-f7be0088.pdf
 
A non-technical introduction to ChatGPT - SEDA.pptx
A non-technical introduction to ChatGPT - SEDA.pptxA non-technical introduction to ChatGPT - SEDA.pptx
A non-technical introduction to ChatGPT - SEDA.pptx
 
Community Led Activities
Community Led ActivitiesCommunity Led Activities
Community Led Activities
 
IRJET- Finding Related Forum Posts through Intention-Based Segmentation
IRJET-  	  Finding Related Forum Posts through Intention-Based SegmentationIRJET-  	  Finding Related Forum Posts through Intention-Based Segmentation
IRJET- Finding Related Forum Posts through Intention-Based Segmentation
 
Think out of the box.pdf
Think out of the box.pdfThink out of the box.pdf
Think out of the box.pdf
 
Experience sharing-of-technologist-cum-mgmt-scientist-2013
Experience sharing-of-technologist-cum-mgmt-scientist-2013Experience sharing-of-technologist-cum-mgmt-scientist-2013
Experience sharing-of-technologist-cum-mgmt-scientist-2013
 
ATTRIBUTES AND EVALUATION OF DISCUSSION CONTRIBUTIONSDue Date E.docx
ATTRIBUTES AND EVALUATION OF DISCUSSION CONTRIBUTIONSDue Date E.docxATTRIBUTES AND EVALUATION OF DISCUSSION CONTRIBUTIONSDue Date E.docx
ATTRIBUTES AND EVALUATION OF DISCUSSION CONTRIBUTIONSDue Date E.docx
 
Disruption in TEL is there any other way to go?
Disruption in TEL is there any other way to go?Disruption in TEL is there any other way to go?
Disruption in TEL is there any other way to go?
 
Research Project Management
Research Project ManagementResearch Project Management
Research Project Management
 
Bilton Enabling and Encouraging Use of RIS
Bilton Enabling and Encouraging Use of RISBilton Enabling and Encouraging Use of RIS
Bilton Enabling and Encouraging Use of RIS
 
Writing Research Paper - Tips For Students
Writing Research Paper - Tips For StudentsWriting Research Paper - Tips For Students
Writing Research Paper - Tips For Students
 
ASK - LOST 2.0: A Web - based Tool for Social Tagging of Digital Educational ...
ASK - LOST 2.0: A Web - based Tool for Social Tagging of Digital Educational ...ASK - LOST 2.0: A Web - based Tool for Social Tagging of Digital Educational ...
ASK - LOST 2.0: A Web - based Tool for Social Tagging of Digital Educational ...
 
Research methodology 3-sps
Research methodology  3-spsResearch methodology  3-sps
Research methodology 3-sps
 
Discussion And Social Networking Presentation
Discussion And Social Networking PresentationDiscussion And Social Networking Presentation
Discussion And Social Networking Presentation
 
Bridging the missing middle for al_tversionfinal_14_08_2014
Bridging the missing middle for al_tversionfinal_14_08_2014Bridging the missing middle for al_tversionfinal_14_08_2014
Bridging the missing middle for al_tversionfinal_14_08_2014
 
Beyond the blend: practical approaches to designing fully online learning
Beyond the blend: practical approaches to designing fully online learningBeyond the blend: practical approaches to designing fully online learning
Beyond the blend: practical approaches to designing fully online learning
 
1. introduction to data science —
1. introduction to data science —1. introduction to data science —
1. introduction to data science —
 

More from Simon Buckingham Shum

Deliberative Democracy as a strategy for co-designing university ethics aro...
Deliberative Democracy as a strategy for co-designing university ethics aro...Deliberative Democracy as a strategy for co-designing university ethics aro...
Deliberative Democracy as a strategy for co-designing university ethics aro...
Simon Buckingham Shum
 
March 2021 • 24/7 Instant Feedback on Writing: Integrating AcaWriter into yo...
March 2021 • 24/7 Instant Feedback on Writing: Integrating AcaWriter into yo...March 2021 • 24/7 Instant Feedback on Writing: Integrating AcaWriter into yo...
March 2021 • 24/7 Instant Feedback on Writing: Integrating AcaWriter into yo...
Simon Buckingham Shum
 
