Aspect-level Sentiment Analysis for Social Media Data in the Political Domain using Hierarchical Attention and Position Embeddings

Renny Pradina Kusumawardani, Muhammad Wildan Maulidani

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

5 Citations (Scopus)

Abstract

In this paper we present our work on aspect-level sentiment analysis on social media data, specifically in the political domain. Aside from being linguistically irregular, political tweets are often ambiguous or contain sentiments of opposite polarity. To address this, we use a deep learning architecture with a hierarchical attention and position embeddings to enable a finer-grained analysis of sentiments at different positions in the text. Our dataset consists of3022 tweets on the politics domain in Bahasa Indonesia having 1514 unique aspects. We find that there are two important factors for model performance: first, the use of a gating mechanism of appropriate complexity - in our case, LSTM gives the best performance in terms of accuracy and outperforms GRU and RNN by almost 7% in average recall. Second, the use of a trainable embeddings pre-trained on data in similar domains - a trainable Word2Vec embeddings trained on social media data in Bahasa Indonesia gives more than 4% better accuracy than without trainable embeddings. Our analysis also shows that correctly predicted tweets have more variance in attention weights, in contrast to incorrectly predicted ones to which input tokens are often assigned similar weights. This indicates the usefulness of attention mechanism in an aspect-based sentiment analysis.

Original languageEnglish
Title of host publication2020 International Conference on Data Science and Its Applications, ICoDSA 2020
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781728182353
DOIs
Publication statusPublished - Aug 2020
Event2020 International Conference on Data Science and Its Applications, ICoDSA 2020 - Bandung, Indonesia
Duration: 5 Aug 20206 Aug 2020

Publication series

Name2020 International Conference on Data Science and Its Applications, ICoDSA 2020

Conference

Conference2020 International Conference on Data Science and Its Applications, ICoDSA 2020
Country/TerritoryIndonesia
CityBandung
Period5/08/206/08/20

Keywords

  • aspect-level
  • deep learning
  • hierarchical attention
  • political domain
  • position embeddings
  • sentiment analysis
  • social media

Fingerprint

Dive into the research topics of 'Aspect-level Sentiment Analysis for Social Media Data in the Political Domain using Hierarchical Attention and Position Embeddings'. Together they form a unique fingerprint.

Cite this