• Aucun résultat trouvé

Adapting LDA Model to Discover Author-Topic Relations for Email Analysis

N/A
N/A
Protected

Academic year: 2021

Partager "Adapting LDA Model to Discover Author-Topic Relations for Email Analysis"

Copied!
13
0
0

Texte intégral

(1)

Publisher’s version / Version de l'éditeur:

Vous avez des questions? Nous pouvons vous aider. Pour communiquer directement avec un auteur, consultez la première page de la revue dans laquelle son article a été publié afin de trouver ses coordonnées. Si vous n’arrivez pas à les repérer, communiquez avec nous à [email protected].

Questions? Contact the NRC Publications Archive team at

[email protected]. If you wish to email the authors directly, please see the first page of the publication for their contact information.

https://publications-cnrc.canada.ca/fra/droits

L’accès à ce site Web et l’utilisation de son contenu sont assujettis aux conditions présentées dans le site LISEZ CES CONDITIONS ATTENTIVEMENT AVANT D’UTILISER CE SITE WEB.

10th International Conference on Data Warehousing and Knowledge Discovery

(DaWaK 2008) [Proceedings], pp. 337-346, 2008

READ THESE TERMS AND CONDITIONS CAREFULLY BEFORE USING THIS WEBSITE.

https://nrc-publications.canada.ca/eng/copyright

NRC Publications Archive Record / Notice des Archives des publications du CNRC :

https://nrc-publications.canada.ca/eng/view/object/?id=9a8cac81-1dcf-4a5a-b905-7b002bb891e8

https://publications-cnrc.canada.ca/fra/voir/objet/?id=9a8cac81-1dcf-4a5a-b905-7b002bb891e8

NRC Publications Archive

Archives des publications du CNRC

This publication could be one of several versions: author’s original, accepted manuscript or the publisher’s version. / La version de cette publication peut être l’une des suivantes : la version prépublication de l’auteur, la version acceptée du manuscrit ou la version de l’éditeur.

For the publisher’s version, please access the DOI link below./ Pour consulter la version de l’éditeur, utilisez le lien DOI ci-dessous.

https://doi.org/10.1007/978-3-540-85836-2_32

Access and use of this website and the material on it are subject to the Terms and Conditions set forth at

Adapting LDA Model to Discover Author-Topic Relations for Email

Analysis

(2)

National Research Council Canada Institute for Information Technology Conseil national de recherches Canada Institut de technologie de l'information

Adapting LDA Model to Discover

Author-Topic Relations for Email Analysis *

Geng, L., Wang, H., Wang, X., Korba, L.

September 2008

* published in the Proceedings of the 10th International Conference on Data

Warehousing and Knowledge Discovery (DaWak 2008). Turin, Italy. September 1-5, 2008. NRC 50384.

Copyright 2008 by

National Research Council of Canada

Permission is granted to quote short excerpts and to reproduce figures and tables from this report, provided that the source of such material is fully acknowledged.

(3)

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

(4)

1 , , " , , , " / $ " ( > "/ +0 " / , " " , " / 4 6( 0 * , <0 = " " " 1 +0 " , 4? @6( , " " , " * , ( & +0 " 0 " , $ , , " , " ( $ / , , 0 " $ " " $ " & ( ( ( * $ " " $ " ( , $ " / / / $ , $ ( # 1 , $ $ $ $ " $ ( - A - A , $ " $ 1 " ( ! * $ " " $ " $ "( , , $ , , " , +0 " " $ " * , ( " $ " , +0 " " / " * , " * , ( $ " * , " * , & ( , , " / , +0 " 0 " ( , , 3 " $ ( ; " +0 " 0 " " , " , " +0 " ( ; B $ , , / , 0 " " , " +0 " ( ; C , 1, " " " " ( ; 9 " , , " " $ &(

!

+0 / " " $ $ " " " " / ( " " / , " , " / $ " ( , +0 , , " / , ( $ " " , " , " , / $ " ( , , " , "( , $ " & , "

=

=

=

=

<

D

=

<

=

=

<

< = $

<

=

=

, , $ , " $ " & " E

<

D

=

=

, $ " " , (

(5)

- 0 B , ( " , , " / $ " $ " (

=

D

<

= <

=

=

φ

" / $ " , "

θ

< =

=

<

=

" / , " ( ,

φ

"

θ

" $ $ " , / , " $ , , , " , / ( / " , " , " " ,

φ

"

θ

( ( , *$ " " " " * , " ( , " / " , ( , * " " , $ *" / $ " " / / ( , " " , " , " / ,, 1 " 4B6( # +0 " , , " " $ " & " " , $ " & , " " , $ " & ( " " , $ A

α

α

β

β

= = − −

+

+

+

+

=

D

(((=

<

< = $

=

, , & , , $ " & " 7F8 & $ / " ( , $ " & " "

α

"

β

, , " , " , , ( - , " ,, , /

α

"

β

" " 4 C6( 0 $ "* , 1 " , *" 1 " , , , " < =( ×

=

(((

(((

(((

(((

(((

(((

×

=

(((

(((

(((

(((

(((

(((

"* , 1 , *+ 1 $ "* , 1 " , " & E , *" 1

(6)

, " $ " & " " ( 0 , , ,

φ

"