24/7 Instant Feedback on Writing: Integrating AcaWriter into your Teaching
24/7 Instant Feedback on Writing: Integrating AcaWriter into your Teaching24/7 Instant Feedback on Writing: Integrating AcaWriter into your Teaching
24/7 Instant Feedback on Writing: Integrating AcaWriter into your Teaching
Simon Buckingham Shum
 
Learning Informatics: AI • Analytics • Accountability • Agency
Learning Informatics: AI • Analytics • Accountability • AgencyLearning Informatics: AI • Analytics • Accountability • Agency
Learning Informatics: AI • Analytics • Accountability • Agency
Simon Buckingham Shum
 
Towards Collaboration Translucence: Giving Meaning to Multimodal Group Data
Towards Collaboration Translucence: Giving Meaning to Multimodal Group DataTowards Collaboration Translucence: Giving Meaning to Multimodal Group Data
Towards Collaboration Translucence: Giving Meaning to Multimodal Group Data
Simon Buckingham Shum
 
Transitioning Education’s Knowledge Infrastructure ICLS 2018
Transitioning Education’s Knowledge Infrastructure ICLS 2018Transitioning Education’s Knowledge Infrastructure ICLS 2018
Transitioning Education’s Knowledge Infrastructure ICLS 2018
Simon Buckingham Shum
 

More from Simon Buckingham Shum (20)

Conversational, generative AI as a cognitive tool for critical thinking
Conversational, generative AI as a cognitive tool for critical thinkingConversational, generative AI as a cognitive tool for critical thinking
Conversational, generative AI as a cognitive tool for critical thinking
 
On the Design of a Writing App offering 24/7 Formative Feedback on Reflective...
On the Design of a Writing App offering 24/7 Formative Feedback on Reflective...On the Design of a Writing App offering 24/7 Formative Feedback on Reflective...
On the Design of a Writing App offering 24/7 Formative Feedback on Reflective...
 
SBS_ISLS2022.pdf
SBS_ISLS2022.pdfSBS_ISLS2022.pdf
SBS_ISLS2022.pdf
 
Is “The Matter With Things” also what’s the matter with Learning Analytics?
Is “The Matter With Things” also what’s the matter with Learning Analytics?Is “The Matter With Things” also what’s the matter with Learning Analytics?
Is “The Matter With Things” also what’s the matter with Learning Analytics?
 
Deliberative Democracy as a strategy for co-designing university ethics aro...
Deliberative Democracy as a strategy for co-designing university ethics aro...Deliberative Democracy as a strategy for co-designing university ethics aro...
Deliberative Democracy as a strategy for co-designing university ethics aro...
 
Knowledge Art or… “Participatory Improvisational DVN”
Knowledge Art or… “Participatory Improvisational DVN”Knowledge Art or… “Participatory Improvisational DVN”
Knowledge Art or… “Participatory Improvisational DVN”
 
March 2021 • 24/7 Instant Feedback on Writing: Integrating AcaWriter into yo...
March 2021 • 24/7 Instant Feedback on Writing: Integrating AcaWriter into yo...March 2021 • 24/7 Instant Feedback on Writing: Integrating AcaWriter into yo...
March 2021 • 24/7 Instant Feedback on Writing: Integrating AcaWriter into yo...
 
ICQE20: Quantitative Ethnography Visualizations as Tools for Thinking
ICQE20: Quantitative Ethnography Visualizations as Tools for ThinkingICQE20: Quantitative Ethnography Visualizations as Tools for Thinking
ICQE20: Quantitative Ethnography Visualizations as Tools for Thinking
 
24/7 Instant Feedback on Writing: Integrating AcaWriter into your Teaching
24/7 Instant Feedback on Writing: Integrating AcaWriter into your Teaching24/7 Instant Feedback on Writing: Integrating AcaWriter into your Teaching
24/7 Instant Feedback on Writing: Integrating AcaWriter into your Teaching
 
Argumentation 101 for Learning Analytics PhDs!
Argumentation 101 for Learning Analytics PhDs!Argumentation 101 for Learning Analytics PhDs!
Argumentation 101 for Learning Analytics PhDs!
 
