Abstract

State-of-the-art in network science of teams offers effective recommendation methods to answer questions like who is the best replacement, what is the best team expansion strategy, but lacks intuitive ways to explain why the optimization algorithm gives the specific recommendation for a given team optimization scenario. To tackle this problem, we develop an interactive prototype system, Extra, as the first step towards addressing such a sense-making challenge, through the lens of the underlying network where teams embed, to explain the team recommendation results. The main advantages are (1) Algorithm efficacy: we propose an effective and fast algorithm to explain random walk graph kernel, the central technique for networked team recommendation; (2) Intuitive visual explanation: we present intuitive visual analysis of the recommendation results, which can help users better understand the rationality of the underlying team recommendation algorithm.

Original languageEnglish (US)
Title of host publicationRecSys 2018 - 12th ACM Conference on Recommender Systems
PublisherAssociation for Computing Machinery, Inc
Pages492-493
Number of pages2
ISBN (Electronic)9781450359016
DOIs
StatePublished - Sep 27 2018
Event12th ACM Conference on Recommender Systems, RecSys 2018 - Vancouver, Canada
Duration: Oct 2 2018Oct 7 2018

Other

Other12th ACM Conference on Recommender Systems, RecSys 2018
CountryCanada
CityVancouver
Period10/2/1810/7/18

Fingerprint

Lenses

Keywords

  • Random Walk Graph Kernel
  • Team Recommendation Explanation
  • Visualization

ASJC Scopus subject areas

  • Hardware and Architecture
  • Software

Cite this

Zhou, Q., Li, L., Cao, N., Buchler, N., & Tong, H. (2018). Extra: Explaining team recommendation in networks. In RecSys 2018 - 12th ACM Conference on Recommender Systems (pp. 492-493). Association for Computing Machinery, Inc. https://doi.org/10.1145/3240323.3241610

Extra : Explaining team recommendation in networks. / Zhou, Qinghai; Li, Liangyue; Cao, Nan; Buchler, Norbou; Tong, Hanghang.

RecSys 2018 - 12th ACM Conference on Recommender Systems. Association for Computing Machinery, Inc, 2018. p. 492-493.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Zhou, Q, Li, L, Cao, N, Buchler, N & Tong, H 2018, Extra: Explaining team recommendation in networks. in RecSys 2018 - 12th ACM Conference on Recommender Systems. Association for Computing Machinery, Inc, pp. 492-493, 12th ACM Conference on Recommender Systems, RecSys 2018, Vancouver, Canada, 10/2/18. https://doi.org/10.1145/3240323.3241610
Zhou Q, Li L, Cao N, Buchler N, Tong H. Extra: Explaining team recommendation in networks. In RecSys 2018 - 12th ACM Conference on Recommender Systems. Association for Computing Machinery, Inc. 2018. p. 492-493 https://doi.org/10.1145/3240323.3241610
Zhou, Qinghai ; Li, Liangyue ; Cao, Nan ; Buchler, Norbou ; Tong, Hanghang. / Extra : Explaining team recommendation in networks. RecSys 2018 - 12th ACM Conference on Recommender Systems. Association for Computing Machinery, Inc, 2018. pp. 492-493
@inproceedings{314ffdc1bb3e4c289624bfafd42d6b99,
title = "Extra: Explaining team recommendation in networks",
abstract = "State-of-the-art in network science of teams offers effective recommendation methods to answer questions like who is the best replacement, what is the best team expansion strategy, but lacks intuitive ways to explain why the optimization algorithm gives the specific recommendation for a given team optimization scenario. To tackle this problem, we develop an interactive prototype system, Extra, as the first step towards addressing such a sense-making challenge, through the lens of the underlying network where teams embed, to explain the team recommendation results. The main advantages are (1) Algorithm efficacy: we propose an effective and fast algorithm to explain random walk graph kernel, the central technique for networked team recommendation; (2) Intuitive visual explanation: we present intuitive visual analysis of the recommendation results, which can help users better understand the rationality of the underlying team recommendation algorithm.",
keywords = "Random Walk Graph Kernel, Team Recommendation Explanation, Visualization",
author = "Qinghai Zhou and Liangyue Li and Nan Cao and Norbou Buchler and Hanghang Tong",
year = "2018",
month = "9",
day = "27",
doi = "10.1145/3240323.3241610",
language = "English (US)",
pages = "492--493",
booktitle = "RecSys 2018 - 12th ACM Conference on Recommender Systems",
publisher = "Association for Computing Machinery, Inc",

}

TY - GEN

T1 - Extra

T2 - Explaining team recommendation in networks

AU - Zhou, Qinghai

AU - Li, Liangyue

AU - Cao, Nan

AU - Buchler, Norbou

AU - Tong, Hanghang

PY - 2018/9/27

Y1 - 2018/9/27

N2 - State-of-the-art in network science of teams offers effective recommendation methods to answer questions like who is the best replacement, what is the best team expansion strategy, but lacks intuitive ways to explain why the optimization algorithm gives the specific recommendation for a given team optimization scenario. To tackle this problem, we develop an interactive prototype system, Extra, as the first step towards addressing such a sense-making challenge, through the lens of the underlying network where teams embed, to explain the team recommendation results. The main advantages are (1) Algorithm efficacy: we propose an effective and fast algorithm to explain random walk graph kernel, the central technique for networked team recommendation; (2) Intuitive visual explanation: we present intuitive visual analysis of the recommendation results, which can help users better understand the rationality of the underlying team recommendation algorithm.

AB - State-of-the-art in network science of teams offers effective recommendation methods to answer questions like who is the best replacement, what is the best team expansion strategy, but lacks intuitive ways to explain why the optimization algorithm gives the specific recommendation for a given team optimization scenario. To tackle this problem, we develop an interactive prototype system, Extra, as the first step towards addressing such a sense-making challenge, through the lens of the underlying network where teams embed, to explain the team recommendation results. The main advantages are (1) Algorithm efficacy: we propose an effective and fast algorithm to explain random walk graph kernel, the central technique for networked team recommendation; (2) Intuitive visual explanation: we present intuitive visual analysis of the recommendation results, which can help users better understand the rationality of the underlying team recommendation algorithm.

KW - Random Walk Graph Kernel

KW - Team Recommendation Explanation

KW - Visualization

UR - http://www.scopus.com/inward/record.url?scp=85056758868&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85056758868&partnerID=8YFLogxK

U2 - 10.1145/3240323.3241610

DO - 10.1145/3240323.3241610

M3 - Conference contribution

SP - 492

EP - 493

BT - RecSys 2018 - 12th ACM Conference on Recommender Systems

PB - Association for Computing Machinery, Inc

ER -