Never trust a human

As search engines become ever more sophisticated, human inadequacies are becoming the biggest limiting factor. A survey by the NEC Research Institute in Princeton, New Jersey, reveals that up to 70 per cent of web users typically type in only one keyword or search term. This is a recipe for obtaining long lists of irrelevant hits. Yet even among the staff of the NEC Research Institute, who should be web-savvy, almost half fail to define their searches more precisely (see figure).

Figure 1

Never trust a human

Statistics such as these have convinced search engine developers that there is little point trying to get users to read the ‘search tips’ or use the advanced search options provided by most search engines.

To address this problem, more sophisticated engines are now building classifications hidden behind the search interface, which allow them to prompt for more information when presented with ambiguous search terms. Asked to search for ‘green’, for example, the engine might ask whether the user wants to search for green beans, green parties, and so on.