Learning Informatics: AI • Analytics • Accountability • Agency
Learning Informatics: AI • Analytics • Accountability • AgencyLearning Informatics: AI • Analytics • Accountability • Agency
Learning Informatics: AI • Analytics • Accountability • Agency
 
AI/Data Analytics (AIDA): Key concepts, examples & risks
AI/Data Analytics (AIDA): Key concepts, examples & risksAI/Data Analytics (AIDA): Key concepts, examples & risks
AI/Data Analytics (AIDA): Key concepts, examples & risks
 
Learning Analytics as Educational Knowledge Infrastructure
Learning Analytics as Educational Knowledge InfrastructureLearning Analytics as Educational Knowledge Infrastructure
Learning Analytics as Educational Knowledge Infrastructure
 
Towards Collaboration Translucence: Giving Meaning to Multimodal Group Data
Towards Collaboration Translucence: Giving Meaning to Multimodal Group DataTowards Collaboration Translucence: Giving Meaning to Multimodal Group Data
Towards Collaboration Translucence: Giving Meaning to Multimodal Group Data
 
Knowledge Art - MDSI Guest Lecture - 1st May 2019
Knowledge Art - MDSI Guest Lecture - 1st May 2019Knowledge Art - MDSI Guest Lecture - 1st May 2019
Knowledge Art - MDSI Guest Lecture - 1st May 2019
 
UX/LX for PLSA: Workshop Welcome
UX/LX for PLSA: Workshop WelcomeUX/LX for PLSA: Workshop Welcome
UX/LX for PLSA: Workshop Welcome
 
Educational Data Scientists: A Scarce Breed
Educational Data Scientists: A Scarce BreedEducational Data Scientists: A Scarce Breed
Educational Data Scientists: A Scarce Breed
 
Transitioning Education’s Knowledge Infrastructure ICLS 2018
Transitioning Education’s Knowledge Infrastructure ICLS 2018Transitioning Education’s Knowledge Infrastructure ICLS 2018
Transitioning Education’s Knowledge Infrastructure ICLS 2018
 
Embracing Imperfection in Learning Analytics
Embracing Imperfection in Learning AnalyticsEmbracing Imperfection in Learning Analytics
Embracing Imperfection in Learning Analytics
 
What is “Learning Analytics” and Why a Schools Day?
What is “Learning Analytics” and Why a Schools Day?What is “Learning Analytics” and Why a Schools Day?
What is “Learning Analytics” and Why a Schools Day?
 

Recently uploaded

1029 - Danh muc Sach Giao Khoa 10 . pdf
1029 -  Danh muc Sach Giao Khoa 10 . pdf1029 -  Danh muc Sach Giao Khoa 10 . pdf
1029 - Danh muc Sach Giao Khoa 10 . pdf
QucHHunhnh
 
An Overview of Mutual Funds Bcom Project.pdf
An Overview of Mutual Funds Bcom Project.pdfAn Overview of Mutual Funds Bcom Project.pdf
An Overview of Mutual Funds Bcom Project.pdf
SanaAli374401
 
Activity 01 - Artificial Culture (1).pdf
Activity 01 - Artificial Culture (1).pdfActivity 01 - Artificial Culture (1).pdf
Activity 01 - Artificial Culture (1).pdf
ciinovamais
 

Recently uploaded (20)

Key note speaker Neum_Admir Softic_ENG.pdf
Key note speaker Neum_Admir Softic_ENG.pdfKey note speaker Neum_Admir Softic_ENG.pdf
Key note speaker Neum_Admir Softic_ENG.pdf
 
How to Give a Domain for a Field in Odoo 17
How to Give a Domain for a Field in Odoo 17How to Give a Domain for a Field in Odoo 17
How to Give a Domain for a Field in Odoo 17
 
Measures of Central Tendency: Mean, Median and Mode
Measures of Central Tendency: Mean, Median and ModeMeasures of Central Tendency: Mean, Median and Mode
Measures of Central Tendency: Mean, Median and Mode
 
This PowerPoint helps students to consider the concept of infinity.
This PowerPoint helps students to consider the concept of infinity.This PowerPoint helps students to consider the concept of infinity.
This PowerPoint helps students to consider the concept of infinity.
 
