Say I have a sequence of documents clicked by a user, how can I mine the identical or semanticly similar word/knowledge/phrases shared among different documents?
Maybe someone can give a paper or subject relating to my goal?
$\begingroup$
$\endgroup$
Add a comment
|
$\begingroup$
$\endgroup$
1
The simplest approach would be extracting the keywords from both documents and by using them as features you can compare the mutuality of the papers.
A better approach would be, build building knowledge graphs for the documents then comparing them. This paper illustrates a way of doing that.
However, if you want to build a deeper knowledge about the issue, for example how text-similarity, plagiarism or recommendation systems work, A. Rajaraman and J. D. Ullman, Mining of Massive Datasets, Cambridge University Press, 2011 has very good content about the topic.
-
$\begingroup$ thank you very much, however, what I want to do is not Knowledge Extraction, rather I want to **Find both Same/Similar knowledges and words/phrases among documents. $\endgroup$ – namespace_Pt Nov 10 '20 at 16:13
