Tell me and I forget. Show me and I remember. Involve me and I understand. – Chinese proverb about education
The website of the AAAI (Association for the Advancement of Artificial Intelligence) describes itself as a “scientific society devoted to advancing the scientific understanding of the mechanisms underlying thought and intelligent behavior and their embodiment in machines.” One of the primary research areas identified by the AAAI is Intelligent Learning Systems (sometimes referred to as Intelligent Tutoring Systems). No other area more fundamentally highlights the cognitive interaction of man and machine than this research area.
Understanding the needs of learners, and marrying this with the design of new educational content, raises many significant questions. One question in particular is key – how do we present this information? At one level, software developers may consider navigation and layout of the software interface when answering this question. However, far more fundamental scientific research is required. The knowledge and assistance of cognitive psychologists, artificial intelligence scientists, technologists and educationalists can all assist in addressing this key question.
Intelligent Tutoring Systems as defined by the AAAI is “educational software containing an artificial intelligence component. The software tracks students’ work, tailoring feedback and hints along the way. By collecting information on a particular student’s performance, the software can make inferences about strengths and weaknesses, and can suggest additional work.” A number of differing systems attempt to provide intelligent tutoring primarily aimed at mathematics. However, these systems have addressed the question of how to present the information in a relatively simplistic manner. Without fully understanding the interaction between artificially intelligent systems and human cognitive science, one is sure to have problems.
Understanding the needs of both systems is key to providing an effective intelligent adaptive learning system. It is relatively straightforward to assess the state of knowledge in an artificial system. However, it is somewhat more convoluted to assess the state of knowledge in a human learner. From a human psychology perspective, through profiling and observation of the individual, an estimation of the knowledge profile of the user is possible. The degree of belief one places in this is grounded on the level of profiling, and what techniques are used in this profiling [1]. Effective user profiling is highly correlated with the development of a homogenistic human computer interaction [2]. Many studies have identified differing profiling techniques (e.g. learning style profiles [3, 4, 5]), all of which can profile some element of the user with 10 questions or 1000 questions. Approaches that have been used lately to assess the interaction of users and systems include those which also measure the cognitive load on a student as he/she interacts with the system. Measuring passive interactions with the systems through various techniques such as head and eye tracking, or EEG, can assist in improving our understanding of the HCI process.
It is the marrying of cognitive psychological techniques and artificial intelligence techniques which will bring about the next generation of adaptive learning systems. We are aware of this, and have identified this area of research as one which we will explore.
See FP7 expressions of interest call.
References:
[1] Gasparetti, F., & Micarelli, A., (2005) User Profile Generation Based on a Memory Retrieval Theory, Proceedings of the 1st International Workshop on Web Personalization, Recommender Systems and Intelligent User Interfaces (WPRSIUI 2005), pp 3-7.
[2] Gray, W. D., Sims, C. R. & Schoelles, M. (2005). Cognitive Metrics Profiling. In. 49th Annual Conference of the Human Factors and Ergonomics Society. Santa Monica, CA: Human Factors and Ergonomics Society.
[3] Zhang, L. (2003). Does the big five predict learning approaches? Personality and Individual Differences, 34, pp1431–1445.
[4] Bidjerano, T., & Yun Daia, D., (2007). The relationship between the big-five model of personality and self-regulated learning strategies. Learning and Individual Differences 17(1), pp 69-81
[5] T. Chamorro-Premuzic, A. Furnham (2008). Personality, intelligence and approaches to learning as predictors of academic performance. Personality and Individual Differences 44, pp1596–1603
