Rafael Pérez Y Pérez
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Rafael Pérez Y Pérez has a total of 6 co-authors. Here are the top co-authors by number of shared publications:
- Mike Sharples
The Open University
3 shared publications - Iván Guerrero Román
Univ Nacl Autonoma Mexico, Posgrad Ciencia & Ingn Comp, Mexico City, DF, Mexico
2 shared publications - Alfredo Aguilar
Universidad Nacional Autónoma de México
1 shared publication - Margareta Ackerman
Santa Clara University, Santa Clara, USA
1 shared publication - Santiago Negrete Yankelevich
Departamento de Tecnologías de la Información. Universidad Autónoma Metropolitana-Cuajimalpa
1 shared publication - Tony Veale
School of Computer Science, University College Dublin, Dublin, Ireland
1 shared publication
Latest Publications
- Open Access
- 21 April 2026
- Published by Elsevier in SSRN Electronic Journal
Comparing the evaluation of the thematic consistency of a symbolic cognitive model and three conversation simulators
A narrative shows thematic consistency when all events in the plot contribute either to advancing the conflict or to sustaining the coherence of the tale. The Model of Thematic Consistency (MTC) (Pérez y Pérez under review) was designed to identify actions that do not support this consistency in computer-generated narratives. The MTC was realised in MEXICA, a symbolic cognitive model of creative writing (Pérez y Pérez and Sharples, 2001; Pérez y Pérez, 2007). This paper reports a study comparing thematic consistency as assessed by MEXICA with the output of three conversation simulators: Claude, Copilot and DeepSeek. The comparison notes differences in their handling of climactic events, thematic coherence, and emotional states. MEXICA relies on mechanisms based on a computer representation of emotion and conflict, which allow systematic exploration of narrative processes. The simulators, in contrast, operate probabilistically, drawing on statistical patterns from large text corpora. The findings indicate that generative AI can broaden literary analysis by offering varied interpretive scenarios, yet its outputs may be unstable, opaque, and prone to anthropomorphism. Cognitive models such as MEXICA provide clear internal mechanisms and explanatory transparency. These observations underline the value of symbolic cognitive models for the study of narrative in the era of generative AI.
- 21 April 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessComparing the evaluation of the thematic consistency of a symbolic cognitive model and three conversation simulators
A narrative shows thematic consistency when all events in the plot contribute either to advancing the conflict or to sustaining the coherence of the tale. The Model of Thematic Consistency (MTC) (Pérez y Pérez under review) was designed to identify actions that do not support this consistency in computer-generated narratives. The MTC was realised in MEXICA, a symbolic cognitive model of creative writing (Pérez y Pérez and Sharples, 2001; Pérez y Pérez, 2007). This paper reports a study comparing thematic consistency as assessed by MEXICA with the output of three conversation simulators: Claude, Copilot and DeepSeek. The comparison notes differences in their handling of climactic events, thematic coherence, and emotional states. MEXICA relies on mechanisms based on a computer representation of emotion and conflict, which allow systematic exploration of narrative processes. The simulators, in contrast, operate probabilistically, drawing on statistical patterns from large text corpora. The findings indicate that generative AI can broaden literary analysis by offering varied interpretive scenarios, yet its outputs may be unstable, opaque, and prone to anthropomorphism. Cognitive models such as MEXICA provide clear internal mechanisms and explanatory transparency. These observations underline the value of symbolic cognitive models for the study of narrative in the era of generative AI.
- 1 January 2024
- Published by Springer Nature
- p. 1-7
Artificial Intelligence and Creative Writing
- 22 April 2022
- Published by Taylor & Francis
- p. 83-100
Storyworlds
The chapter discusses programs that inhabit simulated worlds where characters converse and adventures happen. By logging events in a simulated world as they occur and then sifting the logs for notable occurrences, the program compiles material for a tellable story. The sources for these programs are text-based adventure games, where players move through locations and engage with characters and objects by giving textual commands to the computer. The entire process of designing a text-based adventure, playing the game, recording actions, selecting events to retell, and composing a story from the gameplay can now be automated. Two challenges for designers of storyworld programs are to determine which events contribute to memorable stories and to tell stories from different perspectives, with flashbacks and flashforwards. For game-based story machines to become more inventive, they need general mechanisms to recognize unusual occurrences, track their causes and consequences, and form these into tellable stories. If such programs can be designed, they could not only pick up unusual happenings in the fantasy worlds of computer games but also find and report noteworthy events in our own world, such as new patterns of illness or financial irregularities.
