Serious Games for Language Learning: How Much Game, How Much AI?

  • Authors:
  • W. Lewis Johnson;Hannes Vilhjalmsson;Stacy Marsella

  • Affiliations:
  • Center for Advanced Research in Technology for Education, USC / Information Sciences Institute, 4676 Admiralty Way, Marina del Rey, CA 90292;Center for Advanced Research in Technology for Education, USC / Information Sciences Institute, 4676 Admiralty Way, Marina del Rey, CA 90292;Center for Advanced Research in Technology for Education, USC / Information Sciences Institute, 4676 Admiralty Way, Marina del Rey, CA 90292

  • Venue:
  • Proceedings of the 2005 conference on Artificial Intelligence in Education: Supporting Learning through Intelligent and Socially Informed Technology
  • Year:
  • 2005

Quantified Score

Hi-index 0.00

Visualization

Abstract

Modern computer games show potential not just for engaging and entertaining users, but also in promoting learning. Game designers employ a range of techniques to promote long-term user engagement and motivation. These techniques are increasingly being employed in so-called serious games, games that have non-entertainment purposes such as education or training. Although such games share the goal of AIED of promoting deep learner engagement with subject matter, the techniques employed are very different. Can AIED technologies complement and enhance serious game design techniques, or does good serious game design render AIED techniques superfluous? This paper explores these questions in the context of the Tactical Language Training System (TLTS), a program that supports rapid acquisition of foreign language and cultural skills. The TLTS combines game design principles and game development tools with learner modelling, pedagogical agents, and pedagogical dramas. Learners carry out missions in a simulated game world, interacting with non-player characters. A virtual aide assists the learners if they run into difficulties, and gives performance feedback in the context of preparatory exercises. Artificial intelligence plays a key role in controlling the behaviour of the non-player characters in the game; intelligent tutoring provides supplementary scaffolding.