TorfsBot or Not? Evaluating User Perception on Imitative Text Generation (CLIN33)

T
Thomas WintersPhD Researcher em KU Leuven
Slides: thomaswinters.be/clin
Professor Canon Law & Former Rector KU Leuven
Fully-automated Twitterbot imitating Rik Torfs
Trained on his tweets & columns
Launched in 2016
Algorithm 1: Markov Chain (Interpolated 35-gram)
1. Counts frequency of word after previous words
in tweets & columns van Rik Torfs
“gevolgd door”
4: een
2: zijn
1: iemand
1: acht
Beste,
2. Takes start words and repeatedly predicts
Algorithm 2: Dynamic template
1. Take random tweet and a random column lines
2. Change tweet key words with words from
column with same part-of-speech
Markov chain 35% more interactions
than dynamic template
(17K interactions on 8K tweets over from June 2017 to June 2023)
Previous work: Winters, T. (2019).Generating PhilosophicalStatements using InterpolatedMarkovModels and Dynamic Templates.
31st EuropeanSummer Schoolin Logic, Language and InformationStudent Session Proceedings, 181–189.
Funny fail?
Believable parody?
Tweets daily poll with random tweet from either Rik Torfs or TorfsBot
602 polls
47K votes total (avg 79/poll)
71% correct votes
87% correct majority
68 TorfsBot success
12 Rik Torfs fails
TorfsBot or Not? Evaluating User Perception on Imitative Text Generation (CLIN33)
TorfsBot or Not? Evaluating User Perception on Imitative Text Generation (CLIN33)
Slightly positively
correlated
(0.11 for log(interactions) with %votes)
Little difference
between algorithms
More interactions
~ more believable
Weirdly more so
for Rik than bot
TorfsBot or Not? Evaluating User Perception on Imitative Text Generation (CLIN33)
#1
TorfsBot or Not? Evaluating User Perception on Imitative Text Generation (CLIN33)
#2
TorfsBot or Not? Evaluating User Perception on Imitative Text Generation (CLIN33)
#3
TorfsBot or Not? Evaluating User Perception on Imitative Text Generation (CLIN33)
TorfsBot or Not? Evaluating User Perception on Imitative Text Generation (CLIN33)
#4
TorfsBot or Not? Evaluating User Perception on Imitative Text Generation (CLIN33)
De laatste TorfsBot Or Not!
#5
TorfsBot or Not? Evaluating User Perception on Imitative Text Generation (CLIN33)
Slides: thomaswinters.be/clin
1 de 26

Recomendados

Prompt engineering: De kunst van het leren communiceren met AI por
Prompt engineering: De kunst van het leren communiceren met AIPrompt engineering: De kunst van het leren communiceren met AI
Prompt engineering: De kunst van het leren communiceren met AIThomas Winters
102 visualizações54 slides
Wetenschapscommunicatie on steroids por
Wetenschapscommunicatie on steroidsWetenschapscommunicatie on steroids
Wetenschapscommunicatie on steroidsThomas Winters
53 visualizações40 slides
Prompt engineering: de kunst van het leren communiceren met AI (Juni 2023) por
Prompt engineering: de kunst van het leren communiceren met AI (Juni 2023)Prompt engineering: de kunst van het leren communiceren met AI (Juni 2023)
Prompt engineering: de kunst van het leren communiceren met AI (Juni 2023)Thomas Winters
199 visualizações55 slides
Hoe werken tekstgenerators? (Special Guest in Lieven Scheire's AI voorstelling) por
Hoe werken tekstgenerators? (Special Guest in Lieven Scheire's AI voorstelling)Hoe werken tekstgenerators? (Special Guest in Lieven Scheire's AI voorstelling)
Hoe werken tekstgenerators? (Special Guest in Lieven Scheire's AI voorstelling)Thomas Winters
1.1K visualizações13 slides
Pret met Creatieve Computers por
Pret met Creatieve ComputersPret met Creatieve Computers
Pret met Creatieve ComputersThomas Winters
34 visualizações26 slides
Hoe leer je computers humor? por
Hoe leer je computers humor?Hoe leer je computers humor?
Hoe leer je computers humor?Thomas Winters
445 visualizações42 slides

