David Spretke
Research Student in the PhD program from 01.11.2008 to 31.01.2010.advisorsProf. Dr. Daniel Keimorganisational data
|
![]() |
project description
Text mining, also known as text data mining or knowledge discovery from textual databases, refers to the process of extracting interesting and non-trivial patterns or knowledge from unstructured text documents.More than 80% of the information that is stored in today's databases is in textual form. Effective and efficient methods are needed to deal with this information sources that are encoded in written natural language.
In this context, the aim of our research project is to detect potentially useful quasi-semantic properties in textual documents such as positive or negative statements with respect to an entity or readability. Such properties have to be specified and adequate low-level features have to be chosen that can be used to approximate the quasi-semantic property. Thus, one of the challenges that have to be faced is how to effectively integrate the human into the feature engineering process.
Visual Analytics techniques are needed to let the human contribute his background knowledge and the ability to semantically interpret a text. This information is needed to find an appropriate combination of low-level features.
publications
The following list of publications covers only those, which are or were published during participation at the Graduiertenkolleg / PhD program.
| 2010 |
|


