Detection of current actual status and demand expressions in community complaint reports

Yuta Sano, Tsunenori Mine

Research output: Contribution to journalArticle

Abstract

Government 2.0 activities have become attractive and popular these days. Using tools of their activities, anyone can report issues or complaints in a city on the Web with their photographs and geographical information, and share their information with other people. On the other hand, unlike telephone calls, the concreteness of a report depends on its reporter. Thus, the actual status and demand to the status may not be described clearly or either one may be miss-described in the report. It may accordingly happen that officials in the city management section can not grasp the actual status or demand to the status of the report. To solve the problems, automatic finding incomplete reports and completing missing information are indispensable. In this paper, we propose methods to detect parts related to an actual status or demand to the status in a report using empirical patterns, dependency relations, and several machine learning techniques. Experimental results show that an average F-score and an average accuracy score our methods achieved were 0.798 and 0.893, respectively. In addition, in our methods, RF achieved better results than SVM for both F-score and accuracy scores.

Original languageEnglish
Pages (from-to)AG16-B_1-AG16-B_10
JournalTransactions of the Japanese Society for Artificial Intelligence
Volume32
Issue number5
DOIs
Publication statusPublished - Jan 1 2017

Fingerprint

Telephone
Learning systems

All Science Journal Classification (ASJC) codes

  • Software
  • Artificial Intelligence

Cite this

Detection of current actual status and demand expressions in community complaint reports. / Sano, Yuta; Mine, Tsunenori.

In: Transactions of the Japanese Society for Artificial Intelligence, Vol. 32, No. 5, 01.01.2017, p. AG16-B_1-AG16-B_10.

Research output: Contribution to journalArticle

@article{3eaf903a206045ee8901440ef6a0ab40,
title = "Detection of current actual status and demand expressions in community complaint reports",
abstract = "Government 2.0 activities have become attractive and popular these days. Using tools of their activities, anyone can report issues or complaints in a city on the Web with their photographs and geographical information, and share their information with other people. On the other hand, unlike telephone calls, the concreteness of a report depends on its reporter. Thus, the actual status and demand to the status may not be described clearly or either one may be miss-described in the report. It may accordingly happen that officials in the city management section can not grasp the actual status or demand to the status of the report. To solve the problems, automatic finding incomplete reports and completing missing information are indispensable. In this paper, we propose methods to detect parts related to an actual status or demand to the status in a report using empirical patterns, dependency relations, and several machine learning techniques. Experimental results show that an average F-score and an average accuracy score our methods achieved were 0.798 and 0.893, respectively. In addition, in our methods, RF achieved better results than SVM for both F-score and accuracy scores.",
author = "Yuta Sano and Tsunenori Mine",
year = "2017",
month = "1",
day = "1",
doi = "10.1527/tjsai.AG16-B",
language = "English",
volume = "32",
pages = "AG16--B_1--AG16--B_10",
journal = "Transactions of the Japanese Society for Artificial Intelligence",
issn = "1346-0714",
publisher = "Japanese Society for Artificial Intelligence",
number = "5",

}

TY - JOUR

T1 - Detection of current actual status and demand expressions in community complaint reports

AU - Sano, Yuta

AU - Mine, Tsunenori

PY - 2017/1/1

Y1 - 2017/1/1

N2 - Government 2.0 activities have become attractive and popular these days. Using tools of their activities, anyone can report issues or complaints in a city on the Web with their photographs and geographical information, and share their information with other people. On the other hand, unlike telephone calls, the concreteness of a report depends on its reporter. Thus, the actual status and demand to the status may not be described clearly or either one may be miss-described in the report. It may accordingly happen that officials in the city management section can not grasp the actual status or demand to the status of the report. To solve the problems, automatic finding incomplete reports and completing missing information are indispensable. In this paper, we propose methods to detect parts related to an actual status or demand to the status in a report using empirical patterns, dependency relations, and several machine learning techniques. Experimental results show that an average F-score and an average accuracy score our methods achieved were 0.798 and 0.893, respectively. In addition, in our methods, RF achieved better results than SVM for both F-score and accuracy scores.

AB - Government 2.0 activities have become attractive and popular these days. Using tools of their activities, anyone can report issues or complaints in a city on the Web with their photographs and geographical information, and share their information with other people. On the other hand, unlike telephone calls, the concreteness of a report depends on its reporter. Thus, the actual status and demand to the status may not be described clearly or either one may be miss-described in the report. It may accordingly happen that officials in the city management section can not grasp the actual status or demand to the status of the report. To solve the problems, automatic finding incomplete reports and completing missing information are indispensable. In this paper, we propose methods to detect parts related to an actual status or demand to the status in a report using empirical patterns, dependency relations, and several machine learning techniques. Experimental results show that an average F-score and an average accuracy score our methods achieved were 0.798 and 0.893, respectively. In addition, in our methods, RF achieved better results than SVM for both F-score and accuracy scores.

UR - http://www.scopus.com/inward/record.url?scp=85028662257&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85028662257&partnerID=8YFLogxK

U2 - 10.1527/tjsai.AG16-B

DO - 10.1527/tjsai.AG16-B

M3 - Article

AN - SCOPUS:85028662257

VL - 32

SP - AG16-B_1-AG16-B_10

JO - Transactions of the Japanese Society for Artificial Intelligence

JF - Transactions of the Japanese Society for Artificial Intelligence

SN - 1346-0714

IS - 5

ER -