Mais conteúdo relacionado

Mais de Thomas Winters

AI als creatieve partner por
AI als creatieve partnerAI als creatieve partner
AI als creatieve partnerThomas Winters
320 visualizações78 slides
De magie achter afbeeldingsgenerators por
De magie achter afbeeldingsgeneratorsDe magie achter afbeeldingsgenerators
De magie achter afbeeldingsgeneratorsThomas Winters
139 visualizações46 slides
Computational Humor: Can a machine have a sense of humor (December 2022) por
Computational Humor: Can a machine have a sense of humor (December 2022)Computational Humor: Can a machine have a sense of humor (December 2022)
Computational Humor: Can a machine have a sense of humor (December 2022)Thomas Winters
69 visualizações56 slides
How can AI be a creative partner for PR & marketing? por
How can AI be a creative partner for PR & marketing?How can AI be a creative partner for PR & marketing?
How can AI be a creative partner for PR & marketing?Thomas Winters
120 visualizações49 slides
Beter leren praten met Artificiële Intelligentie por
Beter leren praten met Artificiële IntelligentieBeter leren praten met Artificiële Intelligentie
Beter leren praten met Artificiële IntelligentieThomas Winters
693 visualizações70 slides
Computational Humor: Can a machine have a sense of humor (2022) por
Computational Humor: Can a machine have a sense of humor (2022)Computational Humor: Can a machine have a sense of humor (2022)
Computational Humor: Can a machine have a sense of humor (2022)Thomas Winters
106 visualizações57 slides

Mais de Thomas Winters(17)

AI als creatieve partner por Thomas Winters
AI als creatieve partnerAI als creatieve partner
AI als creatieve partner
Thomas Winters320 visualizações
De magie achter afbeeldingsgenerators por Thomas Winters
De magie achter afbeeldingsgeneratorsDe magie achter afbeeldingsgenerators
De magie achter afbeeldingsgenerators
Thomas Winters139 visualizações
Computational Humor: Can a machine have a sense of humor (December 2022) por Thomas Winters
Computational Humor: Can a machine have a sense of humor (December 2022)Computational Humor: Can a machine have a sense of humor (December 2022)
Computational Humor: Can a machine have a sense of humor (December 2022)
Thomas Winters69 visualizações
How can AI be a creative partner for PR & marketing? por Thomas Winters
How can AI be a creative partner for PR & marketing?How can AI be a creative partner for PR & marketing?
How can AI be a creative partner for PR & marketing?
Thomas Winters120 visualizações
Beter leren praten met Artificiële Intelligentie por Thomas Winters
Beter leren praten met Artificiële IntelligentieBeter leren praten met Artificiële Intelligentie
Beter leren praten met Artificiële Intelligentie
Thomas Winters693 visualizações
Computational Humor: Can a machine have a sense of humor (2022) por Thomas Winters
Computational Humor: Can a machine have a sense of humor (2022)Computational Humor: Can a machine have a sense of humor (2022)
Computational Humor: Can a machine have a sense of humor (2022)
Thomas Winters106 visualizações
TorfsBotOrNot @ Nerdland Festival por Thomas Winters
TorfsBotOrNot @ Nerdland FestivalTorfsBotOrNot @ Nerdland Festival
TorfsBotOrNot @ Nerdland Festival
Thomas Winters143 visualizações
Creative AI for Improv Theatre por Thomas Winters
Creative AI for Improv TheatreCreative AI for Improv Theatre
Creative AI for Improv Theatre
Thomas Winters144 visualizações
Computational Humor: Can a machine have a sense of humor? (2020) por Thomas Winters
Computational Humor: Can a machine have a sense of humor? (2020)Computational Humor: Can a machine have a sense of humor? (2020)
Computational Humor: Can a machine have a sense of humor? (2020)
Thomas Winters123 visualizações
Humor Workshop: Hoe schrijf je satire? (KU Leugen) por Thomas Winters
Humor Workshop: Hoe schrijf je satire? (KU Leugen)Humor Workshop: Hoe schrijf je satire? (KU Leugen)
Humor Workshop: Hoe schrijf je satire? (KU Leugen)
Thomas Winters266 visualizações
Survival of the Wittiest: Evolving Satire with Language Models por Thomas Winters
Survival of the Wittiest: Evolving Satire with Language ModelsSurvival of the Wittiest: Evolving Satire with Language Models
Survival of the Wittiest: Evolving Satire with Language Models
Thomas Winters83 visualizações
Discovering Textual Structures: Generative Grammar Induction using Template T... por Thomas Winters
Discovering Textual Structures: Generative Grammar Induction using Template T...Discovering Textual Structures: Generative Grammar Induction using Template T...
Discovering Textual Structures: Generative Grammar Induction using Template T...
Thomas Winters79 visualizações
Dutch Humor Detection by Generating Negative Examples por Thomas Winters
Dutch Humor Detection by Generating Negative ExamplesDutch Humor Detection by Generating Negative Examples
Dutch Humor Detection by Generating Negative Examples
Thomas Winters84 visualizações
Modelling Mutually Interactive Fictional Character Conversational Agents por Thomas Winters
Modelling Mutually Interactive Fictional Character Conversational AgentsModelling Mutually Interactive Fictional Character Conversational Agents
Modelling Mutually Interactive Fictional Character Conversational Agents
Thomas Winters76 visualizações
Generating Philosophical Statements using Interpolated Markov Models and Dyna... por Thomas Winters
Generating Philosophical Statements using Interpolated Markov Models and Dyna...Generating Philosophical Statements using Interpolated Markov Models and Dyna...
Generating Philosophical Statements using Interpolated Markov Models and Dyna...
Thomas Winters77 visualizações
DeepStochLog: Neural Stochastic Logic Programming por Thomas Winters
DeepStochLog: Neural Stochastic Logic ProgrammingDeepStochLog: Neural Stochastic Logic Programming
DeepStochLog: Neural Stochastic Logic Programming
Thomas Winters208 visualizações
TorfsBot: Een geautomatiseerde Rik Torfs por Thomas Winters
TorfsBot: Een geautomatiseerde Rik TorfsTorfsBot: Een geautomatiseerde Rik Torfs
TorfsBot: Een geautomatiseerde Rik Torfs
Thomas Winters392 visualizações

