Combining Formal Logic and Machine Learning for Sentiment Analysis

Niklas Christoffer  Petersen; Jørgen Villadsen

Combining Formal Logic and Machine Learning for Sentiment Analysis

Niklas Christoffer Petersen, Jørgen Villadsen

Department of Applied Mathematics and Computer Science

Technical University of Denmark

Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

Abstract

This paper presents a formal logical method for deep structural analysis of the syntactical properties of texts using machine learning techniques for efficient syntactical tagging. To evaluate the method it is used for entity level sentiment analysis as an alternative to pure machine learning methods for sentiment analysis, which often work on sentence or word level, and are argued to have difficulties in capturing long distance dependencies.

Original language	English
Title of host publication	Foundations of Intelligent Systems
Editors	T. Andreasen, H. Christiansen, J.-C. Cubero, Z.W. Ras
Publisher	Springer
Publication date	2014
Pages	375-384
ISBN (Print)	978-3-319-08325-4
Publication status	Published - 2014
Event	21st International Symposium on Methodologies for Intelligent Systems (ISMIS 2014) - Roskilde, Denmark Duration: 25 Jun 2014 → 27 Jun 2014 Conference number: 21 http://isl.ruc.dk/ismis2014/

Conference

Conference	21st International Symposium on Methodologies for Intelligent Systems (ISMIS 2014)
Number	21
Country/Territory	Denmark
City	Roskilde
Period	25/06/2014 → 27/06/2014
Internet address	http://isl.ruc.dk/ismis2014/

Series	Lecture Notes in Computer Science
Volume	8502
ISSN	0302-9743

OpenUrl availability

Full text

Cite this

@inproceedings{023bb8268f534aff92fde9f958b89939,

title = "Combining Formal Logic and Machine Learning for Sentiment Analysis",

abstract = "This paper presents a formal logical method for deep structural analysis of the syntactical properties of texts using machine learning techniques for efficient syntactical tagging. To evaluate the method it is used for entity level sentiment analysis as an alternative to pure machine learning methods for sentiment analysis, which often work on sentence or word level, and are argued to have difficulties in capturing long distance dependencies.",

author = "Petersen, {Niklas Christoffer} and J{\o}rgen Villadsen",

year = "2014",

language = "English",

isbn = "978-3-319-08325-4",

series = "Lecture Notes in Computer Science",

publisher = "Springer",

pages = "375--384",

editor = "T. Andreasen and H. Christiansen and J.-C. Cubero and Z.W. Ras",

booktitle = "Foundations of Intelligent Systems",

note = "21st International Symposium on Methodologies for Intelligent Systems (ISMIS 2014), ISMIS ; Conference date: 25-06-2014 Through 27-06-2014",

url = "http://isl.ruc.dk/ismis2014/",

}

Petersen, NC & Villadsen, J 2014, Combining Formal Logic and Machine Learning for Sentiment Analysis. in T Andreasen, H Christiansen, J-C Cubero & ZW Ras (eds), Foundations of Intelligent Systems. Springer, Lecture Notes in Computer Science, vol. 8502, pp. 375-384, 21st International Symposium on Methodologies for Intelligent Systems (ISMIS 2014), Roskilde, Denmark, 25/06/2014.

Combining Formal Logic and Machine Learning for Sentiment Analysis. / Petersen, Niklas Christoffer ; Villadsen, Jørgen.

Foundations of Intelligent Systems. ed. / T. Andreasen; H. Christiansen; J.-C. Cubero; Z.W. Ras. Springer, 2014. p. 375-384 (Lecture Notes in Computer Science, Vol. 8502).

Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

TY - GEN

T1 - Combining Formal Logic and Machine Learning for Sentiment Analysis

AU - Petersen, Niklas Christoffer

AU - Villadsen, Jørgen

N1 - Conference code: 21

PY - 2014

Y1 - 2014

N2 - This paper presents a formal logical method for deep structural analysis of the syntactical properties of texts using machine learning techniques for efficient syntactical tagging. To evaluate the method it is used for entity level sentiment analysis as an alternative to pure machine learning methods for sentiment analysis, which often work on sentence or word level, and are argued to have difficulties in capturing long distance dependencies.

AB - This paper presents a formal logical method for deep structural analysis of the syntactical properties of texts using machine learning techniques for efficient syntactical tagging. To evaluate the method it is used for entity level sentiment analysis as an alternative to pure machine learning methods for sentiment analysis, which often work on sentence or word level, and are argued to have difficulties in capturing long distance dependencies.

M3 - Article in proceedings

SN - 978-3-319-08325-4

T3 - Lecture Notes in Computer Science

SP - 375

EP - 384

BT - Foundations of Intelligent Systems

A2 - Andreasen, T.

A2 - Christiansen, H.

A2 - Cubero, J.-C.

A2 - Ras, Z.W.

PB - Springer

T2 - 21st International Symposium on Methodologies for Intelligent Systems (ISMIS 2014)

Y2 - 25 June 2014 through 27 June 2014

ER -

Combining Formal Logic and Machine Learning for Sentiment Analysis

Abstract

Conference

OpenUrl availability

Fingerprint

Cite this