1029 - Danh muc Sach Giao Khoa 10 . pdf
1029 -  Danh muc Sach Giao Khoa 10 . pdf1029 -  Danh muc Sach Giao Khoa 10 . pdf
1029 - Danh muc Sach Giao Khoa 10 . pdf
 
Grant Readiness 101 TechSoup and Remy Consulting
Grant Readiness 101 TechSoup and Remy ConsultingGrant Readiness 101 TechSoup and Remy Consulting
Grant Readiness 101 TechSoup and Remy Consulting
 
microwave assisted reaction. General introduction
microwave assisted reaction. General introductionmicrowave assisted reaction. General introduction
microwave assisted reaction. General introduction
 
Basic Civil Engineering first year Notes- Chapter 4 Building.pptx
Basic Civil Engineering first year Notes- Chapter 4 Building.pptxBasic Civil Engineering first year Notes- Chapter 4 Building.pptx
Basic Civil Engineering first year Notes- Chapter 4 Building.pptx
 
Mattingly "AI & Prompt Design: Structured Data, Assistants, & RAG"
Mattingly "AI & Prompt Design: Structured Data, Assistants, & RAG"Mattingly "AI & Prompt Design: Structured Data, Assistants, & RAG"
Mattingly "AI & Prompt Design: Structured Data, Assistants, & RAG"
 
Mattingly "AI & Prompt Design: The Basics of Prompt Design"
Mattingly "AI & Prompt Design: The Basics of Prompt Design"Mattingly "AI & Prompt Design: The Basics of Prompt Design"
Mattingly "AI & Prompt Design: The Basics of Prompt Design"
 
Ecological Succession. ( ECOSYSTEM, B. Pharmacy, 1st Year, Sem-II, Environmen...
Ecological Succession. ( ECOSYSTEM, B. Pharmacy, 1st Year, Sem-II, Environmen...Ecological Succession. ( ECOSYSTEM, B. Pharmacy, 1st Year, Sem-II, Environmen...
Ecological Succession. ( ECOSYSTEM, B. Pharmacy, 1st Year, Sem-II, Environmen...
 
Mixin Classes in Odoo 17 How to Extend Models Using Mixin Classes
Mixin Classes in Odoo 17  How to Extend Models Using Mixin ClassesMixin Classes in Odoo 17  How to Extend Models Using Mixin Classes
Mixin Classes in Odoo 17 How to Extend Models Using Mixin Classes
 
An Overview of Mutual Funds Bcom Project.pdf
An Overview of Mutual Funds Bcom Project.pdfAn Overview of Mutual Funds Bcom Project.pdf
An Overview of Mutual Funds Bcom Project.pdf
 
ICT Role in 21st Century Education & its Challenges.pptx
ICT Role in 21st Century Education & its Challenges.pptxICT Role in 21st Century Education & its Challenges.pptx
ICT Role in 21st Century Education & its Challenges.pptx
 
Measures of Dispersion and Variability: Range, QD, AD and SD
Measures of Dispersion and Variability: Range, QD, AD and SDMeasures of Dispersion and Variability: Range, QD, AD and SD
Measures of Dispersion and Variability: Range, QD, AD and SD
 
APM Welcome, APM North West Network Conference, Synergies Across Sectors
APM Welcome, APM North West Network Conference, Synergies Across SectorsAPM Welcome, APM North West Network Conference, Synergies Across Sectors
APM Welcome, APM North West Network Conference, Synergies Across Sectors
 
Unit-V; Pricing (Pharma Marketing Management).pptx
Unit-V; Pricing (Pharma Marketing Management).pptxUnit-V; Pricing (Pharma Marketing Management).pptx
Unit-V; Pricing (Pharma Marketing Management).pptx
 
