The mapping requires the user to figure out how to accomplish a goal with an interface. It implies that "The user must translate the psychological goals and intentions into the desired system state, then determine what settings of the control mechanisms will yield that state, and then determine what physical manipulations of the mechanism are required" [600, p. 37].

In direct manipulation interfaces (Chapter 28), the visual presentation of an object resembles its physical correspondent and can be directly acted on. For example, text in a text editor can be highlighted, deleted, or changed by point-and-click-style interactions [416].

the seven-stage model of interaction proposed by Norman [600] applies to all modalities of interaction

They also aid design and engineering by highlighting desirable properties of a dialogue system [5].

This AAC system was designed to use context to facilitate the creation of personal narratives [75].

The cognitive scientist Kirsh presented a criticism of Norman's view of dialogue and developed an alternative based on the theory of embodied cognition [416].

Horvitz [360] summarized the principles of mixed-initiative interfaces as follows:

A research group at the University of Washington [60] recruited 10 families and recorded their communications with Amazon Echo Dot (Alexa) for four weeks.

Communication repair refers to the "work of restoring shared understanding" when conversational partners misunderstand each other [60].

Section 18.3 outlines a view of dialogue developed by Suchman [804] that emphasizes the situated nature of dialogue.

A cornerstone of this research is the book Plans and Situated Action: The Problem of Human–Machine Communication by Suchman [804].

According to Scholtz [745], the two gulfs manifest differently in the different roles a user may have when interacting with a robot:

Norman's model stresses the need for users' acts to be understood by the computer and for users to understand the computer. Successful interfaces should also "provide a strong sense of understanding and control" [600, p. 49].

Affordance, which we discussed in Chapter 3, refers to how well users can interpret what actions are possible with a widget. Visibility is a handy related concept in design that underlies direct manipulation interfaces [416].

Norman suggested that the ease of mapping is related to its directness, "where directness can be measured by the complexity of the relationship between representation and value, measured by the length of the description of the mapping" [600, pp. 28–29].

Norman offered two central concepts to help us understand these cognitive efforts: the gulf of execution and the gulf of evaluation (Figure 18.2).

A significant early theory of dialogue interaction is the seven-stage model of Norman [600]. It considers interaction as goal-directed, turn-based dialogue.

Liu and Chilton [488] studied prompt engineering for text-to-image generation; see the figure in this paper example box, which shows examples of answers to the prompt "SUBJECT in the style of STYLE."

Liu and Chilton [488] noted that interaction with such models faces a dilemma. While it is possible to input anything as a prompt to such models, users must "engage in bruteforce trial and error with the text prompt when the result quality is poor."