[vc_empty_space][vc_empty_space]
Aspect-based sentiment analysis approach with CNN
Mulyo B.M.a, Widyantoro D.H.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]© 2018 IEEE.Lots of research has been done on the domain of Sentiment Analysis, for example, research that conducted by Bing Liu’s (2012) [1]. Other research conducted in a SemEval competition, the domain of sentiment analysis research has been developed further up to the aspect or commonly called Aspect Based Sentiment Analysis (ABSA) [2]. The domain problem of Aspect Based Sentiment Analysis (ABSA) from SemEval is quite diverse, all of those problems arise mostly from the real data provided. Some existing problems include Implicit, Multi-label, Out Of Vocabulary (OOV), Expression extraction, and the detection of aspects and polarities. This research only focuses on classification aspect and classification of sentiment. This study uses an existing method of Convolution Neural Network (CNN) method, which was introduced again by Alex K. The study by Alex K reduces the error rate by 15%, compared in the previous year the decrease was only 5%. This research would like to propose CNN methods that have been optimized, and use Threshold (CNN-T) to select the best data in training data. This method can produce more than one aspect using one data test. The average result of this experiment using CNN-T got better F-Measure compared to CNN and 3 classic Machine Learning method, i.e. SVM, Naive Bayes, and KNN. The overall F1 score of CNN-T is 0.71, which is greater than the other comparable methods.[/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]Aspect Classification,Convolutional Neural Network,Deep Learning,Multi-Class,Multi-label,Sentiment 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/10.1109/EECSI.2018.8752857[/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]