[vc_empty_space][vc_empty_space]
Aspect Detection and Sentiment Classification Using Deep Neural Network for Indonesian Aspect-Based Sentiment Analysis
Ilmania A.a, Abdurrahmana, Cahyawijaya S.a, Purwarianti A.b
a Prosa Solusi Cerdas, Bandung, Indonesia
b 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.Sentiment analysis can categorize an overall opinion from a sentence or a document. However, there are sentences with more than one opinion in a single sentence statement. This problem is solved by aspect-based sentiment analysis. We conduct experiments on this problem using Indonesian dataset with 2-step process: aspect detection and sentiment classification. On aspect detection, we compare two deep neural network models with different input vector and topology: word embedding vector which is processed using gated recurrent unit (GRU), and bag-of-words vector which is processed using fully-connected layer. On sentiment classification, we also compare two approaches of deep neural network. The first approach uses word embedding, sentiment lexicon and POS tags as the input vector, with bi-GRU based as the topology. The second one uses aspect matrix to rescale the word embedding vector as the input vector and convolutional neural network (CNN)based as the topology. Our work is compared to a baseline framework which uses different model for each aspect. The dataset has approximately 9800 reviews collected from various categories on popular online marketplaces in Indonesia. Our models generalize well over all aspects and achieve state-of-the-art performance on 4 out of 7 aspects compared to the baseline framework.[/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]aspect-based,Convolutional neural network,Indonesian,Neural network model,On-line marketplaces,Sentiment classification,Sentiment lexicons,State-of-the-art performance[/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 detection,aspect-based,deep neural network,Indonesian,sentiment analysis,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/IALP.2018.8629181[/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]