Call For Papers


AI and Feedback is the first international workshop on the topic and it is one of the IJCAI 2015 workshops. It focuses on applying AI techniques for addressing the challenges of mining and extracting feedback, as well as assessing, analysing, and making use of feedback.

Feedback is key for both improvement and decision making. As humans, we are designed to constantly seek feedback on how and what we are doing in life. Feedback can come from ourselves, from our peers, from our teachers, from our collaborators, audiences, customers, public or press. Feedback provides opportunities to learn about how we and our work are perceived by others. If we encounter someone [something] new, we can examine previous feedback to learn how this new person [thing] is perceived by others.

A key target of this workshop is to discuss how to build intelligent feedback agents that are capable of autonomously providing feedback that equals or surpasses that of human beings in its usefulness. The feedback of artificial feedback agents should have some desirable characteristics. It should be socially and culturally appropriate, clearly expressed, sufficiently focused and contextualised, thoughtfully challenging yet encouraging, compassionate, open to debate, justified and comparative, also, it should be trustworthy. Giving and receiving feedback with these characteristics therefore is a challenging, creative process.

Aims and objectives. This workshop aims to bring together researchers from different strands of AI to discuss various aspects of feedback. The following questions are examples for consideration:

 Topics of Interest

Topics of interest cover a variety of feedback-related issues, such as mining and extracting feedback, generating feedback, understanding feedback, and assessing feedback.

Topics of interest cover different strands of AI, such as multiagent systems, machine learning, natural language processing, and knowledge representation.

Topics include, but are not limited to:

 Important Dates


We welcome and strongly encourage the submission of high quality, original work (published or unpublished), as well as visionary papers and roadmaps relevant to the scope of this workshop.

Submitted papers must be formatted according to IJCAI guidelines. Formatting guidelines and electronic templates are available here.

Submitted papers should not exceed 8 pages, excluding the bibliographic references.

Papers should be submitted electronically through the AInF2015 EasyChair site.

Papers will be subject to a single-blind peer review. So authors can keep their names and affiliations on their submitted papers.


The workshop proceedings will be published as a CEUR Workshop Proceedings (ISSN: 1613-0073).

A selection of accepted workshop papers that are relevant to the education domain will be invited as book chapters in a book entitled "Learning about music in the age of MOOCS", to be published by Academic Press, Amsterdam by the end of 2015.


 Accepted Papers

The proceedings are available online at


Date: 26 July 2015
Location: Room 457, at the New Building of Facultad de Ciencias Económicas.
Workshop #: W42 - AI and Feedback

08:45 - 10:25 Session 1
  • Pedagogical agent models for massive online education
    Matthew Yee-King and Mark d'Inverno
  • Implementing feedback in creative systems: a workshop approach
    Joseph Corneli and Anna Jordanous
  • The comic strip game: observing the impact of implicit feedback in the content creation process
    Fiammetta Ghedini, Benjamin Frantz, François Pachet and Pierre Roy
  • Improving music composition through peer feedback: experiment and preliminary results
    Daniel Martín, Benjamin Frantz and François Pachet
  • When reflective feedback triggers goal revision: a computational model for literary creativity
    Pablo Gervás and Carlos León
10:25 - 10:50 Coffee Break
10:50 - 11:30 Session 2
  • Personalised automated assessments
    Patricia Gutierrez, Nardine Osman and Carles Sierra
  • Revealing and interpreting crowd stories in online social environments
    Chris Kiefer, Matthew Yee-King and Mark d'Inverno
11:30 - 12:15 Invited Speaker: Luc Steels
Praise or Flow? Two pedagogies for open-ended learning
12:15 - 12:45 Discussion Session

 Invited Speaker

Luc Steels
ICREA Research Professor at Universitat Pompeu Fabra
Director of the VUB Artificial Intelligence Lab

