The 2021 RecSys Challenge Dataset: Fairness is not optional

Luca Belli; Alykhan Tejani; Frank Portman; Alexandre Lung-Yut-Fong; Ben Chamberlain; Yuanpu Xie; Jonathan Hunt; Michael Bronstein; Vito Walter Anelli; Saikishore Kalloori; Bruce Ferwerda; Wenzhe Shi

doi:10.1145/3487572.3487573

The 2021 RecSys Challenge Dataset: Fairness is not optional

Luca Belli, Alykhan Tejani, Frank Portman, Alexandre Lung-Yut-Fong, Ben Chamberlain, Yuanpu Xie, Jonathan Hunt, Michael Bronstein, Vito Walter Anelli, Saikishore Kalloori, Bruce Ferwerda, Wenzhe Shi

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

Abstract

After the success the RecSys 2020 Challenge, we are describing a novel and bigger dataset that was released in conjunction with the ACM RecSys Challenge 2021. This year's dataset is not only bigger (1B data points, a 5 fold increase), but for the first time it take into consideration fairness aspects of the challenge. Unlike many static datsets, a lot of effort went into making sure that the dataset was synced with the Twitter platform: if a user deleted their content, the same content would be promptly removed from the dataset too. In this paper, we introduce the dataset and challenge, highlighting some of the issues that arise when creating recommender systems at Twitter scale.

Original language	English
Title of host publication	Proceedings of Workshop on the RecSys Challenge 2021, RecSysChallenge 2021
Publisher	Association for Computing Machinery
Pages	1-6
Number of pages	6
ISBN (Electronic)	9781450386937
DOIs	https://doi.org/10.1145/3487572.3487573
State	Published - 1 Oct 2021
Externally published	Yes
Event	15th ACM Recommender Systems Challenge Workshop, RecSysChallenge 2021 - Amsterdam, Netherlands Duration: 1 Oct 2021 → …

Publication series

Name	ACM International Conference Proceeding Series

Conference

Conference	15th ACM Recommender Systems Challenge Workshop, RecSysChallenge 2021
Country/Territory	Netherlands
City	Amsterdam
Period	1/10/21 → …

Keywords

engagement prediction
fairness challenge
large-scale dataset
personalization
recommender system
twitter

Access to Document

10.1145/3487572.3487573

Cite this

Belli, L., Tejani, A., Portman, F., Lung-Yut-Fong, A., Chamberlain, B., Xie, Y., Hunt, J., Bronstein, M., Anelli, V. W., Kalloori, S., Ferwerda, B., & Shi, W. (2021). The 2021 RecSys Challenge Dataset: Fairness is not optional. In Proceedings of Workshop on the RecSys Challenge 2021, RecSysChallenge 2021 (pp. 1-6). (ACM International Conference Proceeding Series). Association for Computing Machinery. https://doi.org/10.1145/3487572.3487573

@inproceedings{17b433041ac84d77936325725365ba5a,

title = "The 2021 RecSys Challenge Dataset: Fairness is not optional",

abstract = "After the success the RecSys 2020 Challenge, we are describing a novel and bigger dataset that was released in conjunction with the ACM RecSys Challenge 2021. This year's dataset is not only bigger (1B data points, a 5 fold increase), but for the first time it take into consideration fairness aspects of the challenge. Unlike many static datsets, a lot of effort went into making sure that the dataset was synced with the Twitter platform: if a user deleted their content, the same content would be promptly removed from the dataset too. In this paper, we introduce the dataset and challenge, highlighting some of the issues that arise when creating recommender systems at Twitter scale.",

keywords = "engagement prediction, fairness challenge, large-scale dataset, personalization, recommender system, twitter",

author = "Luca Belli and Alykhan Tejani and Frank Portman and Alexandre Lung-Yut-Fong and Ben Chamberlain and Yuanpu Xie and Jonathan Hunt and Michael Bronstein and Anelli, {Vito Walter} and Saikishore Kalloori and Bruce Ferwerda and Wenzhe Shi",

note = "Publisher Copyright: {\textcopyright} 2021 ACM.; null ; Conference date: 01-10-2021",

year = "2021",

month = oct,

day = "1",

doi = "10.1145/3487572.3487573",

language = "אנגלית",

series = "ACM International Conference Proceeding Series",

publisher = "Association for Computing Machinery",

pages = "1--6",

booktitle = "Proceedings of Workshop on the RecSys Challenge 2021, RecSysChallenge 2021",