Último

predicting-m3-devopsconMunich-2023.pptx por
predicting-m3-devopsconMunich-2023.pptxpredicting-m3-devopsconMunich-2023.pptx
predicting-m3-devopsconMunich-2023.pptxTier1 app
10 visualizações24 slides
Quality Engineer: A Day in the Life por
Quality Engineer: A Day in the LifeQuality Engineer: A Day in the Life
Quality Engineer: A Day in the LifeJohn Valentino
10 visualizações18 slides
Winter Projects GDSC IITK por
Winter Projects GDSC IITKWinter Projects GDSC IITK
Winter Projects GDSC IITKSahilSingh368445
416 visualizações60 slides
Introduction to Maven por
Introduction to MavenIntroduction to Maven
Introduction to MavenJohn Valentino
7 visualizações10 slides
Unlocking the Power of AI in Product Management - A Comprehensive Guide for P... por
Unlocking the Power of AI in Product Management - A Comprehensive Guide for P...Unlocking the Power of AI in Product Management - A Comprehensive Guide for P...
Unlocking the Power of AI in Product Management - A Comprehensive Guide for P...NimaTorabi2
17 visualizações17 slides
Benefits in Software Development por
Benefits in Software DevelopmentBenefits in Software Development
Benefits in Software DevelopmentJohn Valentino
6 visualizações15 slides

Último(20)

