Topic-Based Document-Level Sentiment Analysis Using Contextual Cues

Ciprian-Octavian Truică, Elena-Simona Apostol, Maria-Luiza Șerban and Adrian Paschke
Additional contact information
Ciprian-Octavian Truică: Computer Science and Engineering Department, Faculty of Automatic Control and Computers, University Politehnica of Bucharest, RO-060042 Bucharest, Romania
Elena-Simona Apostol: Computer Science and Engineering Department, Faculty of Automatic Control and Computers, University Politehnica of Bucharest, RO-060042 Bucharest, Romania
Maria-Luiza Șerban: Computer Science and Engineering Department, Faculty of Automatic Control and Computers, University Politehnica of Bucharest, RO-060042 Bucharest, Romania
Adrian Paschke: Fraunhofer Institute for Open Communication Systems, 10589 Berlin, Germany

Mathematics, 2021, vol. 9, issue 21, 1-23

Abstract: 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, DocTopic 2 Vec , for document-level polarity detection in large texts by employing general and specific contextual cues obtained through the use of document embeddings ( Doc 2 Vec ) and Topic Modeling. In our approach, (1) we use a large dataset with game reviews to create different word embeddings by applying Word 2 Vec , FastText , and GloVe , (2) we create Doc 2 Vec s enriched with the local context given by the word embeddings for each review, (3) we construct topic embeddings Topic 2 Vec using three Topic Modeling algorithms, i.e., LDA, NMF, and LSI, to enhance the global context of the Sentiment Analysis task, (4) for each document and its dominant topic, we build the new DocTopic 2 Vec by concatenating the Doc 2 Vec with the Topic 2 Vec 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 DocTopic 2 Vec 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 Doc 2 Vec .

Keywords: document-level Sentiment Analysis; document-topic embeddings; Topic Modeling; Deep Learning Architectures (search for similar items in EconPapers)
JEL-codes: C (search for similar items in EconPapers)
Date: 2021
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (1)

Downloads: (external link)
https://www.mdpi.com/2227-7390/9/21/2722/pdf (application/pdf)
https://www.mdpi.com/2227-7390/9/21/2722/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jmathe:v:9:y:2021:i:21:p:2722-:d:665812

Access Statistics for this article

Mathematics is currently edited by Ms. Emma He

More articles in Mathematics from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().