View : 347 Download: 0

Deep learning models and datasets for aspect term sentiment classification: Implementing holistic recurrent attention on target-dependent memories

Title
Deep learning models and datasets for aspect term sentiment classification: Implementing holistic recurrent attention on target-dependent memories
Authors
Park, Hyun-jungSong, MinchaeShin, Kyung-Shik
Ewha Authors
신경식박현정송민채
SCOPUS Author ID
신경식scopus; 박현정scopus
Issue Date
2020
Journal Title
KNOWLEDGE-BASED SYSTEMS
ISSN
0950-7051JCR Link

1872-7409JCR Link
Citation
KNOWLEDGE-BASED SYSTEMS vol. 187
Keywords
Aspect-based sentiment analysisSentiment classificationDeep learningLSTMGRUAttention
Publisher
ELSEVIER
Indexed
SCIE; SCOPUS WOS scopus
Document Type
Article
Abstract
An essential challenge in aspect term sentiment classification using deep learning is modeling a tailormade sentence representation towards given aspect terms to enhance the classification performance. To seek a solution to this, we have two main research questions: (1) Which factors are vital for a sentiment classifier? (2) How will these factors interact with dataset characteristics? Regarding the first question, harmonious combination of location attention and content attention may be crucial to alleviate semantic mismatch problem between aspect terms and opinion words. However, location attention does not reflect the fact that critical opinion words usually come left or right of corresponding aspect terms, as implied in the target-dependent method although not well elucidated before. Besides, content attention needs to be sophisticated to combine multiple attention outcomes nonlinearly and consider the entire context to address complicated sentences. We merge all these significant factors for the first time, and design two models differing a little in the implementation of a few factors. Concerning the second question, we suggest a new multifaceted view on the dataset beyond the current tendency to be somewhat indifferent to the dataset in pursuit of a universal best performer. We then observe the interaction between factors of model architecture and dimensions of dataset characteristics. Experimental results show that our models achieve state-of-the-art or comparable performances and that there exist some useful relationships such as superior performance of bidirectional LSTM over one-directional LSTM for sentences containing multiple aspects and vice versa for sentences containing only one aspect. (C) 2019 Elsevier B.V. All rights reserved.
DOI
10.1016/j.knosys.2019.06.033
Appears in Collections:
경영대학 > 경영학전공 > Journal papers
Files in This Item:
There are no files associated with this item.
Export
RIS (EndNote)
XLS (Excel)
XML


qrcode

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

BROWSE