Open-categorical text classification based on multi-LDA models

Verfasser / Beitragende:
[Ruiji Fu, Bing Qin, Ting Liu]
Ort, Verlag, Jahr:
2015
Enthalten in:
Soft Computing, 19/1(2015-01-01), 29-38
Format:
Artikel (online)
ID: 605468419
LEADER caa a22 4500
001 605468419
003 CHVBK
005 20210128100316.0
007 cr unu---uuuuu
008 210128e20150101xx s 000 0 eng
024 7 0 |a 10.1007/s00500-014-1374-x  |2 doi 
035 |a (NATIONALLICENCE)springer-10.1007/s00500-014-1374-x 
245 0 0 |a Open-categorical text classification based on multi-LDA models  |h [Elektronische Daten]  |c [Ruiji Fu, Bing Qin, Ting Liu] 
520 3 |a We present a new and realistic problem, open-categorical text classification, which requires us to classify documents without the categorization system known beforehand. To solve this problem, we propose a novel approach to construct the categorization system and classify documents based on multi-latent Dirichlet allocation (LDA) models. We cluster topics and extract topical keywords to help category annotation. Subsequently, the LDA models are applied to predict the categories of documents comprehensively. Our result, a macro-averaged F1 measure of 84.02%, outperforms the state-of-the-art supervised and semi-supervised text classification methods. 
540 |a Springer-Verlag Berlin Heidelberg, 2014 
690 7 |a Topic model  |2 nationallicence 
690 7 |a Text classification  |2 nationallicence 
690 7 |a Categorization system construction  |2 nationallicence 
700 1 |a Fu  |D Ruiji  |u Harbin Institute of Technology, 6th Floor, No.29, Jiaohua Street, Nangang District, 150001, Harbin, People's Republic of China  |4 aut 
700 1 |a Qin  |D Bing  |u Harbin Institute of Technology, 6th Floor, No.29, Jiaohua Street, Nangang District, 150001, Harbin, People's Republic of China  |4 aut 
700 1 |a Liu  |D Ting  |u Harbin Institute of Technology, 6th Floor, No.29, Jiaohua Street, Nangang District, 150001, Harbin, People's Republic of China  |4 aut 
773 0 |t Soft Computing  |d Springer Berlin Heidelberg  |g 19/1(2015-01-01), 29-38  |x 1432-7643  |q 19:1<29  |1 2015  |2 19  |o 500 
856 4 0 |u https://doi.org/10.1007/s00500-014-1374-x  |q text/html  |z Onlinezugriff via DOI 
898 |a BK010053  |b XK010053  |c XK010000 
900 7 |a Metadata rights reserved  |b Springer special CC-BY-NC licence  |2 nationallicence 
908 |D 1  |a research-article  |2 jats 
949 |B NATIONALLICENCE  |F NATIONALLICENCE  |b NL-springer 
950 |B NATIONALLICENCE  |P 856  |E 40  |u https://doi.org/10.1007/s00500-014-1374-x  |q text/html  |z Onlinezugriff via DOI 
950 |B NATIONALLICENCE  |P 700  |E 1-  |a Fu  |D Ruiji  |u Harbin Institute of Technology, 6th Floor, No.29, Jiaohua Street, Nangang District, 150001, Harbin, People's Republic of China  |4 aut 
950 |B NATIONALLICENCE  |P 700  |E 1-  |a Qin  |D Bing  |u Harbin Institute of Technology, 6th Floor, No.29, Jiaohua Street, Nangang District, 150001, Harbin, People's Republic of China  |4 aut 
950 |B NATIONALLICENCE  |P 700  |E 1-  |a Liu  |D Ting  |u Harbin Institute of Technology, 6th Floor, No.29, Jiaohua Street, Nangang District, 150001, Harbin, People's Republic of China  |4 aut 
950 |B NATIONALLICENCE  |P 773  |E 0-  |t Soft Computing  |d Springer Berlin Heidelberg  |g 19/1(2015-01-01), 29-38  |x 1432-7643  |q 19:1<29  |1 2015  |2 19  |o 500