Intelligent Tutoring

Brian M. Slator, Computer Science Dept., NDSU

Intelligent Tutoring is usually associated with educational software applications and is most typically involved with some notion of STUDENT MODELLING where

Intelligent Tutoring is also commonly associated with the study of LEARNING STYLE which attempts to classify learners and their approach to learning. The common classification schemes usually feature categories like: VISUAL LEARNER, AUDITORY LEARNER, KINETIC (TACTILE) LEARNER, and so on.

There are problems with this schema:

The issues are the same in Virtual Environments where student learners are engaged in "learn-by-doing" exploration.

There is a need for timely and appropriate remediation in the event of student failure of one kind or another.

One advantage of multi-user synthetic environments is asynchronous participation.

The corresponding disadvantage is that players cannot depend on human tutors being available at all times, unless tutors can be hired to inhabit the world around the clock: a practical, economic, impossibility. One obvious approach to the necessary tutoring is to implement software tutoring agents.

Intelligent Software Tutoring Agents

It is easy to imagine three different approaches to intelligent tutoring, based on the knowledge available to the tutoring agent.

  1. Deductive Tutoring
  2. Case-based Tutoring
  3. Rule-based Tutoring

Deductive Tutoring

Deductive Tutors provide assistance to players in the course of their deductive reasoning within the scientific problem solving required for the accomplishment of their goals.

Example: intelligent tutoring agents in the NDSU Geology Explorer, which intends to implement an educational game for teaching the Geosciences. This will take the form of a synthetic (or virtual) envirionment, Planet Oit, where students will be given the means and the equipment to explore a planet as a Geologist would. While on the planet, students are assigned goals related to rock and mineral identification.

The tutors work from knowledge of the rocks and minerals, and knowledge of the "experiments" needed to confirm or deny the identity of a rock or mineral.

Three opportunities for deductive tutoring present themselves:

  1. an equipment tutor who will detect when a student has failed to "buy" equipment necessary to achieving their goals
  2. an exploration tutor who will detect when a student has overlooked a goal in their travels
  3. a science tutor who will detect when a student makes a wrong guess and why (i.e. what evidence they are lacking); or when a student makes a correct guess with insufficient evidence (i.e. a lucky guess)

The three (3) tutoring agents will operate as follows:

  1. The Equipment Tutor
    • The equipment tutor is called by the purchase verb (described in the Geology Explorer Project's Instruments section).
      • The tutor checks whether the instrument purchased can be used to satisfy any of the player's goals.
      • If not, the tutor may decide to remediate on that topic (i.e. buying instruments that serve no obvious purpose)
    • The equipment tutor is also called by the exit(s) from the Equipment Locker.
      • The tutor checks whether the student has ALL the instruments needed to satisfy their goals.
      • If not, the tutor may decide to remediate on that topic (i.e. the need to buy instruments that serve to satisfy goals)

  2. The Exploration Tutor
    • The exploration tutor is called by the exit(s) from each of the locations (rooms) on the Planet.
      • The tutor checks whether the student is leaving a room that might satisfy a goal; i.e. if their goal is to locate Kimberlite, and there is Kimberlite in the room they are leaving, the tutor may decide to remediate on that topic.
    • This remediation could be done on a room-by-room basis (easiest),
      or it could be done on a region-by-region basis (harder);
      or on a hot-cold basis (i.e. if the player is moving farther away from some distant goal).

  3. The Science Tutor
    • The science tutor is called by the report verb (described in the Geology Explorer Project's Reporting section).
    • For example, suppose the student is given the goal of locating and identifying graphite used in the production of steel and other materials. To confirm that a mineral deposit is indeed graphite the student must
      • test the deposit with the "streak plate" and observe a black streak
      • scratch the deposit with the "glass plate" to determine its hardness is less than 2.0 on the standard (Mohs) scale.
      • report that the sample is graphite
    • The tutor checks the player's .geology_history property and determines which of the following cases pertain:
      1. (wrong tests) the player has "guessed" incorrectly
        and the player's .geology_history property indicates they
        have not conducted the necessary tests to identify the rock/mineral in question
      2. (wrong answer) the player has "guessed" incorrectly
        and the player's .geology_history property indicates they
        have conducted the necessary tests to identify the rock/mineral in question
      3. (lucky guess) the player has "guessed" correctly
        but the player's .geology_history property indicates they
        have not conducted the necessary tests to identify the rock/mineral in question
      4. (good work) the player has "guessed" correctly
        and the player's .geology_history property indicates they
        have conducted the necessary tests to identify the rock/mineral in question

    • The system will encode the necessary and sufficient experments for each rock and mineral, as well as their expected results.
    • The system will check these facts against the student's .geology_history property whenever the student "guesses" a deposit's identity
    • The system will remediate, as appropriate, according to the four cases listed above.

