It is obvious that answering the first question is a condition to solve the second. In the same way as human archaeologists, the automated archaeologist needs to know what, where and when before explaining why some social group made something, and how. That is to say, only after having explained why archaeological observables are the way they are in terms of the consequence of some social activity or bio-geological process performed in the past or in the present, the automated archaeologist will try to explain more abstract causal processes.
TopNeuroclassification As Social Explanation
Since the beginning of the book, we know that solving archaeological problems implies answering a double causality question:
- •
Given the perception of visual inputs, the automated archaeologist should explain what social activity produced in the past the evidence perceived in the present.
- •
Once it knows what social activity was performed, where, and when, the automated archaeologist should explain why such activities were performed there and then, and in what way.
It is obvious that answering the first question is a condition to solve the second. In the same way as human archaeologists, the automated archaeologist needs to know what, where and when before explaining why some social group made something, and how. That is to say, only after having explained why archaeological observables are the way they are in terms of the consequence of some social activity or bio-geological process performed in the past or in the present, the automated archaeologist will try to explain more abstract causal processes.
In previous chapters, we have been dealing, for the most part, with the first kind of problem. Automated discovery programs allow describing the action or process, which most probably caused the actual appearance of the archaeological record. Nevertheless, the automated archaeologist has not yet discovered why that activity took place there and then. Things become a bit more difficult when the automated archaeologist moves from the explanation of objects to the explanation of action and social behavior, because it should take into account people and people motivations.
The simplest way of understating social behavior is by classifying it. That means an automated archaeologist will explain people and social acts by recognizing them as members of some previously defined classes of people or events. Social explanation would then consist in the apprehension of the individual case as an instance of a general type, a type for which the intelligent machine should have a detailed and well-informed representation. Such a representation allows the system to anticipate aspects of social activity so far unperceived.
It is usual in the social sciences to classify people according to social attributes. Computational intelligence tools can help in such a classification. In the social sciences, a neural network can classify a population into homogenous groups using factors such as age, sex, and other socio-economic variables to infer social status or position. A classical example is that of Meraviglia (1996, 2001) on social mobility, where input variables “gender,” “father’s education,” “father’s class position when age of respondent is 14,” and so on, are used to predict “son’s (or daughter’s) current class position.” Although this can be a good example of social explanation, no any causal explanation should be generated in that way. After all, we have already examined many examples of causal explanation based on alternative approaches, and we will present some other ways at the end of the chapter. In any case, we can explore the explanatory possibilities of “social classification” beyond trivial associations.
The most obvious way of classifying people to understand social dynamics in archaeology can be done in burial analysis. By studying the differences between graves according to the material remains of funerary rituals, an automated archaeologist can understand how social personality was built by a human group in the past. Wealth and poverty in acient times, prehistoric social elites and inequality, past evidence of social marginality can be discovered by studying the quantity and diversity of archaeological grave goods, ways of body manipulation, etc. In general, the quantity of labor invested in a funerary ritual is a good estimation of the social importance of the buried individual.