Learning user preferences and understanding calendar contexts for event scheduling

Donghyeon Kim, Jinhyuk Lee, Donghee Choi, Jaehoon Choi, Jaewoo Kang

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

1 Citation (Scopus)

Abstract

With online calendar services gaining popularity worldwide, calendar data has become one of the richest context sources for understanding human behavior. However, event scheduling is still time-consuming even with the development of online calendars. Although machine learning based event scheduling models have automated scheduling processes to some extent, they often fail to understand subtle user preferences and complex calendar contexts with event titles written in natural language. In this paper, we propose Neural Event Scheduling Assistant (NESA) which learns user preferences and understands calendar contexts, directly from raw online calendars for fully automated and highly effective event scheduling. We leverage over 593K calendar events for NESA to learn scheduling personal events, and we further utilize NESA for multi-attendee event scheduling. NESA successfully incorporates deep neural networks such as Bidirectional Long Short-Term Memory, Convolutional Neural Network, and Highway Network for learning the preferences of each user and understanding calendar context based on natural languages. The experimental results show that NESA significantly outperforms previous baseline models in terms of various evaluation metrics on both personal and multi-attendee event scheduling tasks. Our qualitative analysis demonstrates the effectiveness of each layer in NESA and learned user preferences.

Original languageEnglish
Title of host publicationCIKM 2018 - Proceedings of the 27th ACM International Conference on Information and Knowledge Management
EditorsNorman Paton, Selcuk Candan, Haixun Wang, James Allan, Rakesh Agrawal, Alexandros Labrinidis, Alfredo Cuzzocrea, Mohammed Zaki, Divesh Srivastava, Andrei Broder, Assaf Schuster
PublisherAssociation for Computing Machinery
Pages337-346
Number of pages10
ISBN (Electronic)9781450360142
DOIs
Publication statusPublished - 2018 Oct 17
Event27th ACM International Conference on Information and Knowledge Management, CIKM 2018 - Torino, Italy
Duration: 2018 Oct 222018 Oct 26

Other

Other27th ACM International Conference on Information and Knowledge Management, CIKM 2018
CountryItaly
CityTorino
Period18/10/2218/10/26

Fingerprint

User preferences
Calendar
Neural networks
Language
Machine learning
Leverage
Evaluation
Qualitative analysis
Human behavior

Keywords

  • Convolutional neural network
  • Digital assistant
  • Event scheduling
  • Highway network
  • Multi-agent
  • Preference
  • Recurrent neural network

ASJC Scopus subject areas

  • Business, Management and Accounting(all)
  • Decision Sciences(all)

Cite this

Kim, D., Lee, J., Choi, D., Choi, J., & Kang, J. (2018). Learning user preferences and understanding calendar contexts for event scheduling. In N. Paton, S. Candan, H. Wang, J. Allan, R. Agrawal, A. Labrinidis, A. Cuzzocrea, M. Zaki, D. Srivastava, A. Broder, ... A. Schuster (Eds.), CIKM 2018 - Proceedings of the 27th ACM International Conference on Information and Knowledge Management (pp. 337-346). Association for Computing Machinery. https://doi.org/10.1145/3269206.3271712

Learning user preferences and understanding calendar contexts for event scheduling. / Kim, Donghyeon; Lee, Jinhyuk; Choi, Donghee; Choi, Jaehoon; Kang, Jaewoo.

CIKM 2018 - Proceedings of the 27th ACM International Conference on Information and Knowledge Management. ed. / Norman Paton; Selcuk Candan; Haixun Wang; James Allan; Rakesh Agrawal; Alexandros Labrinidis; Alfredo Cuzzocrea; Mohammed Zaki; Divesh Srivastava; Andrei Broder; Assaf Schuster. Association for Computing Machinery, 2018. p. 337-346.

