An analytical approach to assess sentiment of text

Mostafa Al Masum Shaikh, Helmut Prendinger, Mitsuru Ishizuka

Research output: Chapter in Book/Report/Conference proceedingConference contribution

3 Citations (Scopus)

Abstract

Sentiment (i.e., bad or good opinion) described in texts has been studied widely, and at three different levels: word, sentence, and document level. This paper describes a well-founded approach for the task of sentence level sentiment analysis by studying the relationship between sentiments conveyed through texts and structure of natural language by a method of numerical analysis. Different approaches have been employed to "sense" sentiment, especially from the texts, but none of those ever considered the valence based appraisal structure of sentiments which we have employed. Therefore the paper describes an approach to sense sentiments contained in a sentence by applying a numerical-valence based analysis. To meet this objective a linguistic tool, SenseNet, has been developed that provides lexical-units on the basis of each semantic verb frame obtained from the input sentence; assigns a numerical value to those based on their sense affinity; assesses the values using rules; and finally outputs sense-valence for each input sentence. Several experiments with a variety of datasets containing data from different domains have been conducted. The obtained results indicate significant performance gains over existing state-of-the-art approaches.

Original languageEnglish
Title of host publication2007 10th International Conference on Computer and Information Technology, ICCIT
DOIs
Publication statusPublished - 2007
Externally publishedYes
Event2007 10th International Conference on Computer and Information Technology, ICCIT - Dhaka
Duration: 2007 Dec 272007 Dec 29

Other

Other2007 10th International Conference on Computer and Information Technology, ICCIT
CityDhaka
Period07/12/2707/12/29

Fingerprint

Linguistics
Numerical analysis
Semantics
Experiments

Keywords

  • Affect sensing from text
  • Sentiment analysis

ASJC Scopus subject areas

  • Computer Science Applications
  • Software

Cite this

Shaikh, M. A. M., Prendinger, H., & Ishizuka, M. (2007). An analytical approach to assess sentiment of text. In 2007 10th International Conference on Computer and Information Technology, ICCIT [4579359] https://doi.org/10.1109/ICCITECHN.2007.4579359

An analytical approach to assess sentiment of text. / Shaikh, Mostafa Al Masum; Prendinger, Helmut; Ishizuka, Mitsuru.

2007 10th International Conference on Computer and Information Technology, ICCIT. 2007. 4579359.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Shaikh, MAM, Prendinger, H & Ishizuka, M 2007, An analytical approach to assess sentiment of text. in 2007 10th International Conference on Computer and Information Technology, ICCIT., 4579359, 2007 10th International Conference on Computer and Information Technology, ICCIT, Dhaka, 07/12/27. https://doi.org/10.1109/ICCITECHN.2007.4579359
Shaikh MAM, Prendinger H, Ishizuka M. An analytical approach to assess sentiment of text. In 2007 10th International Conference on Computer and Information Technology, ICCIT. 2007. 4579359 https://doi.org/10.1109/ICCITECHN.2007.4579359
Shaikh, Mostafa Al Masum ; Prendinger, Helmut ; Ishizuka, Mitsuru. / An analytical approach to assess sentiment of text. 2007 10th International Conference on Computer and Information Technology, ICCIT. 2007.
@inproceedings{5da75e1ccfac4743b82ad6b5d2f83d2f,
title = "An analytical approach to assess sentiment of text",
abstract = "Sentiment (i.e., bad or good opinion) described in texts has been studied widely, and at three different levels: word, sentence, and document level. This paper describes a well-founded approach for the task of sentence level sentiment analysis by studying the relationship between sentiments conveyed through texts and structure of natural language by a method of numerical analysis. Different approaches have been employed to {"}sense{"} sentiment, especially from the texts, but none of those ever considered the valence based appraisal structure of sentiments which we have employed. Therefore the paper describes an approach to sense sentiments contained in a sentence by applying a numerical-valence based analysis. To meet this objective a linguistic tool, SenseNet, has been developed that provides lexical-units on the basis of each semantic verb frame obtained from the input sentence; assigns a numerical value to those based on their sense affinity; assesses the values using rules; and finally outputs sense-valence for each input sentence. Several experiments with a variety of datasets containing data from different domains have been conducted. The obtained results indicate significant performance gains over existing state-of-the-art approaches.",
keywords = "Affect sensing from text, Sentiment analysis",
author = "Shaikh, {Mostafa Al Masum} and Helmut Prendinger and Mitsuru Ishizuka",
year = "2007",
doi = "10.1109/ICCITECHN.2007.4579359",
language = "English",
isbn = "1424415519",
booktitle = "2007 10th International Conference on Computer and Information Technology, ICCIT",

}

TY - GEN

T1 - An analytical approach to assess sentiment of text

AU - Shaikh, Mostafa Al Masum

AU - Prendinger, Helmut

AU - Ishizuka, Mitsuru

PY - 2007

Y1 - 2007

N2 - Sentiment (i.e., bad or good opinion) described in texts has been studied widely, and at three different levels: word, sentence, and document level. This paper describes a well-founded approach for the task of sentence level sentiment analysis by studying the relationship between sentiments conveyed through texts and structure of natural language by a method of numerical analysis. Different approaches have been employed to "sense" sentiment, especially from the texts, but none of those ever considered the valence based appraisal structure of sentiments which we have employed. Therefore the paper describes an approach to sense sentiments contained in a sentence by applying a numerical-valence based analysis. To meet this objective a linguistic tool, SenseNet, has been developed that provides lexical-units on the basis of each semantic verb frame obtained from the input sentence; assigns a numerical value to those based on their sense affinity; assesses the values using rules; and finally outputs sense-valence for each input sentence. Several experiments with a variety of datasets containing data from different domains have been conducted. The obtained results indicate significant performance gains over existing state-of-the-art approaches.

AB - Sentiment (i.e., bad or good opinion) described in texts has been studied widely, and at three different levels: word, sentence, and document level. This paper describes a well-founded approach for the task of sentence level sentiment analysis by studying the relationship between sentiments conveyed through texts and structure of natural language by a method of numerical analysis. Different approaches have been employed to "sense" sentiment, especially from the texts, but none of those ever considered the valence based appraisal structure of sentiments which we have employed. Therefore the paper describes an approach to sense sentiments contained in a sentence by applying a numerical-valence based analysis. To meet this objective a linguistic tool, SenseNet, has been developed that provides lexical-units on the basis of each semantic verb frame obtained from the input sentence; assigns a numerical value to those based on their sense affinity; assesses the values using rules; and finally outputs sense-valence for each input sentence. Several experiments with a variety of datasets containing data from different domains have been conducted. The obtained results indicate significant performance gains over existing state-of-the-art approaches.

KW - Affect sensing from text

KW - Sentiment analysis

UR - http://www.scopus.com/inward/record.url?scp=51549106280&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=51549106280&partnerID=8YFLogxK

U2 - 10.1109/ICCITECHN.2007.4579359

DO - 10.1109/ICCITECHN.2007.4579359

M3 - Conference contribution

AN - SCOPUS:51549106280

SN - 1424415519

SN - 9781424415519

BT - 2007 10th International Conference on Computer and Information Technology, ICCIT

ER -