Incorporating accuracy and diversity in a news recommender system

Shaina Raza; Syed Raza Bashir; Usman Naseem; Dora D. Liu; Deepak John Reji

doi:10.1109/DSAA54385.2022.10032442

Incorporating accuracy and diversity in a news recommender system

Shaina Raza^*, Syed Raza Bashir, Usman Naseem, Dora D. Liu, Deepak John Reji

^*Corresponding author for this work

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

1 Citation (Scopus)

Abstract

There are certain challenges in news recommender systems that arise due to changing users' preferences over dynamically generated news articles. It is important to expose users to a variety of information. Diversity is required in a news recommender system not only so that users do not get bored of reading similar news but because so that they do not get trapped in information bubbles. We propose a deep neural network based on a two-tower architecture that learns news representation through a news item tower and users' representations through a query tower. To learn diversity, we introduce a category loss function that aligns items' representation of uneven news categories. Experimental results on two news datasets reveal that our proposed architecture is more effective compared to the state-of-the-art methods and achieves a balance between accuracy and diversity.

Original language	English
Title of host publication	2022 IEEE 9th International Conference on Data Science and Advanced Analytics DSAA'2022
Subtitle of host publication	proceedings
Editors	Joshua Zhexue Huang, Yi Pan, Barbara Hammer, Muhammad Khurram Khan, Xing Xie, Laizhong Cui, Yulin He
Place of Publication	Piscataway, NJ
Publisher	Institute of Electrical and Electronics Engineers (IEEE)
Number of pages	10
ISBN (Electronic)	9781665473309
ISBN (Print)	9781665473316
DOIs	https://doi.org/10.1109/DSAA54385.2022.10032442
Publication status	Published - 2022
Externally published	Yes
Event	9th IEEE International Conference on Data Science and Advanced Analytics, DSAA 2022 - Shenzhen, China Duration: 13 Oct 2022 → 16 Oct 2022

Conference

Conference	9th IEEE International Conference on Data Science and Advanced Analytics, DSAA 2022
Country/Territory	China
City	Shenzhen
Period	13/10/22 → 16/10/22

Keywords

News recommender system
recommendations
accuracy
relevancy
diversity
trade-off

Access to Document

10.1109/DSAA54385.2022.10032442

Cite this

Raza, S., Bashir, S. R., Naseem, U., Liu, D. D., & Reji, D. J. (2022). Incorporating accuracy and diversity in a news recommender system. In J. Z. Huang, Y. Pan, B. Hammer, M. K. Khan, X. Xie, L. Cui, & Y. He (Eds.), 2022 IEEE 9th International Conference on Data Science and Advanced Analytics DSAA'2022: proceedings Institute of Electrical and Electronics Engineers (IEEE). https://doi.org/10.1109/DSAA54385.2022.10032442

Raza, Shaina ; Bashir, Syed Raza ; Naseem, Usman et al. / Incorporating accuracy and diversity in a news recommender system. 2022 IEEE 9th International Conference on Data Science and Advanced Analytics DSAA'2022: proceedings. editor / Joshua Zhexue Huang ; Yi Pan ; Barbara Hammer ; Muhammad Khurram Khan ; Xing Xie ; Laizhong Cui ; Yulin He. Piscataway, NJ : Institute of Electrical and Electronics Engineers (IEEE), 2022.

@inproceedings{85b7db643df24e0ab94745849d3b638d,

title = "Incorporating accuracy and diversity in a news recommender system",

abstract = "There are certain challenges in news recommender systems that arise due to changing users' preferences over dynamically generated news articles. It is important to expose users to a variety of information. Diversity is required in a news recommender system not only so that users do not get bored of reading similar news but because so that they do not get trapped in information bubbles. We propose a deep neural network based on a two-tower architecture that learns news representation through a news item tower and users' representations through a query tower. To learn diversity, we introduce a category loss function that aligns items' representation of uneven news categories. Experimental results on two news datasets reveal that our proposed architecture is more effective compared to the state-of-the-art methods and achieves a balance between accuracy and diversity.",

keywords = "News recommender system, recommendations, accuracy, relevancy, diversity, trade-off",

author = "Shaina Raza and Bashir, {Syed Raza} and Usman Naseem and Liu, {Dora D.} and Reji, {Deepak John}",

year = "2022",

doi = "10.1109/DSAA54385.2022.10032442",

language = "English",

isbn = "9781665473316",

editor = "Huang, {Joshua Zhexue} and Yi Pan and Barbara Hammer and Khan, {Muhammad Khurram} and Xing Xie and Laizhong Cui and Yulin He",

booktitle = "2022 IEEE 9th International Conference on Data Science and Advanced Analytics DSAA'2022",

publisher = "Institute of Electrical and Electronics Engineers (IEEE)",

address = "United States",

note = "9th IEEE International Conference on Data Science and Advanced Analytics, DSAA 2022 ; Conference date: 13-10-2022 Through 16-10-2022",