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

Kim, D, Lee, J, Choi, D, Choi, J & Kang, J 2018, Learning user preferences and understanding calendar contexts for event scheduling. in N Paton, S Candan, H Wang, J Allan, R Agrawal, A Labrinidis, A Cuzzocrea, M Zaki, D Srivastava, A Broder & A Schuster (eds), CIKM 2018 - Proceedings of the 27th ACM International Conference on Information and Knowledge Management. Association for Computing Machinery, pp. 337-346, 27th ACM International Conference on Information and Knowledge Management, CIKM 2018, Torino, Italy, 18/10/22. https://doi.org/10.1145/3269206.3271712
Kim D, Lee J, Choi D, Choi J, Kang J. Learning user preferences and understanding calendar contexts for event scheduling. In Paton N, Candan S, Wang H, Allan J, Agrawal R, Labrinidis A, Cuzzocrea A, Zaki M, Srivastava D, Broder A, Schuster A, editors, CIKM 2018 - Proceedings of the 27th ACM International Conference on Information and Knowledge Management. Association for Computing Machinery. 2018. p. 337-346 https://doi.org/10.1145/3269206.3271712
Kim, Donghyeon ; Lee, Jinhyuk ; Choi, Donghee ; Choi, Jaehoon ; Kang, Jaewoo. / Learning user preferences and understanding calendar contexts for event scheduling. CIKM 2018 - Proceedings of the 27th ACM International Conference on Information and Knowledge Management. editor / Norman Paton ; Selcuk Candan ; Haixun Wang ; James Allan ; Rakesh Agrawal ; Alexandros Labrinidis ; Alfredo Cuzzocrea ; Mohammed Zaki ; Divesh Srivastava ; Andrei Broder ; Assaf Schuster. Association for Computing Machinery, 2018. pp. 337-346
@inproceedings{b7c5a717b30d4f07a34632dfd1277da1,
title = "Learning user preferences and understanding calendar contexts for event scheduling",
abstract = "With online calendar services gaining popularity worldwide, calendar data has become one of the richest context sources for understanding human behavior. However, event scheduling is still time-consuming even with the development of online calendars. Although machine learning based event scheduling models have automated scheduling processes to some extent, they often fail to understand subtle user preferences and complex calendar contexts with event titles written in natural language. In this paper, we propose Neural Event Scheduling Assistant (NESA) which learns user preferences and understands calendar contexts, directly from raw online calendars for fully automated and highly effective event scheduling. We leverage over 593K calendar events for NESA to learn scheduling personal events, and we further utilize NESA for multi-attendee event scheduling. NESA successfully incorporates deep neural networks such as Bidirectional Long Short-Term Memory, Convolutional Neural Network, and Highway Network for learning the preferences of each user and understanding calendar context based on natural languages. The experimental results show that NESA significantly outperforms previous baseline models in terms of various evaluation metrics on both personal and multi-attendee event scheduling tasks. Our qualitative analysis demonstrates the effectiveness of each layer in NESA and learned user preferences.",
keywords = "Convolutional neural network, Digital assistant, Event scheduling, Highway network, Multi-agent, Preference, Recurrent neural network",
author = "Donghyeon Kim and Jinhyuk Lee and Donghee Choi and Jaehoon Choi and Jaewoo Kang",
year = "2018",
month = "10",
day = "17",
doi = "10.1145/3269206.3271712",
language = "English",
pages = "337--346",
editor = "Norman Paton and Selcuk Candan and Haixun Wang and James Allan and Rakesh Agrawal and Alexandros Labrinidis and Alfredo Cuzzocrea and Mohammed Zaki and Divesh Srivastava and Andrei Broder and Assaf Schuster",
booktitle = "CIKM 2018 - Proceedings of the 27th ACM International Conference on Information and Knowledge Management",
publisher = "Association for Computing Machinery",

}

TY - GEN

T1 - Learning user preferences and understanding calendar contexts for event scheduling

AU - Kim, Donghyeon

AU - Lee, Jinhyuk

AU - Choi, Donghee

AU - Choi, Jaehoon

AU - Kang, Jaewoo

PY - 2018/10/17

Y1 - 2018/10/17

N2 - With online calendar services gaining popularity worldwide, calendar data has become one of the richest context sources for understanding human behavior. However, event scheduling is still time-consuming even with the development of online calendars. Although machine learning based event scheduling models have automated scheduling processes to some extent, they often fail to understand subtle user preferences and complex calendar contexts with event titles written in natural language. In this paper, we propose Neural Event Scheduling Assistant (NESA) which learns user preferences and understands calendar contexts, directly from raw online calendars for fully automated and highly effective event scheduling. We leverage over 593K calendar events for NESA to learn scheduling personal events, and we further utilize NESA for multi-attendee event scheduling. NESA successfully incorporates deep neural networks such as Bidirectional Long Short-Term Memory, Convolutional Neural Network, and Highway Network for learning the preferences of each user and understanding calendar context based on natural languages. The experimental results show that NESA significantly outperforms previous baseline models in terms of various evaluation metrics on both personal and multi-attendee event scheduling tasks. Our qualitative analysis demonstrates the effectiveness of each layer in NESA and learned user preferences.

AB - With online calendar services gaining popularity worldwide, calendar data has become one of the richest context sources for understanding human behavior. However, event scheduling is still time-consuming even with the development of online calendars. Although machine learning based event scheduling models have automated scheduling processes to some extent, they often fail to understand subtle user preferences and complex calendar contexts with event titles written in natural language. In this paper, we propose Neural Event Scheduling Assistant (NESA) which learns user preferences and understands calendar contexts, directly from raw online calendars for fully automated and highly effective event scheduling. We leverage over 593K calendar events for NESA to learn scheduling personal events, and we further utilize NESA for multi-attendee event scheduling. NESA successfully incorporates deep neural networks such as Bidirectional Long Short-Term Memory, Convolutional Neural Network, and Highway Network for learning the preferences of each user and understanding calendar context based on natural languages. The experimental results show that NESA significantly outperforms previous baseline models in terms of various evaluation metrics on both personal and multi-attendee event scheduling tasks. Our qualitative analysis demonstrates the effectiveness of each layer in NESA and learned user preferences.

KW - Convolutional neural network

KW - Digital assistant

KW - Event scheduling

KW - Highway network

KW - Multi-agent

KW - Preference

KW - Recurrent neural network

UR - http://www.scopus.com/inward/record.url?scp=85058003552&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85058003552&partnerID=8YFLogxK

U2 - 10.1145/3269206.3271712

DO - 10.1145/3269206.3271712

M3 - Conference contribution

AN - SCOPUS:85058003552

SP - 337

EP - 346

BT - CIKM 2018 - Proceedings of the 27th ACM International Conference on Information and Knowledge Management

A2 - Paton, Norman

A2 - Candan, Selcuk

A2 - Wang, Haixun

A2 - Allan, James

A2 - Agrawal, Rakesh

A2 - Labrinidis, Alexandros

A2 - Cuzzocrea, Alfredo

A2 - Zaki, Mohammed

A2 - Srivastava, Divesh

A2 - Broder, Andrei

A2 - Schuster, Assaf

PB - Association for Computing Machinery

ER -