Header

UZH-Logo

Maintenance Infos

A Simple and Effective biLSTM Approach to Aspect-Based Sentiment Analysis in Social Media Customer Feedback


Clematide, Simon (2018). A Simple and Effective biLSTM Approach to Aspect-Based Sentiment Analysis in Social Media Customer Feedback. In: Barbaresi, Adrien; Biber, Hanno; Neubarth, Friedrich; Osswald, Rainer. 14th Conference on Natural Language Processing - KONVENS 2018. Vienna: Verlag der Österreichischen Akademie der Wissenschaften, 29-33.

Abstract

This paper describes a system for aspectbased sentiment analysis (ABSA) using a straight-forward supervised sequence labeling approach. Specifically, we apply a bidirectional, recurrent long short-term memory (biLSTM) architecture with a multilayer perceptron on top that predicts the labels token by token. We deal with the issue of rare words by dynamically switching between character-level and token-level representations depending on an occurrence threshold. A simple encoding of the aspects and their sentiments, a careful preprocessing of the data, and a generous ensemble of 24 single models beats the published state-of-the-art results for the GermEval 2017 ABSA data set for aspect-based sentiment analysis on the document level (joint prediction of aspect and sentiment in task C). For task D, the opinion target expression (OPE) detection task, our approach improves the current state-of-the-art even by 2.7-14.3 percentage points.

Abstract

This paper describes a system for aspectbased sentiment analysis (ABSA) using a straight-forward supervised sequence labeling approach. Specifically, we apply a bidirectional, recurrent long short-term memory (biLSTM) architecture with a multilayer perceptron on top that predicts the labels token by token. We deal with the issue of rare words by dynamically switching between character-level and token-level representations depending on an occurrence threshold. A simple encoding of the aspects and their sentiments, a careful preprocessing of the data, and a generous ensemble of 24 single models beats the published state-of-the-art results for the GermEval 2017 ABSA data set for aspect-based sentiment analysis on the document level (joint prediction of aspect and sentiment in task C). For task D, the opinion target expression (OPE) detection task, our approach improves the current state-of-the-art even by 2.7-14.3 percentage points.

Statistics

Altmetrics

Downloads

22 downloads since deposited on 25 Jan 2019
22 downloads since 12 months
Detailed statistics

Additional indexing

Item Type:Book Section, original work
Communities & Collections:06 Faculty of Arts > Institute of Computational Linguistics
Dewey Decimal Classification:000 Computer science, knowledge & systems
410 Linguistics
Uncontrolled Keywords:sentiment analysis aspect-based sentiment analysis sequence labeling
Language:English
Date:12 December 2018
Deposited On:25 Jan 2019 07:46
Last Modified:17 Sep 2019 19:56
Publisher:Verlag der Österreichischen Akademie der Wissenschaften
ISBN:978-3-7001-8437-9
OA Status:Green
Free access at:Official URL. An embargo period may apply.
Official URL:https://epub.oeaw.ac.at/?arp=0x003a238a

Download

Download PDF  'A Simple and Effective biLSTM Approach to Aspect-Based Sentiment Analysis in Social Media Customer Feedback'.
Preview
Content: Published Version
Language: English
Filetype: PDF
Size: 177kB
Get full-text in a library