Sentiment assessment of text by analyzing linguistic features and contextual valence assignment

Mostafa Al Masum Shaikh, Helmut Prendinger, Mitsuru Ishizuka

Research output: Contribution to journalArticle

30 Citations (Scopus)

Abstract

Text is not only an important medium to describe facts and events, but also to effectively communicate information about the writer's positive or negative sentiment underlying an opinion, or to express an affective or emotional state, such as happiness, fearfulness, surpriseness, and so on. We consider sentiment assessment and emotion sensing from text as two different problems, whereby sentiment assessment is the task that we want to solve first. Thus, this article presents an approach to sentiment assessment, i.e., the recognition of negative or positive valence of a sentence. For the purpose of sentiment recognition from text, we perform semantic dependency analysis on the semantic verb frames of each sentence, and then apply a set of rules to each dependency relation to calculate the contextual valence of the whole sentence. By employing a domain-independent, rule-based approach our system is able to automatically identify sentence-level sentiment. A linguistic tool called "SenseNet" has been developed to recognize sentiments in text, and to visualize the detected sentiments. We conducted several experiments with a variety of datasets containing data from different domains. The obtained results indicate significant performance gains over existing state-of-the-art approaches.

Original languageEnglish
Pages (from-to)558-601
Number of pages44
JournalApplied Artificial Intelligence
Volume22
Issue number6
DOIs
Publication statusPublished - 2008 Jul
Externally publishedYes

Fingerprint

Linguistics
Semantics
Experiments

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Electrical and Electronic Engineering
  • Artificial Intelligence

Cite this

Sentiment assessment of text by analyzing linguistic features and contextual valence assignment. / Shaikh, Mostafa Al Masum; Prendinger, Helmut; Ishizuka, Mitsuru.

In: Applied Artificial Intelligence, Vol. 22, No. 6, 07.2008, p. 558-601.

Research output: Contribution to journalArticle

Shaikh, Mostafa Al Masum ; Prendinger, Helmut ; Ishizuka, Mitsuru. / Sentiment assessment of text by analyzing linguistic features and contextual valence assignment. In: Applied Artificial Intelligence. 2008 ; Vol. 22, No. 6. pp. 558-601.
@article{7449ed2ebb1e4474ae65635b1a4bc432,
title = "Sentiment assessment of text by analyzing linguistic features and contextual valence assignment",
abstract = "Text is not only an important medium to describe facts and events, but also to effectively communicate information about the writer's positive or negative sentiment underlying an opinion, or to express an affective or emotional state, such as happiness, fearfulness, surpriseness, and so on. We consider sentiment assessment and emotion sensing from text as two different problems, whereby sentiment assessment is the task that we want to solve first. Thus, this article presents an approach to sentiment assessment, i.e., the recognition of negative or positive valence of a sentence. For the purpose of sentiment recognition from text, we perform semantic dependency analysis on the semantic verb frames of each sentence, and then apply a set of rules to each dependency relation to calculate the contextual valence of the whole sentence. By employing a domain-independent, rule-based approach our system is able to automatically identify sentence-level sentiment. A linguistic tool called {"}SenseNet{"} has been developed to recognize sentiments in text, and to visualize the detected sentiments. We conducted several experiments with a variety of datasets containing data from different domains. The obtained results indicate significant performance gains over existing state-of-the-art approaches.",
author = "Shaikh, {Mostafa Al Masum} and Helmut Prendinger and Mitsuru Ishizuka",
year = "2008",
month = "7",
doi = "10.1080/08839510802226801",
language = "English",
volume = "22",
pages = "558--601",
journal = "Applied Artificial Intelligence",
issn = "0883-9514",
publisher = "Taylor and Francis Ltd.",
number = "6",

}

TY - JOUR

T1 - Sentiment assessment of text by analyzing linguistic features and contextual valence assignment

AU - Shaikh, Mostafa Al Masum

AU - Prendinger, Helmut

AU - Ishizuka, Mitsuru

PY - 2008/7

Y1 - 2008/7

N2 - Text is not only an important medium to describe facts and events, but also to effectively communicate information about the writer's positive or negative sentiment underlying an opinion, or to express an affective or emotional state, such as happiness, fearfulness, surpriseness, and so on. We consider sentiment assessment and emotion sensing from text as two different problems, whereby sentiment assessment is the task that we want to solve first. Thus, this article presents an approach to sentiment assessment, i.e., the recognition of negative or positive valence of a sentence. For the purpose of sentiment recognition from text, we perform semantic dependency analysis on the semantic verb frames of each sentence, and then apply a set of rules to each dependency relation to calculate the contextual valence of the whole sentence. By employing a domain-independent, rule-based approach our system is able to automatically identify sentence-level sentiment. A linguistic tool called "SenseNet" has been developed to recognize sentiments in text, and to visualize the detected sentiments. We conducted several experiments with a variety of datasets containing data from different domains. The obtained results indicate significant performance gains over existing state-of-the-art approaches.

AB - Text is not only an important medium to describe facts and events, but also to effectively communicate information about the writer's positive or negative sentiment underlying an opinion, or to express an affective or emotional state, such as happiness, fearfulness, surpriseness, and so on. We consider sentiment assessment and emotion sensing from text as two different problems, whereby sentiment assessment is the task that we want to solve first. Thus, this article presents an approach to sentiment assessment, i.e., the recognition of negative or positive valence of a sentence. For the purpose of sentiment recognition from text, we perform semantic dependency analysis on the semantic verb frames of each sentence, and then apply a set of rules to each dependency relation to calculate the contextual valence of the whole sentence. By employing a domain-independent, rule-based approach our system is able to automatically identify sentence-level sentiment. A linguistic tool called "SenseNet" has been developed to recognize sentiments in text, and to visualize the detected sentiments. We conducted several experiments with a variety of datasets containing data from different domains. The obtained results indicate significant performance gains over existing state-of-the-art approaches.

UR - http://www.scopus.com/inward/record.url?scp=48849091785&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=48849091785&partnerID=8YFLogxK

U2 - 10.1080/08839510802226801

DO - 10.1080/08839510802226801

M3 - Article

AN - SCOPUS:48849091785

VL - 22

SP - 558

EP - 601

JO - Applied Artificial Intelligence

JF - Applied Artificial Intelligence

SN - 0883-9514

IS - 6

ER -