- 22 April 2022
- Published by Taylor & Francis
- p. 83-100
Storyworlds
The chapter discusses programs that inhabit simulated worlds where characters converse and adventures happen. By logging events in a simulated world as they occur and then sifting the logs for notable occurrences, the program compiles material for a tellable story. The sources for these programs are text-based adventure games, where players move through locations and engage with characters and objects by giving textual commands to the computer. The entire process of designing a text-based adventure, playing the game, recording actions, selecting events to retell, and composing a story from the gameplay can now be automated. Two challenges for designers of storyworld programs are to determine which events contribute to memorable stories and to tell stories from different perspectives, with flashbacks and flashforwards. For game-based story machines to become more inventive, they need general mechanisms to recognize unusual occurrences, track their causes and consequences, and form these into tellable stories. If such programs can be designed, they could not only pick up unusual happenings in the fantasy worlds of computer games but also find and report noteworthy events in our own world, such as new patterns of illness or financial irregularities.
- 22 April 2022
- Published by Taylor & Francis
- p. 115-125
Modelling the mind of a writer
The focus of this chapter is computer programs that model how people write. Such programs require two components: a model of the human writing process, and a computer system based on the model that can generate stories while revealing its inner workings. The chapter introduces the Engagement-Reflection (E-R) model of human writing and the MEXICA program, based on the E-R model, that generates outlines for stories about the Mexicas, the indigenous inhabitants of Mexico City. The E-R writing model describes creative writing as an interaction between two mental processes – engagement and reflection – that form ideas into text and drive composing forward. The MEXICA program implements engaged writing to generate new stories out of a stock of previous stories with characters and their actions. Then, it switches to a reflective state where it checks the flow of tension in the story and fills in gaps in the narrative. It then switches back to an engaged state to continue the text and alternates between these states until the story is finished. Models of creative writing can act like weather models, helping writers to forecast how a story could continue and the effects of altering plot, characters, or setting.
- 22 April 2022
- Published by Taylor & Francis
- p. 115-125
Modelling the mind of a writer
The focus of this chapter is computer programs that model how people write. Such programs require two components: a model of the human writing process, and a computer system based on the model that can generate stories while revealing its inner workings. The chapter introduces the Engagement-Reflection (E-R) model of human writing and the MEXICA program, based on the E-R model, that generates outlines for stories about the Mexicas, the indigenous inhabitants of Mexico City. The E-R writing model describes creative writing as an interaction between two mental processes – engagement and reflection – that form ideas into text and drive composing forward. The MEXICA program implements engaged writing to generate new stories out of a stock of previous stories with characters and their actions. Then, it switches to a reflective state where it checks the flow of tension in the story and fills in gaps in the narrative. It then switches back to an engaged state to continue the text and alternates between these states until the story is finished. Models of creative writing can act like weather models, helping writers to forecast how a story could continue and the effects of altering plot, characters, or setting.
- Open Access
- 9 November 2020
- Published by Springer Nature in New Generation Computing
- Vol. 38 (4) , 551-563
Leaps and Bounds: An Introduction to the Field of Computational Creativity
- 9 November 2020
- Published by Springer Nature in New Generation Computing
- Vol. 38 (4) , 551-563
Open AccessLeaps and Bounds: An Introduction to the Field of Computational Creativity
- 7 September 2020
- Published by Springer Nature in New Generation Computing
- Vol. 38 (4) , 713-737
Towards a Methodology for Field Work in Computational Creativity
- 7 September 2020
- Published by Springer Nature in New Generation Computing
- Vol. 38 (4) , 713-737
Towards a Methodology for Field Work in Computational Creativity
- 26 July 2019
- Published by Springer Nature
- p. 255-274
Representing Social Common-Sense Knowledge in MEXICA
- 26 July 2019
- Published by Springer Nature
- p. 255-274
Representing Social Common-Sense Knowledge in MEXICA
- 29 June 2019
- Published by Instituto Politecnico Nacional/Centro de Investigacion en Computacion in Computación y Sistemas
- Vol. 23 (2) , 583-600-599
Adding Social Aspects to the Automatic Generation of Narratives
Adding Social Aspects to the Automatic Generation of Narratives
- 29 June 2019
- Published by Instituto Politecnico Nacional/Centro de Investigacion en Computacion in Computación y Sistemas
- Vol. 23 (2) , 583-600-599
Adding Social Aspects to the Automatic Generation of Narratives
Adding Social Aspects to the Automatic Generation of Narratives
- 29 January 2019
- Published by Springer Nature in Annals of Mathematics and Artificial Intelligence
- Vol. 88 (5-6) , 549-588
A computer agent that develops visual compositions based on the ER-model
- 29 January 2019
- Published by Springer Nature in Annals of Mathematics and Artificial Intelligence
- Vol. 88 (5-6) , 549-588
A computer agent that develops visual compositions based on the ER-model
- 5 December 2014
- Published by Atlantis Press SARL
- p. 267-284
From MEXICA to MEXICA-Impro: The Evolution of a Computer Model for Plot Generation
- 5 December 2014
- Published by Atlantis Press SARL
- p. 267-284
From MEXICA to MEXICA-Impro: The Evolution of a Computer Model for Plot Generation