ScholarSpace will be down for maintenance on Thursday (8/16) at 8am HST (6pm UTC)
Please use this identifier to cite or link to this item:

Improving Sentiment Analysis with Document-Level Semantic Relationships from Rhetoric Discourse Structures

File SizeFormat 
paper0139.pdf918.02 kBAdobe PDFView/Open

Item Summary

Title: Improving Sentiment Analysis with Document-Level Semantic Relationships from Rhetoric Discourse Structures
Authors: Märkle-Huß, Joscha
Feuerriegel, Stefan
Prendinger, Helmut
Keywords: Sentiment analysis
Semantic Relationships
Rhetoric structure theory
Machine learning
Issue Date: 04 Jan 2017
Abstract: Conventional sentiment analysis usually neglects semantic information between (sub-)clauses, as it merely implements so-called bag-of-words approaches, where the sentiment of individual words is aggregated independently of the document structure. Instead, we advance sentiment analysis by the use of rhetoric structure theory (RST), which provides a hierarchical representation of texts at document level. For this purpose, texts are split into elementary discourse units (EDU). These EDUs span a hierarchical structure in the form of a binary tree, where the branches are labeled according to their semantic discourse. Accordingly, this paper proposes a novel combination of weighting and grid search to aggregate sentiment scores from the RST tree, as well as feature engineering for machine learning. We apply our algorithms to the especially hard task of predicting stock returns subsequent to financial disclosures. As a result, machine learning improves the balanced accuracy by 8.6 percent compared to the baseline.
Pages/Duration: 10 pages
ISBN: 978-0-9981331-0-2
DOI: 10.24251/HICSS.2017.135
Rights: Attribution-NonCommercial-NoDerivatives 4.0 International
Appears in Collections:Data, Text, and Web Mining for Business Analytics Minitrack

Please email if you need this content in an ADA-compliant format.

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