Case-based Tutoring

Case-based Tutors provide assistance to players by presenting them with examples of relevant experience. This is accomplished by

Example: intelligent tutoring in ORCA, the ORganizational Change Advisor which is designed to teach consultants how to identify problems that may face a business, and to expose them to potential solutions to those problems.

ORCA presents business war stories about organizational change in response to economic and technological pressures. As the user works with a client, the client becomes a new story in the system, thus extending ORCA to serve as a corporate memory.

Tutoring agent behavior is adaptive in two senses.

  1. Each agent is the "owner" of a small set of sub-topics and related cases.
    • As a learner operates in the synthetic environment they are building their own case, and the relevant agent is alerted for remediation whenever a learner case becomes similar and relevant to a case under the agent's control.
    • As learner behavior changes, so does their profile and the nature of the cases they match against. In this way, agents will "gain and lose interest" in a player according to the changes in the learner's profile.

  2. Learner state will be preserved throughout the course of their involvement of the synthetic environment.
    • As learners leave the game, either as successful or unsuccessful players, their state and experience is saved as a new case. These saved cases, according to their profile, will become part of the inventory assigned to one or more of the tutorial agents.
    • As later players enter the synthetic environment, the tutorial agents will have these additional cases of success and failure to present as part of their remediation package.

In other words, case-based tutoring agents begin the game armed with prototypical case studies, but they will accumulate additional student case studies as players enter and leave the game over time.

Rule Based Tutoring

Rule Based Tutors provide assistance by

  1. encoding a set of rules about the domain
  2. monitoring student action looking for one of these rules to be "broken"
  3. "visiting" the student to present an expert dialog, or a case-based tutorial, or a passive presentation (in, say, video).

    Example: the NDSU Retail Game, simulating of a micro-economic environment.

    For example, a player may decide to try and maximize profits by pricing their products at ten times the wholesale price. This is a naive strategy that says, "I might not sell very many, but each sale will be very profitable".

    This breaks the simple rule:

    • Don't set prices unreasonably high.
    • the intelligent tutoring agent recognizes this as a losing strategy
    • and knows the player is unlikely to sell anything at all.

    When the agent detects a strategic mistake it

    • sends a message to the player saying, "You may be setting your prices too high".
    • The player can then decide to ignore the message or pursue it.
    • This unintrusive method of tutoring is implemented to be consistent with the educational game principles of leaving the player in control and letting them make their own mistakes.
    • If the player chooses to pursue the warning, they are engaged by the agent who presents cases and explains the ideas of profit margin and Manufacturers Suggested Retail Price (MSRP).
    • The special tutorial lessons include further case retrievals, conversational browsing with the agent, and possibly a canned tutorial on price setting.

    The drawback is that rules of this sort are relatively rare (and relatively obvious) in a complex domain. Therefore the rule-based method does not afford as many opportunities as other approaches.

    Finally, breaking the rules is not always the wrong thing to do (as many experts will tell you), which could create problems in all but the most elementary teaching systems.

    Tutoring Strategies

    A common problem with simulations is that, like the real world, players can foul things up and not know why. Unlike the real world, though, all the information for the simulation is readily available, and can be used to generate explanations or warnings.

    Tutoring agents are based on the design and information in the model, and are triggered by user actions. When an agent is activated, the player sees a warning; they can ask for more information (possibly bringing them a "visit" from an intelligent tutoring agent), or they can ignore it and carry on at their own risk.

    • The idea is that intelligent tutoring agents are looking over your shoulder as you play. They should be there when you need them, but when you know what you're doing (or when you think you know), you can ignore the agent.
    • There is no penalty for ignoring the agent's warnings, other than the inevitable failure to succeed, a penalty imposed by the simulation as a consequence of the player's failure to learn their role in the environment. In all cases it is up to the player to decide how the warnings and advice apply to them.
    • The simulation allows the player to win or lose in any way they choose. It is important the environment be an active one, where the player is stimulated by the events occurring in the game. The environment is not just a passive, reactive one, it seeks opportunities to interact and tutor.
    • Given the approaches to tutoring described above, there still remains the question of tutoring stategies, which in large measure reduce to a question of timing. The following questions remain:
      • How often should a student be remediated?
      • What should trigger a tutor's decision to remediate?
      • How do human experts/mentors make these decisions?

    One interesting approach might lie in the notion of a tutoring script that shapes the interaction in general terms. One could imagine tutoring scripts that arrayed different combinations of questions, examples, cases, remedical exercises, and canned presentations to engage different students at different times, depending on student behavior.


    This talk was orignially presented to the NDSU CS Department Seminar on Multimedia and Distance Education,
    Wed. Sept. 9th, 1997, at 9:00 am in IACC 258C (the CS dept. conference room).

    e-mail: slator@badlands.nodak.edu