Machine learning is better than human to satisfy decision by majority

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

4 Citations (Scopus)

Abstract

Government 2.0 activities have become very attractive and popular these days. Using platforms to support the activities, anyone can anytime report issues or complaints in a city with their photographs and geographical information on the Web, and share them with other people. Since a variety of reports are posted, officials in the city management section have to check the importance of each report and sort out their priorities to the reports. However, it is not easy task to judge the importance of the reports. When several officials work on the task, the agreement rate of their judgments is not always high. Even if the task is done by only one official, his/her judgment sometimes varies on a similar report. To remedy this low agreement rate problem of human judgments, we propose a method of detecting signs of danger or unsafe problems described in citizens' reports. The proposed method uses a machine learning technique with word feature selection. Experimental results clearly explain the low agreement rate of human judgments, and illustrate that the proposed machine learning method has much higher performance than human judgments.

Original languageEnglish
Title of host publicationProceedings - 2017 IEEE/WIC/ACM International Conference on Web Intelligence, WI 2017
PublisherAssociation for Computing Machinery, Inc
Pages694-701
Number of pages8
ISBN (Electronic)9781450349512
DOIs
Publication statusPublished - Aug 23 2017
Event16th IEEE/WIC/ACM International Conference on Web Intelligence, WI 2017 - Leipzig, Germany
Duration: Aug 23 2017Aug 26 2017

Publication series

NameProceedings - 2017 IEEE/WIC/ACM International Conference on Web Intelligence, WI 2017

Other

Other16th IEEE/WIC/ACM International Conference on Web Intelligence, WI 2017
CountryGermany
CityLeipzig
Period8/23/178/26/17

Fingerprint

Learning systems
Feature extraction

All Science Journal Classification (ASJC) codes

  • Computer Networks and Communications
  • Artificial Intelligence
  • Software

Cite this

Hirokawa, S., Suzuki, T., & Mine, T. (2017). Machine learning is better than human to satisfy decision by majority. In Proceedings - 2017 IEEE/WIC/ACM International Conference on Web Intelligence, WI 2017 (pp. 694-701). (Proceedings - 2017 IEEE/WIC/ACM International Conference on Web Intelligence, WI 2017). Association for Computing Machinery, Inc. https://doi.org/10.1145/3106426.3106520

Machine learning is better than human to satisfy decision by majority. / Hirokawa, Sachio; Suzuki, Takahiko; Mine, Tsunenori.

Proceedings - 2017 IEEE/WIC/ACM International Conference on Web Intelligence, WI 2017. Association for Computing Machinery, Inc, 2017. p. 694-701 (Proceedings - 2017 IEEE/WIC/ACM International Conference on Web Intelligence, WI 2017).