}

Belli, L, Tejani, A, Portman, F, Lung-Yut-Fong, A, Chamberlain, B, Xie, Y, Hunt, J, Bronstein, M, Anelli, VW, Kalloori, S, Ferwerda, B & Shi, W 2021, The 2021 RecSys Challenge Dataset: Fairness is not optional. in Proceedings of Workshop on the RecSys Challenge 2021, RecSysChallenge 2021. ACM International Conference Proceeding Series, Association for Computing Machinery, pp. 1-6, 15th ACM Recommender Systems Challenge Workshop, RecSysChallenge 2021, Amsterdam, Netherlands, 1/10/21. https://doi.org/10.1145/3487572.3487573

The 2021 RecSys Challenge Dataset : Fairness is not optional. / Belli, Luca; Tejani, Alykhan; Portman, Frank et al.

Proceedings of Workshop on the RecSys Challenge 2021, RecSysChallenge 2021. Association for Computing Machinery, 2021. p. 1-6 (ACM International Conference Proceeding Series).

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

TY - GEN

T1 - The 2021 RecSys Challenge Dataset

AU - Belli, Luca

AU - Tejani, Alykhan

AU - Portman, Frank

AU - Lung-Yut-Fong, Alexandre

AU - Chamberlain, Ben

AU - Xie, Yuanpu

AU - Hunt, Jonathan

AU - Bronstein, Michael

AU - Anelli, Vito Walter

AU - Kalloori, Saikishore

AU - Ferwerda, Bruce

AU - Shi, Wenzhe

PY - 2021/10/1

Y1 - 2021/10/1

N2 - After the success the RecSys 2020 Challenge, we are describing a novel and bigger dataset that was released in conjunction with the ACM RecSys Challenge 2021. This year's dataset is not only bigger (1B data points, a 5 fold increase), but for the first time it take into consideration fairness aspects of the challenge. Unlike many static datsets, a lot of effort went into making sure that the dataset was synced with the Twitter platform: if a user deleted their content, the same content would be promptly removed from the dataset too. In this paper, we introduce the dataset and challenge, highlighting some of the issues that arise when creating recommender systems at Twitter scale.

AB - After the success the RecSys 2020 Challenge, we are describing a novel and bigger dataset that was released in conjunction with the ACM RecSys Challenge 2021. This year's dataset is not only bigger (1B data points, a 5 fold increase), but for the first time it take into consideration fairness aspects of the challenge. Unlike many static datsets, a lot of effort went into making sure that the dataset was synced with the Twitter platform: if a user deleted their content, the same content would be promptly removed from the dataset too. In this paper, we introduce the dataset and challenge, highlighting some of the issues that arise when creating recommender systems at Twitter scale.

KW - engagement prediction

KW - fairness challenge

KW - large-scale dataset

KW - personalization

KW - recommender system

KW - twitter

UR - http://www.scopus.com/inward/record.url?scp=85140909302&partnerID=8YFLogxK

U2 - 10.1145/3487572.3487573

DO - 10.1145/3487572.3487573

M3 - פרסום בספר כנס

AN - SCOPUS:85140909302

T3 - ACM International Conference Proceeding Series

SP - 1

EP - 6

BT - Proceedings of Workshop on the RecSys Challenge 2021, RecSysChallenge 2021

PB - Association for Computing Machinery

Y2 - 1 October 2021

ER -

The 2021 RecSys Challenge Dataset: Fairness is not optional

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this