θ

" " $ "* , 1 " , *" 1 $ <B= " <C=(

=

+

+

=

= <

G

β

β

φ

<B=

α

α

θ

=

+

+

=

= <

G

<C= , , " / , $ ( ( 3 " ( # H " II , B " " $ " & " B( ! , , " ( C( ; , , " , " , B 9( .," 1 " $ $ , 5( , B $ " & / "( :( - " 0 " 1 +0 " / / $ " $ " / , ( 0 " $ " " " $ $ , A " , 4?6( " / ( $ / < 1 , $ " " $ $ " "" " " =( $ , , , 0 " , ( $ " , , " 0 " / " " ,, +0 " " " ( $ 0 " " , $ " , , $ " " , " ( ( $ " $ " "( * , " " * , , , ( # " & $ / / $ , " * , " ( , , " , " +0 " " / " , ,( " $ "( # , +0 " " / " * , ,( * , , " " * , 1 $ ;J A

(7)

- 0 9 ; < = F ! = < = K <" = < #$ % <" =$ , $ < = " , " " * , 1( <" = " , , $ " " ( # , " , " +0 " " 0 " < $ $ , , =( " , " +0 " / " " / / " , ( , " " +0 " ( ( " * , & , ( *" " , , " / * , ( " 0+ " 0+ " " * , , $ # < =( 3 $ + " θ 0 α α φ β 3 $ + " θ α α φ β < = ; , " 0 " < = 0" , " +0 " " , " 0 " " " , " +0 "

#

$

# " " , " , " / , " , / $ " & $ ( / " $ " , " $ " " " / " " ( ; 0 " " " , " +0 " , / " " " " / " , " " " $ " " , " / " , " " , " " $ ( , " / " , " , , *$ ( , $ " $ "

(8)

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

∑∑

= =

=

+

$ " , , & $ " (

(9)

- 0 : * , $ / &L " / < *" = / $ " / " , ( / " " "

= ≠ =

=

(

,-

<

=

$ ( < = " * " $ , " , " " "

=

=

<

=

<

=

<

=

<

=

<

=

<

<

=

<

=

+

( (

(

(

.

(

.

(

.

(

(

(

( 0 *" / , $ " " "(

%

&

" " 1, " " , " , " +0 " " 0 " ( , , " , $ " , " $ " " , / " / $ " $ , ( $ , " " * , A * , " " * , " ( 0 * , " " $ " , $ * , " " $ " , ( $ , * , A , "* * , " 1 "* * , ( , "* * , $ , / / " , ( 1 "* * , $ , / / " $ ( " * , " " * , # B $ 1 , ( * , " $ , " * , / " * , " $ , "* * , $ , " , ( # 1 , # B< = , " , " , " , B " , C " , ( $ " ( " " , / ( - " 9@@@ $ / @@ $ " ( @ , $ , @ $ " ( @ " $ , ( 0 " " , " +0 " $ , @ $ $ " & $ , "/ ( , <; , , ,, , , $ " " 4C6=( $ 4?6 " α H 9@I "β H @(@ (

(10)

0 + , 0 + , 0 + B , B < = ; * , " , "* * , 0 + , 0 + , 0 + B , < = ; * , " 1 "* , 0 + , , 0 + , , 0 + B , B , C < = Q * , " * , 0 + , , 0 + , , B 0 B + B , B , <"= Q * , " 1 "* * , " # # * , " " * , # C 1* 1 " " " * 1 " " $ " " / " , " " ; B( # C $ +0 " , 0 " $ "

(11)

- 0 ? " @(B( # C< = $ * , " " , " * , +0 " , 0 " ( 0 " 1 " " " * ( # C< = $ * , " " 1 " * , +0 , 0 " ( , 0 " * $ " * " " * , ( # C< = $ , * , " " 1 " " +0 K , 0 " ( , 0 * / "( < = ; *; , " < = ; *Q 1 " < = Q , *Q 1 " " % + , *$ " " " / " " # " / " ( , " " $ " / " , $ " , $ "

(12)

" " / " , ( " " $ , $ " " / " , $ " " , ( % " " $ " " / " , $ / " " $ " " / " M " / , $ 1, ( " " , *$ " " " * , " @(B " $ ( + * , " " R ; *; , " ; *Q 1 " Q , *Q 1 " +0 ?@ ?@ ?@ 0 99 S@ ?@ " " 1, - " 4 6 , +0 " 0 " ( / " , @ @@ " " " , " *" # 9( # 9< = $ $ , " , / , " 0 " $ , " +0 " ( * , +0 " / , " , " 0 " , " " " $ , ( 0 +0 " , " 0 " * , ( < = - , < = " " ' ! , 0 " +0 " - " # 9< = $ +0 " / 0 " " , " , ( +0 " , " $ * , ( 0 $ , " , " $ / $ "

(13)

- 0 ( $ , * , 0 " " " $ +0 " (

' $

"

(

)

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

Références

Documents relatifs

L’archive ouverte pluridisciplinaire HAL, est destinée au dépôt et à la diffusion de documents scientifiques de niveau recherche, publiés ou non, émanant des

In the light of the state of the art, we propose an original approach for expert finding consisting in combining text mining, more precisely machine learning algorithms applied on

When applying correlation algorithms, we cor- related each target alert with all other non-background alerts (i.e., the back- ground alerts identified by the Ljung-Box test

To explain why one combination of fitness func - tion and distance measure performs better than another, the correlation between the best fitness value and the clustering accuracy

Our preliminary results are obtained us- ing a methodology that pulls strengths from several machine learning techniques, including Latent Dirichlet Allocation (LDA) for topic

The relations between requirements, multidimensional design and underlying data sources were focused in [10] which applied a goal-oriented approach to requirement

All needed UML classes and associations are already denoted in our shared class figure (Figure 4). At the technical layer, we describe all data movement- related dependencies as a

We will use a representation of Devroye [4, 5] for the binary search tree, and a well-known bijection between binary trees and recursive trees, together with different applications