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

Hirokawa, S, Suzuki, T & Mine, T 2017, Machine learning is better than human to satisfy decision by majority. in Proceedings - 2017 IEEE/WIC/ACM International Conference on Web Intelligence, WI 2017. Proceedings - 2017 IEEE/WIC/ACM International Conference on Web Intelligence, WI 2017, Association for Computing Machinery, Inc, pp. 694-701, 16th IEEE/WIC/ACM International Conference on Web Intelligence, WI 2017, Leipzig, Germany, 8/23/17. https://doi.org/10.1145/3106426.3106520
Hirokawa S, Suzuki T, Mine T. Machine learning is better than human to satisfy decision by majority. In Proceedings - 2017 IEEE/WIC/ACM International Conference on Web Intelligence, WI 2017. Association for Computing Machinery, Inc. 2017. p. 694-701. (Proceedings - 2017 IEEE/WIC/ACM International Conference on Web Intelligence, WI 2017). https://doi.org/10.1145/3106426.3106520
Hirokawa, Sachio ; Suzuki, Takahiko ; Mine, Tsunenori. / Machine learning is better than human to satisfy decision by majority. Proceedings - 2017 IEEE/WIC/ACM International Conference on Web Intelligence, WI 2017. Association for Computing Machinery, Inc, 2017. pp. 694-701 (Proceedings - 2017 IEEE/WIC/ACM International Conference on Web Intelligence, WI 2017).
@inproceedings{0c1638df62e848c8b704c598213a6ba4,
title = "Machine learning is better than human to satisfy decision by majority",
abstract = "Government 2.0 activities have become very attractive and popular these days. Using platforms to support the activities, anyone can anytime report issues or complaints in a city with their photographs and geographical information on the Web, and share them with other people. Since a variety of reports are posted, officials in the city management section have to check the importance of each report and sort out their priorities to the reports. However, it is not easy task to judge the importance of the reports. When several officials work on the task, the agreement rate of their judgments is not always high. Even if the task is done by only one official, his/her judgment sometimes varies on a similar report. To remedy this low agreement rate problem of human judgments, we propose a method of detecting signs of danger or unsafe problems described in citizens' reports. The proposed method uses a machine learning technique with word feature selection. Experimental results clearly explain the low agreement rate of human judgments, and illustrate that the proposed machine learning method has much higher performance than human judgments.",
author = "Sachio Hirokawa and Takahiko Suzuki and Tsunenori Mine",
year = "2017",
month = "8",
day = "23",
doi = "10.1145/3106426.3106520",
language = "English",
series = "Proceedings - 2017 IEEE/WIC/ACM International Conference on Web Intelligence, WI 2017",
publisher = "Association for Computing Machinery, Inc",
pages = "694--701",
booktitle = "Proceedings - 2017 IEEE/WIC/ACM International Conference on Web Intelligence, WI 2017",

}

TY - GEN

T1 - Machine learning is better than human to satisfy decision by majority

AU - Hirokawa, Sachio

AU - Suzuki, Takahiko

AU - Mine, Tsunenori

PY - 2017/8/23

Y1 - 2017/8/23

N2 - Government 2.0 activities have become very attractive and popular these days. Using platforms to support the activities, anyone can anytime report issues or complaints in a city with their photographs and geographical information on the Web, and share them with other people. Since a variety of reports are posted, officials in the city management section have to check the importance of each report and sort out their priorities to the reports. However, it is not easy task to judge the importance of the reports. When several officials work on the task, the agreement rate of their judgments is not always high. Even if the task is done by only one official, his/her judgment sometimes varies on a similar report. To remedy this low agreement rate problem of human judgments, we propose a method of detecting signs of danger or unsafe problems described in citizens' reports. The proposed method uses a machine learning technique with word feature selection. Experimental results clearly explain the low agreement rate of human judgments, and illustrate that the proposed machine learning method has much higher performance than human judgments.

AB - Government 2.0 activities have become very attractive and popular these days. Using platforms to support the activities, anyone can anytime report issues or complaints in a city with their photographs and geographical information on the Web, and share them with other people. Since a variety of reports are posted, officials in the city management section have to check the importance of each report and sort out their priorities to the reports. However, it is not easy task to judge the importance of the reports. When several officials work on the task, the agreement rate of their judgments is not always high. Even if the task is done by only one official, his/her judgment sometimes varies on a similar report. To remedy this low agreement rate problem of human judgments, we propose a method of detecting signs of danger or unsafe problems described in citizens' reports. The proposed method uses a machine learning technique with word feature selection. Experimental results clearly explain the low agreement rate of human judgments, and illustrate that the proposed machine learning method has much higher performance than human judgments.

UR - http://www.scopus.com/inward/record.url?scp=85031044631&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85031044631&partnerID=8YFLogxK

U2 - 10.1145/3106426.3106520

DO - 10.1145/3106426.3106520

M3 - Conference contribution

T3 - Proceedings - 2017 IEEE/WIC/ACM International Conference on Web Intelligence, WI 2017

SP - 694

EP - 701

BT - Proceedings - 2017 IEEE/WIC/ACM International Conference on Web Intelligence, WI 2017

PB - Association for Computing Machinery, Inc

ER -