Topic-Based Document-Level Sentiment Analysis Using Contextual Cues

Document-level Sentiment Analysis is a complex task that implies the analysis of large textual content that can incorporate multiple contradictory polarities at the phrase and word levels. Most of the current approaches either represent textual data using pre-trained word embeddings without consider...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Ciprian-Octavian Truică, Elena-Simona Apostol, Maria-Luiza Șerban, Adrian Paschke
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	document-level Sentiment Analysis document-topic embeddings Topic Modeling Deep Learning Architectures Mathematics QA1-939
Acceso en línea:	https://doaj.org/article/fcc251ef6f8741c1bd58e33288986d24
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:fcc251ef6f8741c1bd58e33288986d24
record_format	dspace
spelling	oai:doaj.org-article:fcc251ef6f8741c1bd58e33288986d242021-11-11T18:16:38ZTopic-Based Document-Level Sentiment Analysis Using Contextual Cues10.3390/math92127222227-7390https://doaj.org/article/fcc251ef6f8741c1bd58e33288986d242021-10-01T00:00:00Zhttps://www.mdpi.com/2227-7390/9/21/2722https://doaj.org/toc/2227-7390Document-level Sentiment Analysis is a complex task that implies the analysis of large textual content that can incorporate multiple contradictory polarities at the phrase and word levels. Most of the current approaches either represent textual data using pre-trained word embeddings without considering the local context that can be extracted from the dataset, or they detect the overall topic polarity without considering both the local and global context. In this paper, we propose a novel document-topic embedding model, <span style="font-variant: small-caps;">DocTopic</span>2<span style="font-variant: small-caps;">Vec</span>, for document-level polarity detection in large texts by employing general and specific contextual cues obtained through the use of document embeddings (<span style="font-variant: small-caps;">Doc</span>2<span style="font-variant: small-caps;">Vec</span>) and Topic Modeling. In our approach, <i>(1)</i> we use a large dataset with game reviews to create different word embeddings by applying <span style="font-variant: small-caps;">Word</span>2<span style="font-variant: small-caps;">Vec</span>, <span style="font-variant: small-caps;">FastText</span>, and <span style="font-variant: small-caps;">GloVe</span>, <i>(2)</i> we create <span style="font-variant: small-caps;">Doc</span>2<span style="font-variant: small-caps;">Vec</span>s enriched with the local context given by the word embeddings for each review, <i>(3)</i> we construct topic embeddings <span style="font-variant: small-caps;">Topic</span>2<span style="font-variant: small-caps;">Vec</span> using three Topic Modeling algorithms, i.e., LDA, NMF, and LSI, to enhance the global context of the Sentiment Analysis task, <i>(4)</i> for each document and its dominant topic, we build the new <span style="font-variant: small-caps;">DocTopic</span>2<span style="font-variant: small-caps;">Vec</span> by concatenating the <span style="font-variant: small-caps;">Doc</span>2<span style="font-variant: small-caps;">Vec</span> with the <span style="font-variant: small-caps;">Topic</span>2<span style="font-variant: small-caps;">Vec</span> created with the same word embedding. We also design six new Convolutional-based (Bidirectional) Recurrent Deep Neural Network Architectures that show promising results for this task. The proposed <span style="font-variant: small-caps;">DocTopic</span>2<span style="font-variant: small-caps;">Vec</span>s are used to benchmark multiple Machine and Deep Learning models, i.e., a Logistic Regression model, used as a baseline, and 18 Deep Neural Networks Architectures. The experimental results show that the new embedding and the new Deep Neural Network Architectures achieve better results than the baseline, i.e., Logistic Regression and <span style="font-variant: small-caps;">Doc</span>2<span style="font-variant: small-caps;">Vec</span>.Ciprian-Octavian TruicăElena-Simona ApostolMaria-Luiza ȘerbanAdrian PaschkeMDPI AGarticledocument-level Sentiment Analysisdocument-topic embeddingsTopic ModelingDeep Learning ArchitecturesMathematicsQA1-939ENMathematics, Vol 9, Iss 2722, p 2722 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	document-level Sentiment Analysis document-topic embeddings Topic Modeling Deep Learning Architectures Mathematics QA1-939
