[vc_empty_space][vc_empty_space]
Automatic identification of compare paper relations
Sibaroni Y.a, Widyantoro D.H.a, Khodra M.L.a
a School of Electrical Engineering and Informatics, Institut Teknologi Bandung, Bandung, 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]© 2020, School of Electrical Engineering and Informatics. All rights reserved.One important issue in performing a good research is to compare their current research with results of others. However, the comparison requires two or more papers to form a so-called compare-paper relation. This comparison can be identified based on their citation context, that consist of high number of sentences, rather than through basic features such as N-Gram. To investigate the relationship between papers, Wang et al. and several other researchers have applied the cue phrase feature, which was obtained via a manual analysis of a data set of scientific paper. Furthermore, a more complex feature was proposed by Park and Black for the same purpose. Nevertheless, they were unable to investigate accurately such relation, since their features are not made specifically for this purpose. In this paper, we propose new features that specifically intended to identify the relationship of papers or compare-paper relation. The experimental results show that the proposed features result in much better performance compared to the experiments by using the best baseline feature. By using 6 different classifiers, the experimental results also show that maximal values result in best values for each classifier. Moreover, other experimental results show that the best performance is obtained by combining the baseline features and the newly developed features, which shows that they are mutually reinforcing.[/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][/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]Compare,Cue phrase,Feature,Paper relation,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=”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/10.15676/ijeei.2020.12.1.12[/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]