orange-text / docs / old-html / widgets / catalog / Text / TextDistance.htm

mitar 4d843d6 

<title>Text distance</title>
<link rel=stylesheet href="../../../style.css" type="text/css" media=screen>
<link rel=stylesheet href="style-print.css" type="text/css" media=print></link>


<h1>Text distance</h1>

<img class="screenshot" src="../icons/TextDistance.png">
<p>Compute distances between documents.</p>



<DL class=attributes>
<DT>Examples (ExampleTable)</DT>
<dd>Attribute-valued data set.</dd>

<DL class=attributes>
<DT>Distance matrix (SymMatrix)</DT>
<DD>Matrix where rows and columns are documents and values are distances between them.</DD>


<p>This is a simple widget that takes an ExampleTable with text features as metaatributes
and computes the distances between documents based on those features. The Matrix
type box is used to specify the output matrix type. If Similarity matrix is chosen,
a larger value in the matrix means that two documents are more similar, whereas
choosing the Distance matrix option means that a larger value will indicate greater
distance between two documents.</p>

<a href="TextDistance.png"><img class="schema" src="TextDistance.png" alt="Text distance widget"></a>


<p>Below is a simple example how to use this widget. The input is fed
from the <a href="BagOfWords.htm">Bag of words</a> widget, and the output
to the Hierarhical Clustering widget.</p>

<a href="TextDistance-Example.png"><img class="schema"
src="TextDistance-Example.png" alt="Schema with TextDistance widget"></a>