}

Raza, S, Bashir, SR, Naseem, U, Liu, DD & Reji, DJ 2022, Incorporating accuracy and diversity in a news recommender system. in JZ Huang, Y Pan, B Hammer, MK Khan, X Xie, L Cui & Y He (eds), 2022 IEEE 9th International Conference on Data Science and Advanced Analytics DSAA'2022: proceedings. Institute of Electrical and Electronics Engineers (IEEE), Piscataway, NJ, 9th IEEE International Conference on Data Science and Advanced Analytics, DSAA 2022, Shenzhen, China, 13/10/22. https://doi.org/10.1109/DSAA54385.2022.10032442

Incorporating accuracy and diversity in a news recommender system. / Raza, Shaina; Bashir, Syed Raza; Naseem, Usman et al.
2022 IEEE 9th International Conference on Data Science and Advanced Analytics DSAA'2022: proceedings. ed. / Joshua Zhexue Huang; Yi Pan; Barbara Hammer; Muhammad Khurram Khan; Xing Xie; Laizhong Cui; Yulin He. Piscataway, NJ: Institute of Electrical and Electronics Engineers (IEEE), 2022.

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

TY - GEN

T1 - Incorporating accuracy and diversity in a news recommender system

AU - Raza, Shaina

AU - Bashir, Syed Raza

AU - Naseem, Usman

AU - Liu, Dora D.

AU - Reji, Deepak John

PY - 2022

Y1 - 2022

N2 - There are certain challenges in news recommender systems that arise due to changing users' preferences over dynamically generated news articles. It is important to expose users to a variety of information. Diversity is required in a news recommender system not only so that users do not get bored of reading similar news but because so that they do not get trapped in information bubbles. We propose a deep neural network based on a two-tower architecture that learns news representation through a news item tower and users' representations through a query tower. To learn diversity, we introduce a category loss function that aligns items' representation of uneven news categories. Experimental results on two news datasets reveal that our proposed architecture is more effective compared to the state-of-the-art methods and achieves a balance between accuracy and diversity.

AB - There are certain challenges in news recommender systems that arise due to changing users' preferences over dynamically generated news articles. It is important to expose users to a variety of information. Diversity is required in a news recommender system not only so that users do not get bored of reading similar news but because so that they do not get trapped in information bubbles. We propose a deep neural network based on a two-tower architecture that learns news representation through a news item tower and users' representations through a query tower. To learn diversity, we introduce a category loss function that aligns items' representation of uneven news categories. Experimental results on two news datasets reveal that our proposed architecture is more effective compared to the state-of-the-art methods and achieves a balance between accuracy and diversity.

KW - News recommender system

KW - recommendations

KW - accuracy

KW - relevancy

KW - diversity

KW - trade-off

UR - http://www.scopus.com/inward/record.url?scp=85148542118&partnerID=8YFLogxK

U2 - 10.1109/DSAA54385.2022.10032442

DO - 10.1109/DSAA54385.2022.10032442

M3 - Conference proceeding contribution

AN - SCOPUS:85148542118

SN - 9781665473316

BT - 2022 IEEE 9th International Conference on Data Science and Advanced Analytics DSAA'2022

A2 - Huang, Joshua Zhexue

A2 - Pan, Yi

A2 - Hammer, Barbara

A2 - Khan, Muhammad Khurram

A2 - Xie, Xing

A2 - Cui, Laizhong

A2 - He, Yulin

PB - Institute of Electrical and Electronics Engineers (IEEE)

CY - Piscataway, NJ

T2 - 9th IEEE International Conference on Data Science and Advanced Analytics, DSAA 2022

Y2 - 13 October 2022 through 16 October 2022

ER -

Raza S, Bashir SR, Naseem U, Liu DD, Reji DJ. Incorporating accuracy and diversity in a news recommender system. In Huang JZ, Pan Y, Hammer B, Khan MK, Xie X, Cui L, He Y, editors, 2022 IEEE 9th International Conference on Data Science and Advanced Analytics DSAA'2022: proceedings. Piscataway, NJ: Institute of Electrical and Electronics Engineers (IEEE). 2022 doi: 10.1109/DSAA54385.2022.10032442

Incorporating accuracy and diversity in a news recommender system

Abstract

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this