Logical Entity Level Sentiment Analysis

Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review

318 Downloads (Pure)

Abstract

We present a formal logical approach using a combinatory categorial grammar for entity level sentiment analysis that utilizes machine learning techniques for efficient syntactical tagging and performs a deep structural analysis of the syntactical properties of texts in order to yield precise results. The method should be seen as an alternative to pure machine learning methods for sentiment analysis, which are argued to have high difficulties in capturing long distance dependencies, and can be dependent on significant amount of domain specific training data. The results show that the method yields high correctness, but further investment is needed in order to improve its robustness.
Original languageEnglish
Title of host publicationInternational Conference on Formal Grammar
EditorsAnnie Foret, Reinhardt Muskens, Sylvain Pogodalla
PublisherSpringer
Publication date2017
Pages54-71
DOIs
Publication statusPublished - 2017
Event22nd International Conference, Formal Grammar 2017 - Toulouse, France
Duration: 22 Jul 201723 Jul 2017
Conference number: 22

Conference

Conference22nd International Conference, Formal Grammar 2017
Number22
CountryFrance
CityToulouse
Period22/07/201723/07/2017
SeriesLecture Notes in Computer Science
Volume10686
ISSN0302-9743

Fingerprint Dive into the research topics of 'Logical Entity Level Sentiment Analysis'. Together they form a unique fingerprint.

Cite this