A Hybrid Recommendation System Based on Bidirectional Encoder Representations

Irem Islek; Sule Gunduz Oguducu

doi:10.1007/978-3-030-65965-3_14

A Hybrid Recommendation System Based on Bidirectional Encoder Representations

Irem Islek^*, Sule Gunduz Oguducu

^*Corresponding author for this work

Department of Artificial Intelligence and Data Engineering

Istanbul Technical University

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

4 Citations (Scopus)

Abstract

Using auxiliary data about items provides more accurate item recommendations when utilizing deep learning in the recommendation system. Users often read item descriptions during online shopping, which contain key information about the item and its features. However the item descriptions are in unstructured form and using them in the deep learning model is a problem. In this study, we integrate a pioneering Natural Language Processing technique into a recommendation system to create an item embedding vector from unstructured item description text. The experimental results show that the proposed approach is efficient in generating more accurate recommendations by creating item embedding vectors from unstructured item description text.

Original language	English
Title of host publication	ECML PKDD 2020 Workshops - Workshops of the European Conference on Machine Learning and Knowledge Discovery in Databases ECML PKDD 2020
Subtitle of host publication	SoGood 2020, PDFL 2020, MLCS 2020, NFMCP 2020, DINA 2020, EDML 2020, XKDD 2020 and INRA 2020, Proceedings
Editors	Irena Koprinska, Annalisa Appice, Luiza Antonie, Riccardo Guidotti, Rita P. Ribeiro, João Gama, Yamuna Krishnamurthy, Donato Malerba, Michelangelo Ceci, Elio Masciari, Peter Christen, Erich Schubert, Monreale Monreale, Salvatore Rinzivillo, Andreas Lommatzsch, Michael Kamp, Corrado Loglisci, Albrecht Zimmermann, Özlem Özgöbek, Ricard Gavaldà, Linara Adilova, Pedro M. Ferreira, Ibéria Medeiros, Giuseppe Manco, Zbigniew W. Ras, Eirini Ntoutsi, Arthur Zimek, Przemyslaw Biecek, Benjamin Kille, Jon Atle Gulla
Publisher	Springer Science and Business Media Deutschland GmbH
Pages	225-236
Number of pages	12
ISBN (Print)	9783030659646
DOIs	https://doi.org/10.1007/978-3-030-65965-3_14
Publication status	Published - 2020
Event	Workshops of the 20th Joint European Conference on Machine Learning and Knowledge Discovery in Databases, ECML PKDD - Ghent, Belgium Duration: 14 Sept 2020 → 18 Sept 2020

Publication series

Name	Communications in Computer and Information Science
Volume	1323
ISSN (Print)	1865-0929
ISSN (Electronic)	1865-0937

Conference

Conference	Workshops of the 20th Joint European Conference on Machine Learning and Knowledge Discovery in Databases, ECML PKDD
Country/Territory	Belgium
City	Ghent
Period	14/09/20 → 18/09/20

Bibliographical note

Publisher Copyright:
© 2020, Springer Nature Switzerland AG.

Keywords

Bidirectional encoder representations
Hybrid recommendation systems
Recommendation models

Access to Document

10.1007/978-3-030-65965-3_14

Cite this

Islek, I., & Oguducu, S. G. (2020). A Hybrid Recommendation System Based on Bidirectional Encoder Representations. In I. Koprinska, A. Appice, L. Antonie, R. Guidotti, R. P. Ribeiro, J. Gama, Y. Krishnamurthy, D. Malerba, M. Ceci, E. Masciari, P. Christen, E. Schubert, M. Monreale, S. Rinzivillo, A. Lommatzsch, M. Kamp, C. Loglisci, A. Zimmermann, Ö. Özgöbek, R. Gavaldà, L. Adilova, P. M. Ferreira, I. Medeiros, G. Manco, Z. W. Ras, E. Ntoutsi, A. Zimek, P. Biecek, B. Kille, ... J. A. Gulla (Eds.), ECML PKDD 2020 Workshops - Workshops of the European Conference on Machine Learning and Knowledge Discovery in Databases ECML PKDD 2020: SoGood 2020, PDFL 2020, MLCS 2020, NFMCP 2020, DINA 2020, EDML 2020, XKDD 2020 and INRA 2020, Proceedings (pp. 225-236). (Communications in Computer and Information Science; Vol. 1323). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-3-030-65965-3_14

Islek, Irem ; Oguducu, Sule Gunduz. / A Hybrid Recommendation System Based on Bidirectional Encoder Representations. ECML PKDD 2020 Workshops - Workshops of the European Conference on Machine Learning and Knowledge Discovery in Databases ECML PKDD 2020: SoGood 2020, PDFL 2020, MLCS 2020, NFMCP 2020, DINA 2020, EDML 2020, XKDD 2020 and INRA 2020, Proceedings. editor / Irena Koprinska ; Annalisa Appice ; Luiza Antonie ; Riccardo Guidotti ; Rita P. Ribeiro ; João Gama ; Yamuna Krishnamurthy ; Donato Malerba ; Michelangelo Ceci ; Elio Masciari ; Peter Christen ; Erich Schubert ; Monreale Monreale ; Salvatore Rinzivillo ; Andreas Lommatzsch ; Michael Kamp ; Corrado Loglisci ; Albrecht Zimmermann ; Özlem Özgöbek ; Ricard Gavaldà ; Linara Adilova ; Pedro M. Ferreira ; Ibéria Medeiros ; Giuseppe Manco ; Zbigniew W. Ras ; Eirini Ntoutsi ; Arthur Zimek ; Przemyslaw Biecek ; Benjamin Kille ; Jon Atle Gulla. Springer Science and Business Media Deutschland GmbH, 2020. pp. 225-236 (Communications in Computer and Information Science).

@inproceedings{a050d1f64834475385aa145469b781be,

title = "A Hybrid Recommendation System Based on Bidirectional Encoder Representations",

abstract = "Using auxiliary data about items provides more accurate item recommendations when utilizing deep learning in the recommendation system. Users often read item descriptions during online shopping, which contain key information about the item and its features. However the item descriptions are in unstructured form and using them in the deep learning model is a problem. In this study, we integrate a pioneering Natural Language Processing technique into a recommendation system to create an item embedding vector from unstructured item description text. The experimental results show that the proposed approach is efficient in generating more accurate recommendations by creating item embedding vectors from unstructured item description text.",

keywords = "Bidirectional encoder representations, Hybrid recommendation systems, Recommendation models",

author = "Irem Islek and Oguducu, {Sule Gunduz}",

note = "Publisher Copyright: {\textcopyright} 2020, Springer Nature Switzerland AG.; Workshops of the 20th Joint European Conference on Machine Learning and Knowledge Discovery in Databases, ECML PKDD ; Conference date: 14-09-2020 Through 18-09-2020",

year = "2020",

doi = "10.1007/978-3-030-65965-3_14",

language = "English",

isbn = "9783030659646",

series = "Communications in Computer and Information Science",

publisher = "Springer Science and Business Media Deutschland GmbH",

pages = "225--236",

editor = "Irena Koprinska and Annalisa Appice and Luiza Antonie and Riccardo Guidotti and Ribeiro, {Rita P.} and Jo{\~a}o Gama and Yamuna Krishnamurthy and Donato Malerba and Michelangelo Ceci and Elio Masciari and Peter Christen and Erich Schubert and Monreale Monreale and Salvatore Rinzivillo and Andreas Lommatzsch and Michael Kamp and Corrado Loglisci and Albrecht Zimmermann and {\"O}zlem {\"O}zg{\"o}bek and Ricard Gavald{\`a} and Linara Adilova and Ferreira, {Pedro M.} and Ib{\'e}ria Medeiros and Giuseppe Manco and Ras, {Zbigniew W.} and Eirini Ntoutsi and Arthur Zimek and Przemyslaw Biecek and Benjamin Kille and Gulla, {Jon Atle}",

booktitle = "ECML PKDD 2020 Workshops - Workshops of the European Conference on Machine Learning and Knowledge Discovery in Databases ECML PKDD 2020",

address = "Germany",

}

Islek, I & Oguducu, SG 2020, A Hybrid Recommendation System Based on Bidirectional Encoder Representations. in I Koprinska, A Appice, L Antonie, R Guidotti, RP Ribeiro, J Gama, Y Krishnamurthy, D Malerba, M Ceci, E Masciari, P Christen, E Schubert, M Monreale, S Rinzivillo, A Lommatzsch, M Kamp, C Loglisci, A Zimmermann, Ö Özgöbek, R Gavaldà, L Adilova, PM Ferreira, I Medeiros, G Manco, ZW Ras, E Ntoutsi, A Zimek, P Biecek, B Kille & JA Gulla (eds), ECML PKDD 2020 Workshops - Workshops of the European Conference on Machine Learning and Knowledge Discovery in Databases ECML PKDD 2020: SoGood 2020, PDFL 2020, MLCS 2020, NFMCP 2020, DINA 2020, EDML 2020, XKDD 2020 and INRA 2020, Proceedings. Communications in Computer and Information Science, vol. 1323, Springer Science and Business Media Deutschland GmbH, pp. 225-236, Workshops of the 20th Joint European Conference on Machine Learning and Knowledge Discovery in Databases, ECML PKDD, Ghent, Belgium, 14/09/20. https://doi.org/10.1007/978-3-030-65965-3_14

A Hybrid Recommendation System Based on Bidirectional Encoder Representations. / Islek, Irem; Oguducu, Sule Gunduz.
ECML PKDD 2020 Workshops - Workshops of the European Conference on Machine Learning and Knowledge Discovery in Databases ECML PKDD 2020: SoGood 2020, PDFL 2020, MLCS 2020, NFMCP 2020, DINA 2020, EDML 2020, XKDD 2020 and INRA 2020, Proceedings. ed. / Irena Koprinska; Annalisa Appice; Luiza Antonie; Riccardo Guidotti; Rita P. Ribeiro; João Gama; Yamuna Krishnamurthy; Donato Malerba; Michelangelo Ceci; Elio Masciari; Peter Christen; Erich Schubert; Monreale Monreale; Salvatore Rinzivillo; Andreas Lommatzsch; Michael Kamp; Corrado Loglisci; Albrecht Zimmermann; Özlem Özgöbek; Ricard Gavaldà; Linara Adilova; Pedro M. Ferreira; Ibéria Medeiros; Giuseppe Manco; Zbigniew W. Ras; Eirini Ntoutsi; Arthur Zimek; Przemyslaw Biecek; Benjamin Kille; Jon Atle Gulla. Springer Science and Business Media Deutschland GmbH, 2020. p. 225-236 (Communications in Computer and Information Science; Vol. 1323).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - A Hybrid Recommendation System Based on Bidirectional Encoder Representations

AU - Islek, Irem

AU - Oguducu, Sule Gunduz

PY - 2020

Y1 - 2020

N2 - Using auxiliary data about items provides more accurate item recommendations when utilizing deep learning in the recommendation system. Users often read item descriptions during online shopping, which contain key information about the item and its features. However the item descriptions are in unstructured form and using them in the deep learning model is a problem. In this study, we integrate a pioneering Natural Language Processing technique into a recommendation system to create an item embedding vector from unstructured item description text. The experimental results show that the proposed approach is efficient in generating more accurate recommendations by creating item embedding vectors from unstructured item description text.

AB - Using auxiliary data about items provides more accurate item recommendations when utilizing deep learning in the recommendation system. Users often read item descriptions during online shopping, which contain key information about the item and its features. However the item descriptions are in unstructured form and using them in the deep learning model is a problem. In this study, we integrate a pioneering Natural Language Processing technique into a recommendation system to create an item embedding vector from unstructured item description text. The experimental results show that the proposed approach is efficient in generating more accurate recommendations by creating item embedding vectors from unstructured item description text.

KW - Bidirectional encoder representations

KW - Hybrid recommendation systems

KW - Recommendation models

UR - http://www.scopus.com/inward/record.url?scp=85101422449&partnerID=8YFLogxK

U2 - 10.1007/978-3-030-65965-3_14

DO - 10.1007/978-3-030-65965-3_14

M3 - Conference contribution

AN - SCOPUS:85101422449

SN - 9783030659646

T3 - Communications in Computer and Information Science

SP - 225

EP - 236

BT - ECML PKDD 2020 Workshops - Workshops of the European Conference on Machine Learning and Knowledge Discovery in Databases ECML PKDD 2020

A2 - Koprinska, Irena

A2 - Appice, Annalisa

A2 - Antonie, Luiza

A2 - Guidotti, Riccardo

A2 - Ribeiro, Rita P.

A2 - Gama, João

A2 - Krishnamurthy, Yamuna

A2 - Malerba, Donato

A2 - Ceci, Michelangelo

A2 - Masciari, Elio

A2 - Christen, Peter

A2 - Schubert, Erich

A2 - Monreale, Monreale

A2 - Rinzivillo, Salvatore

A2 - Lommatzsch, Andreas

A2 - Kamp, Michael

A2 - Loglisci, Corrado

A2 - Zimmermann, Albrecht

A2 - Özgöbek, Özlem

A2 - Gavaldà, Ricard

A2 - Adilova, Linara

A2 - Ferreira, Pedro M.

A2 - Medeiros, Ibéria

A2 - Manco, Giuseppe

A2 - Ras, Zbigniew W.

A2 - Ntoutsi, Eirini

A2 - Zimek, Arthur

A2 - Biecek, Przemyslaw

A2 - Kille, Benjamin

A2 - Gulla, Jon Atle

PB - Springer Science and Business Media Deutschland GmbH

T2 - Workshops of the 20th Joint European Conference on Machine Learning and Knowledge Discovery in Databases, ECML PKDD

Y2 - 14 September 2020 through 18 September 2020

ER -

Islek I, Oguducu SG. A Hybrid Recommendation System Based on Bidirectional Encoder Representations. In Koprinska I, Appice A, Antonie L, Guidotti R, Ribeiro RP, Gama J, Krishnamurthy Y, Malerba D, Ceci M, Masciari E, Christen P, Schubert E, Monreale M, Rinzivillo S, Lommatzsch A, Kamp M, Loglisci C, Zimmermann A, Özgöbek Ö, Gavaldà R, Adilova L, Ferreira PM, Medeiros I, Manco G, Ras ZW, Ntoutsi E, Zimek A, Biecek P, Kille B, Gulla JA, editors, ECML PKDD 2020 Workshops - Workshops of the European Conference on Machine Learning and Knowledge Discovery in Databases ECML PKDD 2020: SoGood 2020, PDFL 2020, MLCS 2020, NFMCP 2020, DINA 2020, EDML 2020, XKDD 2020 and INRA 2020, Proceedings. Springer Science and Business Media Deutschland GmbH. 2020. p. 225-236. (Communications in Computer and Information Science). doi: 10.1007/978-3-030-65965-3_14

A Hybrid Recommendation System Based on Bidirectional Encoder Representations

Abstract

Publication series

Conference

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this