Text Mining with Latent Semantic Analysis

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F62156489%3A43110%2F15%3A43909062" target="_blank" >RIV/62156489:43110/15:43909062 - isvavai.cz</a>

Výsledek na webu

—

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

Text Mining with Latent Semantic Analysis

Popis výsledku v původním jazyce

Latent semantic analysis is presented as an advanced model for representing text data used in order to eliminate problems with processing large amount of text documents. The paper describes information retrieval, classification, and clustering experiments with real world document collections in four different natural languages. Different preprocessing techniques are applied to the data and the experiments are carried out with the original data and the data projected to a reduced dimensionality space after singular value decomposition. The results show that preprocessing influenced the results differently according to the language of the documents and that singular value decomposition has a positive impact mainly on the computational aspects of the textmining processes.

Název v anglickém jazyce

Text Mining with Latent Semantic Analysis

Popis výsledku anglicky

Latent semantic analysis is presented as an advanced model for representing text data used in order to eliminate problems with processing large amount of text documents. The paper describes information retrieval, classification, and clustering experiments with real world document collections in four different natural languages. Different preprocessing techniques are applied to the data and the experiments are carried out with the original data and the data projected to a reduced dimensionality space after singular value decomposition. The results show that preprocessing influenced the results differently according to the language of the documents and that singular value decomposition has a positive impact mainly on the computational aspects of the textmining processes.

Druh

O - Ostatní výsledky

CEP obor

IN - Informatika

OECD FORD obor

—

Projekt

—

Návaznosti

S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2015

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů