search for




 

Sentimatal analysis on urban regeneration policy: Focused on reviews of Gamcheon culture village
Journal of the Korean Data & Information Science Society 2019;30:1233-44
Published online November 30, 2019;  https://doi.org/10.7465/jkdi.2019.30.6.1233
© 2019 Korean Data and Information Science Society.

Soongoo Hong1 · Seungeui Ryu2 · Soonjae Ahn3

1Department of Management Information System, Dong-A University
23Smart Governance Research Center, Dong-A University
Correspondence to: Ph.D., Smart Governance Research Center, Dong-A University, Busan, Korea. E-mail: juim0928@dau.ac.kr

This work was supported by the Ministry of Education of the Republic of Korea and the National Research Foundation of Korea(NRF-2018S1A3A2075240).
Received August 23, 2019; Revised September 23, 2019; Accepted September 24, 2019.
This is an Open Access article distributed under the terms of the Creative Commons Attribution Non-Commercial License (http://creativecommons.org/licenses/by-nc/3.0) which permits unrestricted non-commercial use, distribution, and reproduction in any medium, provided the original work is properly cited.
Abstract
This study conducted a sentiment analysis using comments from domestic tourists who visited the Gamcheon Culture Village to evaluate the government’s urban regeneration project automatically and efficiently. For this purpose, 41,496 comments from the local review from Google Map were collected and analyzed using a Multi-Channel CNN model that combines morphemes, syllables, and phonemes. The accuracy of the Multi-Channel CNN model was 85.72 percent, which is higher than the accuracy seen in Single-Channel CNN model. In the sentiment analysis, the ratio between the positive and negative responses was eight to two, indicating overall positive opinion regarding the urban regeneration project that is taking place in the Gamcheon Culture Village. Furthermore, the main factors that generated the positive and negative sentiments were extracted by classifying each positive and negative sentence using the TF-IDF weighted model. This study has an academic contribution in that the suggestion of policy evaluation through the application of a sentiment analysis will induce future studies. Practically, this study suggested an analysis of the visitors’ comments as a new method of evaluating government policies, which can be used as fundamental data that can determine the success of other government projects in the future.
Keywords : Big data analysis, Gamcheon culture village, policy evaluation, sentimental analysis, TF-IDF weighted model, urban regeneration policy.