Luc Steels studied linguistics at the University of Antwerp (Belgium) and computer science at the Massachusetts Institute of Technology (USA). His main research field is Artificial Intelligence covering a wide range of intelligent abilities, including vision, robotic behavior, conceptual representations and language. In 1983 he became a professor of computer science at the University of Brussels (VUB). He has been co-founder and chairman (from 1990 until 1995) of the VUB Computer Science Department (Faculty of Sciences).
He founded the Sony Computer Science Laboratory in Paris in 1996 and became its first director. Currently he is ICREA research professor at the Institute for Evolutionary Biology (CSIC,UPF). Steels has participated in dozens of large-scale European projects and more than 30 PhD theses have been granted under his direction. He has produced over 200 articles and edited 15 books directly related to his research. During the past decade he has focused on theories for the origins and evolution of language using computer simulations and robotic experiments to discover and test them.

Talk's Abstract. MOOCs have recently flourished as a new way to bring education to large numbers of people at affordable cost. However most MOOCs so far rely on rigid structured instruction based on prior lesson plans. Can we also develop MOOCs that follow the paradigm of open-ended, student-centered learning? This requires (i) a challenging environment and tools in which students can learn how to solve problems without a rigid prior lesson plan, (ii) ways in which to orchestrate peer-to-peer social feedback between students, and (iii) mechanisms fostering motivation. This talk focuses on the latter. I discuss two pedagogies at opposite ends of a spectrum: one based on praise, which means encouragement or possibly punishment, the other based on flow, which means that students can regulate their own problem challenge in relation to their skill level and thus become self-motivated.

 Attending AInF 2015

IJCAI-15 will be held in Buenos Aires, Argentina from July 25th to July 31st, 2015.

The AInF workshop at IJCAI-15 (workshop # W42) will take place on July 26th, 2015, at the New Building of Facultad de Ciencias Económicas. Please refer to the IJCAI website for further information on the list of IJCAI workshops and their schedule.

Further information about IJCAI 2015, Visa to Argentina, air fares and accomodation, as well as information about Buenos Aires is also available at the IJCAI 2015 website.



Nardine Osman , Artificial Intelligence Research Institute (IIIA-CSIC), Barcelona, Spain
Matthew Yee-King , Department of Computing, Goldsmiths, University of London, London, UK

 PC Members

James Bailey, Department of Computing and Information Systems, The University of Melbourne, Melbourne, Australia
Oliver Bown, Design Lab, University of Sydney, Sydney, Australia
Mark d'Inverno, Department of Computing, Goldsmiths, University of London, London, UK
Alice Eldridge, Department of Informatics, University of Sussex, Sussex, UK
Jesualdo Tomás Fernández-Breis, Department of Informatics and Systems, University of Murcia, Murcia, Spain
Ilya Goldin, Pearson Education, Pennsylvania, USA
Sumit Gulwani, Microsoft Research - Redmond Lab, Washington, USA
Sergio Gutierrez-Santos, Computer Science and Information Systems, University of London, London, UK
Sharon Hsiao, School of Computing, Informatics & Decision Systems Engineering, Arizona State University, Arizona, USA
Jimmy Huang, School of Information Technology, York University, Toronto, Canada
Anna Jordanous, School of Computing, University of Kent, Canterbury, UK
Chris Kiefer, Department of Informatics, University of Sussex, Sussex, UK
Manolis Mavrikis, UCL Institute of Education, University College London, London, UK
François Pachet, Sony Computer Science Laboratory, Paris, France
Emanuele Ruffaldi, Perceptual Robotics Laboratory (PERCRO), Pisa, Italy
Dario Sanfilippo,
Carles Sierra, Artificial Intelligence Research Institute (IIIA-CSIC), Barcelona, Spain
Luc Steels, Artificial Intelligence Lab, Vrije Universiteit Brussel, Brussels, Belgium
Shusaku Tsumoto, Department of Medical Informatics, Shimane University, Izumo, Japan
Jacco van Ossenbruggen, Information Access Group, Centrum Wiskunde and Informatica (CWI), Amsterdam, the Netherlands
Toby Walsh, National ICT Australia (NICTA) & University of New South Wales, Sydney, Australia
Daniel Zeng, Management Information Systems, University of Arizona, Arizona, USA