Z Score,T Score, Percential Rank and Box Plot Graph
Z Score,T Score, Percential Rank and Box Plot GraphZ Score,T Score, Percential Rank and Box Plot Graph
Z Score,T Score, Percential Rank and Box Plot Graph
 
Activity 01 - Artificial Culture (1).pdf
Activity 01 - Artificial Culture (1).pdfActivity 01 - Artificial Culture (1).pdf
Activity 01 - Artificial Culture (1).pdf
 
Application orientated numerical on hev.ppt
Application orientated numerical on hev.pptApplication orientated numerical on hev.ppt
Application orientated numerical on hev.ppt
 

Could Generative AI Augment Reflection, Deliberation and Argumentation?

  • 1. UTS CRICOS 00099F Could Generative AI Augment Reflection, Deliberation and Argumentation? Simon Buckingham Shum Professor of Learning Informatics & Director, Connected Intelligence Centre https://cic.uts.edu.au 15th May 2023 Critical Deliberative Democracy Tech Workshop • 11th Int. Conf. Communities & Technologies
  • 2. How to support the analysis of these arguments? https://futureoflife.org/open-letter/pause-giant-ai-experiments/ https://www.dair-institute.org/blog/letter-statement-March2023 challenges
  • 3. Generate the ArgDown syntax description for the key arguments
  • 4. Paste the GPT-generated code into the ArgDown web app à Argument Map
  • 5. GPT-generated Argument Map (green) Elements classified by Argumentation Scheme article à GPT analysis à code à visualization Claim in the original letter which is not contested (green supporting premises) (white) Claims and Premises
  • 6. Questioning GPT on why it added (unrequested) Argumentation Scheme classifications to (green) nodes
  • 7. GPT inserts the Critical Questions in the Argument Tree (an alternative view in ArgDown to the graph)
  • 8. Additional step: Hide the Critical Questions as an example student activity
  • 9. Evaluating the Argument Map X i X X Correct summary of authors Hallucination https://www.reasoninglab.com/patterns-of-argument/argumentation-schemes/waltons-argumentation-schemes/ Fallacy of Fallacy of omission X Incorrect term i Ad hominem i “commentary” from Bing
  • 10. When challenged about a node in the Argument Map, Bing Chat fabricates a quote from the article, and refuses to back down!
  • 11. Conclusions (1/2) Bing Chat (a version of GPT-4) showed the capability to analyse an argumentative article: • extracted the key claim and underlying premises, summarising them in own words • generated markdown (ArgDown) showing supporting/challenging relationships • (without being asked to) attempted to classify some nodes using Walton’s Argumentation Schemes. Bing Chat also introduced: • fallacious nodes (incorrect summaries of the authors, and incorrect commentary nodes), links, and argument classifications (inventing argument types, and/or misclassifying nodes) This is an exploratory example, and more systematic Argument Mining evaluations are required
  • 12. Conclusions (2/2) We’ve argued that embracing imperfection* in tech can be productive if it promotes deeper critical thinking in learners, e.g., learning by correcting the automated output, or reflecting on questions it asks, or why it seems wrong. Students can be directed and scaffolded to engage in such activity. This is permissible in formal education, but may be less attractive to citizens engaged in a policy deliberation, many of whom lack the internal or external motivation to think that hard. But assuming future tools give more accurate argument maps/outlines, perhaps we can see use-cases including: • assisting facilitators/educators to prepare learning resources for civic deliberations • assisting very engaged citizens to dissect complex arguments, and perhaps lowering the entry threshold for others who might otherwise not engage with such structured, critical deliberation • an article is very different to a multi-author conversation, but we can envisage summarising online discussions (NB: Teams is starting to summarise topics and actions in meeting transcripts) For this analysis see https://simon.buckinghamshum.net/2023/05/conversational-genai-for-argument-analysis * Kitto, K., Buckingham Shum, S., & Gibson, A. (2018). Embracing imperfection in learning analytics. Proceedings 8th International Conference on Learning Analytics and Knowledge (LAK18), Sydney, AUS. ACM, NY, pp. 451–460. https://doi.org/10.1145/3170358.3170413