spellingShingle	document-level Sentiment Analysis document-topic embeddings Topic Modeling Deep Learning Architectures Mathematics QA1-939 Ciprian-Octavian Truică Elena-Simona Apostol Maria-Luiza Șerban Adrian Paschke Topic-Based Document-Level Sentiment Analysis Using Contextual Cues
description	Document-level Sentiment Analysis is a complex task that implies the analysis of large textual content that can incorporate multiple contradictory polarities at the phrase and word levels. Most of the current approaches either represent textual data using pre-trained word embeddings without considering the local context that can be extracted from the dataset, or they detect the overall topic polarity without considering both the local and global context. In this paper, we propose a novel document-topic embedding model, <span style="font-variant: small-caps;">DocTopic</span>2<span style="font-variant: small-caps;">Vec</span>, for document-level polarity detection in large texts by employing general and specific contextual cues obtained through the use of document embeddings (<span style="font-variant: small-caps;">Doc</span>2<span style="font-variant: small-caps;">Vec</span>) and Topic Modeling. In our approach, <i>(1)</i> we use a large dataset with game reviews to create different word embeddings by applying <span style="font-variant: small-caps;">Word</span>2<span style="font-variant: small-caps;">Vec</span>, <span style="font-variant: small-caps;">FastText</span>, and <span style="font-variant: small-caps;">GloVe</span>, <i>(2)</i> we create <span style="font-variant: small-caps;">Doc</span>2<span style="font-variant: small-caps;">Vec</span>s enriched with the local context given by the word embeddings for each review, <i>(3)</i> we construct topic embeddings <span style="font-variant: small-caps;">Topic</span>2<span style="font-variant: small-caps;">Vec</span> using three Topic Modeling algorithms, i.e., LDA, NMF, and LSI, to enhance the global context of the Sentiment Analysis task, <i>(4)</i> for each document and its dominant topic, we build the new <span style="font-variant: small-caps;">DocTopic</span>2<span style="font-variant: small-caps;">Vec</span> by concatenating the <span style="font-variant: small-caps;">Doc</span>2<span style="font-variant: small-caps;">Vec</span> with the <span style="font-variant: small-caps;">Topic</span>2<span style="font-variant: small-caps;">Vec</span> created with the same word embedding. We also design six new Convolutional-based (Bidirectional) Recurrent Deep Neural Network Architectures that show promising results for this task. The proposed <span style="font-variant: small-caps;">DocTopic</span>2<span style="font-variant: small-caps;">Vec</span>s are used to benchmark multiple Machine and Deep Learning models, i.e., a Logistic Regression model, used as a baseline, and 18 Deep Neural Networks Architectures. The experimental results show that the new embedding and the new Deep Neural Network Architectures achieve better results than the baseline, i.e., Logistic Regression and <span style="font-variant: small-caps;">Doc</span>2<span style="font-variant: small-caps;">Vec</span>.
format	article
author	Ciprian-Octavian Truică Elena-Simona Apostol Maria-Luiza Șerban Adrian Paschke
author_facet	Ciprian-Octavian Truică Elena-Simona Apostol Maria-Luiza Șerban Adrian Paschke
author_sort	Ciprian-Octavian Truică
title	Topic-Based Document-Level Sentiment Analysis Using Contextual Cues
title_short	Topic-Based Document-Level Sentiment Analysis Using Contextual Cues
title_full	Topic-Based Document-Level Sentiment Analysis Using Contextual Cues
title_fullStr	Topic-Based Document-Level Sentiment Analysis Using Contextual Cues
title_full_unstemmed	Topic-Based Document-Level Sentiment Analysis Using Contextual Cues
title_sort	topic-based document-level sentiment analysis using contextual cues
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/fcc251ef6f8741c1bd58e33288986d24
work_keys_str_mv	AT ciprianoctaviantruica topicbaseddocumentlevelsentimentanalysisusingcontextualcues AT elenasimonaapostol topicbaseddocumentlevelsentimentanalysisusingcontextualcues AT marialuizaserban topicbaseddocumentlevelsentimentanalysisusingcontextualcues AT adrianpaschke topicbaseddocumentlevelsentimentanalysisusingcontextualcues
_version_	1718431920711270400

Topic-Based Document-Level Sentiment Analysis Using Contextual Cues

Ejemplares similares