The domain model contains the set of skills, knowledge, and strategies of the topic being tutored. It normally contains the ideal expert knowledge and may also contain the bugs, mal-rules, and misconceptions that students periodically exhibit. It is a representation of all the possible student states in the domain. While these states are typically tied to content, general psychological states (e.g., boredom, persistence) may also be included, since such states are relevant for a full understanding of possible pedagogy within the domain. (Pavlik et al., 2013)

The student model consists of the cognitive, affective, motivational, and other psychological states that are inferred from performance data during the course of learning. Typically, these states are summary information about the student that will subsequently be used for pedagogical decision making. The student model is often viewed as a subset of the domain model, which changes over the course of tutoring. For example, “knowledge tracing” tracks the student’s progress from problem to problem and builds a profile of strengths and weaknesses relative to the domain model (Anderson, Corbett, Koedinger & Pelletier, 1995). Since ITS domain models may track general psychological states, student models may also represent these general states of the student. (Pavlik et al., 2013)

The pedagogical model takes the domain and student models as input and selects tutoring strategies, steps, and actions on what the tutor should do next in the exchange with the student to move the student state to more optimal states in the domain. In mixed-initiative systems, the students may also initiate actions, ask questions, or request help (Aleven, McLaren, Roll & Koedinger, 2006; Rus & Graesser, 2009), but the ITS always needs to be ready to decide “what to do next” at any point and this is determined by a tutoring model that captures the researchers’ pedagogical theories. Sometimes what to do next implies waiting for the student to respond (Pavlik et al., 2013)

The tutor-student interface model interprets the student’s contributions through various input media (speech, typing, clicking) and produces output in different media (text, diagrams, animations, agents). In addition to the conventional human-computer interface features, some recent systems have had natural language interaction (Graesser, D’Mello, et al., 2012; Johnson & Valente, 2008), speech recognition (D’Mello, Graesser & King, 2010; Litman, 2013), and the sensing of student emotions (Baker, D’Mello, Rodrigo & Graesser, 2010; D’Mello & Graesser, 2010; Goldberg, Sottilare, Brawner & Holden, 2011). (Pavlik et al., 2013)

Group models seek to capture the characteristics of groups of users / learners... group models are based on the identification of groups of learners that share common characteristics, behaviour, etc. As such, group models are used to determine and “describe” what makes learners “similar” or not, as well as whether any two learners can belong to the same group. (Kerr, 2004)