[vc_empty_space][vc_empty_space]
Indonesian Twitter text authority classification for government in Bandung
Laksana J.a, Purwarianti A.a
a Informatics Engineering, Bandung Institute of Technology, Indonesia
[vc_row][vc_column][vc_row_inner][vc_column_inner][vc_separator css=”.vc_custom_1624529070653{padding-top: 30px !important;padding-bottom: 30px !important;}”][/vc_column_inner][/vc_row_inner][vc_row_inner layout=”boxed”][vc_column_inner width=”3/4″ css=”.vc_custom_1624695412187{border-right-width: 1px !important;border-right-color: #dddddd !important;border-right-style: solid !important;border-radius: 1px !important;}”][vc_empty_space][megatron_heading title=”Abstract” size=”size-sm” text_align=”text-left”][vc_column_text]© 2014 IEEE.Nowadays, social media based complaint management systems have been deployed in several countries and cities including Bandung. We proposed an automatic authority classification for Twitter text in Indonesian as part of the complaint management system. Our analysis showed that there are several Twitter message types raised in official account Twitter of the city government. The classification employed a statistical based multi-label text classification. Here, we compared several techniques in the classification such as the features, the algorithms and the classification schemes. In the features comparison, we examined several features such as the complaint word feature, n-gram feature, and the @username feature. In the algorithms comparison, we employed Decision Tree algorithm, Naïve Bayes algorithm, and Support Vector Machine algorithm with multi-label classification techniques of Binary Relevance and Label Power Set. In the complaint classification schemes, we compared the direct classification and two steps classification. Using 2244 twitter texts from twitter of Bandung city government and 5-fold cross validation, the best experimental result of 70.90% accuracy was achieved by the feature combination of 1-gram and complaint word, with Support Vector Machine and Label Power Set as the algorithm, in the direct scheme of text classification.[/vc_column_text][vc_empty_space][vc_separator css=”.vc_custom_1624528584150{padding-top: 25px !important;padding-bottom: 25px !important;}”][vc_empty_space][megatron_heading title=”Author keywords” size=”size-sm” text_align=”text-left”][vc_column_text]Bandung,Classification scheme,Decision-tree algorithm,Management systems,Multi label classification,Multi-label text classification,Support vector machine algorithm,Twitter[/vc_column_text][vc_empty_space][vc_separator css=”.vc_custom_1624528584150{padding-top: 25px !important;padding-bottom: 25px !important;}”][vc_empty_space][megatron_heading title=”Indexed keywords” size=”size-sm” text_align=”text-left”][vc_column_text]Authority Classification,Bandung,Complaint Management System,Twitter[/vc_column_text][vc_empty_space][vc_separator css=”.vc_custom_1624528584150{padding-top: 25px !important;padding-bottom: 25px !important;}”][vc_empty_space][megatron_heading title=”Funding details” size=”size-sm” text_align=”text-left”][vc_column_text][/vc_column_text][vc_empty_space][vc_separator css=”.vc_custom_1624528584150{padding-top: 25px !important;padding-bottom: 25px !important;}”][vc_empty_space][megatron_heading title=”DOI” size=”size-sm” text_align=”text-left”][vc_column_text]https://doi.org/10.1109/ICAICTA.2014.7005928[/vc_column_text][/vc_column_inner][vc_column_inner width=”1/4″][vc_column_text]Widget Plumx[/vc_column_text][/vc_column_inner][/vc_row_inner][/vc_column][/vc_row][vc_row][vc_column][vc_separator css=”.vc_custom_1624528584150{padding-top: 25px !important;padding-bottom: 25px !important;}”][/vc_column][/vc_row]