Living Reference Work Entry

Encyclopedia of Database Systems

pp 1-4

Date: Latest Version

Crowd Mining and Analysis

  • Yael AmsterdamerAffiliated withDepartment of Computer Science, Bar Ilan University Email author 
  • , Tova MiloAffiliated withSchool of Computer Science, Tel Aviv University

Definition

Crowd mining is the process of identifying data patterns in human knowledge, with the assistance of a crowd of web users. The focus is on domain areas in which data is partially or entirely undocumented and where humans are the main source of knowledge, such as data that involves people’s habits, experiences, and opinions. A key challenge in mining such data is that the human knowledge forms an open world and it is thus difficult to know what kind of information one should be looking for.

In classic databases, a similar problem is addressed by data mining techniques that identify interesting patterns in recorded data such as relational databases or textual documents. These techniques, however, are not suitable for the crowd. This is mainly due to properties of the human memory, such as the tendency to remember simple trends and summaries rather than exact details, which should be taken into consideration when gathering and analyzing human ...

This is an excerpt from the content