predicting-m3-devopsconMunich-2023.pptx por Tier1 app
predicting-m3-devopsconMunich-2023.pptxpredicting-m3-devopsconMunich-2023.pptx
predicting-m3-devopsconMunich-2023.pptx
Tier1 app10 visualizações
Quality Engineer: A Day in the Life por John Valentino
Quality Engineer: A Day in the LifeQuality Engineer: A Day in the Life
Quality Engineer: A Day in the Life
John Valentino10 visualizações
Winter Projects GDSC IITK por SahilSingh368445
Winter Projects GDSC IITKWinter Projects GDSC IITK
Winter Projects GDSC IITK
SahilSingh368445416 visualizações
Introduction to Maven por John Valentino
Introduction to MavenIntroduction to Maven
Introduction to Maven
John Valentino7 visualizações
Unlocking the Power of AI in Product Management - A Comprehensive Guide for P... por NimaTorabi2
Unlocking the Power of AI in Product Management - A Comprehensive Guide for P...Unlocking the Power of AI in Product Management - A Comprehensive Guide for P...
Unlocking the Power of AI in Product Management - A Comprehensive Guide for P...
NimaTorabi217 visualizações
Benefits in Software Development por John Valentino
Benefits in Software DevelopmentBenefits in Software Development
Benefits in Software Development
John Valentino6 visualizações
Introduction to Git Source Control por John Valentino
Introduction to Git Source ControlIntroduction to Git Source Control
Introduction to Git Source Control
John Valentino8 visualizações
Techstack Ltd at Slush 2023, Ukrainian delegation por ViktoriiaOpanasenko
Techstack Ltd at Slush 2023, Ukrainian delegationTechstack Ltd at Slush 2023, Ukrainian delegation
Techstack Ltd at Slush 2023, Ukrainian delegation
ViktoriiaOpanasenko7 visualizações
Dapr Unleashed: Accelerating Microservice Development por Miroslav Janeski
Dapr Unleashed: Accelerating Microservice DevelopmentDapr Unleashed: Accelerating Microservice Development
Dapr Unleashed: Accelerating Microservice Development
Miroslav Janeski16 visualizações
Top-5-production-devconMunich-2023.pptx por Tier1 app
Top-5-production-devconMunich-2023.pptxTop-5-production-devconMunich-2023.pptx
Top-5-production-devconMunich-2023.pptx
Tier1 app10 visualizações
tecnologia18.docx por nosi6702
tecnologia18.docxtecnologia18.docx
tecnologia18.docx
nosi67026 visualizações
nintendo_64.pptx por paiga02016
nintendo_64.pptxnintendo_64.pptx
nintendo_64.pptx
paiga020167 visualizações
Mobile App Development Company por Richestsoft
Mobile App Development CompanyMobile App Development Company
Mobile App Development Company
Richestsoft 5 visualizações
Bootstrapping vs Venture Capital.pptx por Zeljko Svedic
Bootstrapping vs Venture Capital.pptxBootstrapping vs Venture Capital.pptx
Bootstrapping vs Venture Capital.pptx
Zeljko Svedic16 visualizações
predicting-m3-devopsconMunich-2023-v2.pptx por Tier1 app
predicting-m3-devopsconMunich-2023-v2.pptxpredicting-m3-devopsconMunich-2023-v2.pptx
predicting-m3-devopsconMunich-2023-v2.pptx
Tier1 app14 visualizações
Understanding HTML terminology por artembondar5
Understanding HTML terminologyUnderstanding HTML terminology
Understanding HTML terminology
artembondar58 visualizações
The Path to DevOps por John Valentino
The Path to DevOpsThe Path to DevOps
The Path to DevOps
John Valentino6 visualizações
How to build dyanmic dashboards and ensure they always work por Wiiisdom
How to build dyanmic dashboards and ensure they always workHow to build dyanmic dashboards and ensure they always work
How to build dyanmic dashboards and ensure they always work
Wiiisdom16 visualizações
EV Charging App Case por iCoderz Solutions
EV Charging App Case EV Charging App Case
EV Charging App Case
iCoderz Solutions10 visualizações
Introduction to Gradle por John Valentino
Introduction to GradleIntroduction to Gradle
Introduction to Gradle
John Valentino7 visualizações

TorfsBot or Not? Evaluating User Perception on Imitative Text Generation (CLIN33)

Notas do Editor

  1. Voor de mensen die Rik Torfs niet kennen: Professor Kerkelijk Recht Ex-rector KU Leuven Maarook: fervent Twitteraar Op Twitter sinds 2010 Speaks in algemeenheden en boutades “Vlaams Orakel” “Koning van de boutade”
  2. Volautomatische Twitterbot Heeft leren tweeten zoals Rik Torfs door zijn tweets & columns te analyseren Simpel Markov model & kernwoorden vervanger Tweet 5x per dag en antwoordt op iedereen
  3. automatische kernwoord vervangingen
  4. Deze tweet is met het dynamische sjabloon op Rik’s originele tweet