Singular Value Decomposition in Text Mining. Ram Akella University of California Berkeley Silicon Valley Center/SC Lecture 4b February 9, 2011. Class Outline. Summary of last lecture Indexing Vector Space Models Matrix Decompositions Latent Semantic Analysis Mechanics
Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author.While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server.
University of California
Silicon Valley Center/SC
February 9, 2011
How can we retrieve information using a search engine?.
To buid an automatic index, we need to perform two steps:
Decide what information or parts of the document should be indexed
Decide with words should be used in order to obtain the best representation of the semantic content of documents.
After this preliminary analysis we need to perform another preprocessing of the data
Once we have eliminated the stop words and apply the stemmer to the document we can construct:
Where a is the document and q is the query vector
Cos 2=Cos 3=0.4082
Cos 5=Cos 6=0.500
With a threshold of 0.5, the 5th and the 6th would be retrieved.
Local Term Weights
Global Term Weights
Will have small cosine
but are related
Will have large cosine
but not truly related
To produce a reduced –rank approximation of the document matrix, first we need to be able to identify the dependence between columns (documents) and rows (terms)
Where Q is an mXm orthogonal matrix and R is an
mX m upper triangular matrix
V is nnSingular Value Decomposition (SVD)
Where the columns U are orthogonal eigenvectors of AAT.
The columns of V are orthogonal eigenvectors of ATA.
Eigenvalues 1 … r of AATare the square root of the eigenvalues of ATA.
The V matrix refers to terms
and U matrix refers to documents
This formula can be simplified as
Apply the LSA method to the following technical memo titles
c1: Human machine interface for ABC computer applications
c2: A survey of user opinion of computersystemresponsetime
c3: The EPSuserinterface management system
c4: System and humansystem engineering testing of EPS
c5: Relation of user perceived responsetime to error measurement
m1: The generation of random, binary, ordered trees
m2: The intersection graph of paths in trees
m3: Graphminors IV: Widths of trees and well-quasi-ordering
m4: Graphminors: A survey
First we construct the document matrix
The Resulting decomposition is the following
The word user seems to have presence in the documents where the word human appears