Explanations

What is the goal of this post? The goal is to describe ideas about "explanations" from the social sciences.

In future posts, explanation-tools for two different audiences —researchers and ordinary people— will be analysed.

Definitions

Explanations may be interactive (a conversation), static (a book), or a mix of both. In most explanations there is that which needs clarification, called the explanandum.

• Static explanations: descriptions aiming to clarify the explanandum, and may be found as written text, videos or other formats.
• Interactive explanations: a communicator and an audience interact aiming to resolve what, how or why questions posed by the audience.
• Mix: consider machines with pre-set questions and answers, where the audience can't always ask what it needs.

The explanation process

Explanations involve a cognitive and a social process. The version below was inspired by Explanation in artificial intelligence: insights from the social sciences.

1. During the cognitive process, hypotheses (e.g. causal connections) are generated aiming to clarify the explanandum.
   • Hypotheses are then compared, and one may be selected until contradicted by experience or superseeded (e.g. by a simpler explanation).
2. During the social process, the answer is communicated to an audience.

The process may iterate and update during the interaction (or not, in a static explanation). For example, the explanandum may be refined.

Note: the problems of causal connection and selection (1.) are well known in psychology.

Contrastive Questions

Research has shown that why-questions are usually contrastive. That is, they are phrased as Why P rather than Q? instead of simply Why P?. It's easy to remember it as a "reality (P) vs expectation (Q)" case.

The fact that requires explanation is "P"; the foil is "Q", and represents the case that was expected —which may also be implicit. The foil can aid explanation-generation. The reason for this is that answering a contrastive question can focus on the difference between the two cases, which is usually easier to answer than the case separately.

As Section 3-1 states:

For example, explaining "Why did Mr. Jones open the window?" with the response "Because he was hot" is not useful if the implied foil is Mr. Jones turning on the air conditioner, as this explains both the fact and the foil; or if the implied foil was why Ms. Smith, who was sitting closer to the window, did not open it instead, as the cited cause does not refer to a cause of Ms. Smith's lack of action.

Another way to state this by Hesslow:

What I want to suggest, then, is that the explanandum should be construed as a relation which involves three things: an object a, an object of comparison b and an explanandum property E which a has and b does not have.

Relevant Causes

We never provide causal chains (it's infinite), but a small-enough one that explains the event in question (this is the causal selection problem).

Researchers have pointed out many heuristics used: proximal over distal events (in the causal chain of events); abnormal or unexpected events; controllable events, deviation from theoretical ideals, model, predictive power, responsibility, and so forth.

But those are taken care of by contrastive why-questions which compare the event to be explained to a reference case (particular instance or general case). In this regard, Hesslow states (bold is mine):

Many of the selection criteria listed in Section 3 can be construed as the result of choosing different objects of comparison or reference classes. Let us consider again the fire in the barn, and let us suppose that we have in the back of our minds the picture of a normal barn. (...) the normal barn has not caught fire, it follows that an explanatorily relevant condition for this barn's catching fire must be abnormal. Thus, selection of abnormal conditions can be viewed as the result of comparing the explanandum object with a normal object.

And also most other causal selections are contained:

(...) the difference between this barn now and this barn yesterday, i.e. we would be selecting a precipitating cause [proximal in the list above]. Selection of the unexpected may be viewed as the result of explaining the difference between an expected and an actual outcome. Selection according to responsibility follows from a comparison between actual and morally ideal behaviour. Selection of conditions which cause a deviation from a theoretical ideal involves a comparison between an actual and a theoretically ideal situation, and so on (cf. Hesslow, 1983).

Here is yet another illustration by Hesslow, of how contrasts cases narrow down possible causes:

For instance, if we want to explain why the fly Ml has shorter wings than Nl, then the temperature in which the flies were raised is explanatorily irrelevant, since the temperature was the same in both cases. The mutated gene on the other hand was present in one case and absent in the other.It is, therefore, explanatorily relevant.

Pragmatism

Notably, accuracy may not be preferred in an explanation; rather, usefulness, simplicity, generality and consistency with prior knowledge are.

Many of these results come from work by Tania Lombrozo. (This section will eventually be expanded.)

Social Process (Communication)

The communication can be aided by the gricean maxims: rules of effective communication.

• Informative (Quantity): right amount of context and details,
• Truthful (Quality, or Fidelity): the explanation should be true,
• Relevance (Relation): avoid presumed-known or superfluous details, focus on what provides insight,
  • One example given earlier is to focus on unexpected events, whilst ignoring what is presumed to be known by the listener.
• Manner (clarity): express it in elegant terms.

In some cases, humans also tend to prefer concrete over abstract explanations, so "concreteness" could be added to the list.

Relevance is primarily related to the causal selection problem, as [how-people-explain-action-and-autonomous-intelligent-systems-should-too][Malle et al state]:

How do people solve this problem? They determine what exact question the audience is interested in (McClure and Hilton 1998); they take into account what their audience member already knows (Slugoski et al. 1993); and they offer elements of explanations that build bridges between presumed knowledge and novel information (Korman and Malle 2016). In short, they offer explanations that generate coherence in a knowledge structure of old and new information (Thagard 1989).

Contrastive explanations take care of many of these aspects automatically.

Metaphors: The Machine and The Person

As Miller et al. state:

Attribution theory is the study of how people attribute causes to events; something that is necessary to provide explanations.

Humans attribute causes using either:

• Agent-like model Explanation uses goals, motives, duties to justify intentional actions or behaviour.
  • Unintentional behaviour is usually explained using the next type.
• General causal model explain outcomes by counterfactual reasoning or contrastive explanations.

These basically define modes of explanation.

In technical fields, many complex systems are conceptualised as machines: composed of parts, each with a function, a role. Many are also conceptualised as graphs.

Ordinary people conceptualise certain kinds of complex systems as humans or agents (wholly or in part). This may happen with systems using human language or behaving autonomously, but other times it is due to pragmatic reasons. They would use and expect the kind of explanation a human would give, if there were one.

This is similar to what researchers hypothesise:

For those intentional agents, we hypothesize, people will apply the same conceptual framework of behavior explanation that they apply to humans (...) a subset of AIS that people do not regard as intentional agents; and for those, they may apply a purely mechanical explanatory framework.

Other metaphors could be proposed.