A Data Type-Driven Property Alignment Framework for Product Duplicate Detection on the Web

G van Rooij; R (Ravi) Sewnarain; M Skogholt; T van der Zaan; Flavius Frasincar; Kim Schouten

doi:10.1007/978-3-319-48740-3_28

A Data Type-Driven Property Alignment Framework for Product Duplicate Detection on the Web

G van Rooij
, R (Ravi) Sewnarain
, M Skogholt
, T van der Zaan
, Flavius Frasincar^*
, Kim Schouten

^*Corresponding author for this work

Econometrics

Research output: Chapter/Conference proceeding › Conference proceeding › Academic › peer-review

4 Citations (Scopus)

5 Downloads (Pure)

Abstract

During the last decade daily life has morphed into a world of broadband ubiquity, where devices facilitate constant engagement. As a consequence of this, the area of e-commerce has seen an immense growth. Despite the market opportunities for retailers and the ease for customers to acquire products through webshops, the shift to digital retail has its drawbacks. For example, it leads to cluttered and incomparable information among different webshops, which calls for an automated method to regain homogeneity in product representations. This paper presents a product duplicate detection solution, which exploits a data type-driven property alignment framework. Based on the performed experiment, we show a statistically significant improvement of the F
-score from 47.91 % to 78.13 % compared to an existing state-of-the-art approach.

Original language	English
Title of host publication	17th International Conference on Web Information Systems Engineering (WISE 2016)
Publisher	Springer-Verlag
Pages	380-395
Number of pages	16
Volume	10041
DOIs	https://doi.org/10.1007/978-3-319-48740-3_28
Publication status	Published - 2 Nov 2016

Research programs

EUR ESE 32

Access to Document

10.1007/978-3-319-48740-3_28

wise2016aFinal published version, 233 KBLicence: Article 25fa Dutch Copyright Act

Cite this

@inproceedings{048e6af7e2b44b5f83e85577bbe58c8a,

title = "A Data Type-Driven Property Alignment Framework for Product Duplicate Detection on the Web",

abstract = "During the last decade daily life has morphed into a world of broadband ubiquity, where devices facilitate constant engagement. As a consequence of this, the area of e-commerce has seen an immense growth. Despite the market opportunities for retailers and the ease for customers to acquire products through webshops, the shift to digital retail has its drawbacks. For example, it leads to cluttered and incomparable information among different webshops, which calls for an automated method to regain homogeneity in product representations. This paper presents a product duplicate detection solution, which exploits a data type-driven property alignment framework. Based on the performed experiment, we show a statistically significant improvement of the F -score from 47.91 \% to 78.13 \% compared to an existing state-of-the-art approach.",

author = "\{van Rooij\}, G and Sewnarain, \{R (Ravi)\} and M Skogholt and \{van der Zaan\}, T and Flavius Frasincar and Kim Schouten",

year = "2016",

month = nov,

day = "2",

doi = "10.1007/978-3-319-48740-3\_28",

language = "English",

volume = "10041",

pages = "380--395",

booktitle = "17th International Conference on Web Information Systems Engineering (WISE 2016)",

publisher = "Springer-Verlag",

address = "Germany",

}

A Data Type-Driven Property Alignment Framework for Product Duplicate Detection on the Web. / van Rooij, G; Sewnarain, R (Ravi); Skogholt, M et al.
17th International Conference on Web Information Systems Engineering (WISE 2016). Vol. 10041 Springer-Verlag, 2016. p. 380-395.

Research output: Chapter/Conference proceeding › Conference proceeding › Academic › peer-review

TY - GEN

T1 - A Data Type-Driven Property Alignment Framework for Product Duplicate Detection on the Web

AU - van Rooij, G

AU - Sewnarain, R (Ravi)

AU - Skogholt, M

AU - van der Zaan, T

AU - Frasincar, Flavius

AU - Schouten, Kim

PY - 2016/11/2

Y1 - 2016/11/2

N2 - During the last decade daily life has morphed into a world of broadband ubiquity, where devices facilitate constant engagement. As a consequence of this, the area of e-commerce has seen an immense growth. Despite the market opportunities for retailers and the ease for customers to acquire products through webshops, the shift to digital retail has its drawbacks. For example, it leads to cluttered and incomparable information among different webshops, which calls for an automated method to regain homogeneity in product representations. This paper presents a product duplicate detection solution, which exploits a data type-driven property alignment framework. Based on the performed experiment, we show a statistically significant improvement of the F -score from 47.91 % to 78.13 % compared to an existing state-of-the-art approach.

AB - During the last decade daily life has morphed into a world of broadband ubiquity, where devices facilitate constant engagement. As a consequence of this, the area of e-commerce has seen an immense growth. Despite the market opportunities for retailers and the ease for customers to acquire products through webshops, the shift to digital retail has its drawbacks. For example, it leads to cluttered and incomparable information among different webshops, which calls for an automated method to regain homogeneity in product representations. This paper presents a product duplicate detection solution, which exploits a data type-driven property alignment framework. Based on the performed experiment, we show a statistically significant improvement of the F -score from 47.91 % to 78.13 % compared to an existing state-of-the-art approach.

U2 - 10.1007/978-3-319-48740-3_28

DO - 10.1007/978-3-319-48740-3_28

M3 - Conference proceeding

VL - 10041

SP - 380

EP - 395

BT - 17th International Conference on Web Information Systems Engineering (WISE 2016)

PB - Springer-Verlag

ER -

A Data Type-Driven Property Alignment Framework for Product Duplicate Detection on the Web

Abstract

Research programs

Access to Document

Fingerprint

Cite this