Content determination is the process of deciding what information to include or exclude in a document. It involves considering the intended audience, style, and format. Humans typically perform this task, but computers can use techniques such as the outline, statistical, and explicit reasoning methods. The ultimate goal is to develop a computer capable of understanding data and producing summaries based on the objectives of the text.
Content determination occurs when a person, group, or program decides what information should be included or excluded within a document or text. It is related to concepts related to document structuring. It is also related to natural language generation and computational linguistics. Each area of study uses content determination to examine how information is chosen.
When considering what to include in a document or text, the compiler will either have conducted his research or been provided with all available data. Content determination covers the ways in which this information is reduced to the final document. This is done by determining what angle or focus of the text is and what information within the text is relevant to it.
The second consideration in determining content is its style. This tends to depend on the nature of the intended audience. The audience’s intellect and subject familiarity alter the lexical density and complexity of the information imparted. Academics will tend to produce denser writing than gossip magazines, for example. Other considerations include format size, whether it will be a book, article, or text message.
Each state of content determination is done by a human. There is the researcher and the writer, who are often, but not always, the same person, and then the editor or publishers. Each level has an opinion on what content is relevant to the goal of the text. Computational linguists and computer engineers have looked for ways to reproduce this system using computer programs instead of relying on humans.
There are three computational techniques employed by computers with regards to content determination. The ‘outline technique’ is based on the examination of written texts. Use the pre-screened texts as a basis for the information to be included in the produced text. The “statistical” method automatically determines the content based on a number of general statistics. “Explicit reasoning” uses artificial intelligence (AI) to examine and filter information.
The overall goal of content determination is to understand how documents are produced so that they can be reproduced using computers. The result of such success will be a computer capable of receiving data, filtering it and producing summaries of the most important information. The computer will base such documents not only on the information, but on the objectives of the text produced. In the vein of Chinese room theory, this could mean that the computer is capable of understanding data rather than being able to replicate and calculate.
Protect your devices with Threat Protection by NordVPN