Language-independent sentiment analysis using subjectivity and positional information

Veselin Raychev, Preslav Nakov

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

13 Citations (Scopus)

Abstract

We describe a novel language-independent approach to the task of determining the polarity, positive or negative, of the author's opinion on a specific topic in natural language text. In particular, weights are assigned to attributes, individual words or word bi-grams, based on their position and on their likelihood of being subjective. The subjectivity of each attribute is estimated in a two-step process, where first the probability of being subjective is calculated for each sentence containing the attribute, and then these probabilities are used to alter the attribute's weights for polarity classification. The evaluation results on a standard dataset of movie reviews shows 89.85% classification accuracy, which rivals the best previously published results for this dataset for systems that use no additional linguistic information nor external resources.

Original languageEnglish
Title of host publicationInternational Conference Recent Advances in Natural Language Processing, RANLP
Pages360-364
Number of pages5
Publication statusPublished - 2009
Externally publishedYes
EventInternational Conference on Recent Advances in Natural Language Processing, RANLP-2009 - Borovets, Bulgaria
Duration: 14 Sep 200916 Sep 2009

Other

OtherInternational Conference on Recent Advances in Natural Language Processing, RANLP-2009
CountryBulgaria
CityBorovets
Period14/9/0916/9/09

Fingerprint

Linguistics

Keywords

  • Polarity classification
  • Sentiment analysis
  • Subjectivity identification
  • Text categorization

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Science Applications
  • Software
  • Electrical and Electronic Engineering

Cite this

Raychev, V., & Nakov, P. (2009). Language-independent sentiment analysis using subjectivity and positional information. In International Conference Recent Advances in Natural Language Processing, RANLP (pp. 360-364)

Language-independent sentiment analysis using subjectivity and positional information. / Raychev, Veselin; Nakov, Preslav.

International Conference Recent Advances in Natural Language Processing, RANLP. 2009. p. 360-364.

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

Raychev, V & Nakov, P 2009, Language-independent sentiment analysis using subjectivity and positional information. in International Conference Recent Advances in Natural Language Processing, RANLP. pp. 360-364, International Conference on Recent Advances in Natural Language Processing, RANLP-2009, Borovets, Bulgaria, 14/9/09.
Raychev V, Nakov P. Language-independent sentiment analysis using subjectivity and positional information. In International Conference Recent Advances in Natural Language Processing, RANLP. 2009. p. 360-364
Raychev, Veselin ; Nakov, Preslav. / Language-independent sentiment analysis using subjectivity and positional information. International Conference Recent Advances in Natural Language Processing, RANLP. 2009. pp. 360-364
@inproceedings{bd49a515c8db47278bb3626c9314f9f8,
title = "Language-independent sentiment analysis using subjectivity and positional information",
abstract = "We describe a novel language-independent approach to the task of determining the polarity, positive or negative, of the author's opinion on a specific topic in natural language text. In particular, weights are assigned to attributes, individual words or word bi-grams, based on their position and on their likelihood of being subjective. The subjectivity of each attribute is estimated in a two-step process, where first the probability of being subjective is calculated for each sentence containing the attribute, and then these probabilities are used to alter the attribute's weights for polarity classification. The evaluation results on a standard dataset of movie reviews shows 89.85{\%} classification accuracy, which rivals the best previously published results for this dataset for systems that use no additional linguistic information nor external resources.",
keywords = "Polarity classification, Sentiment analysis, Subjectivity identification, Text categorization",
author = "Veselin Raychev and Preslav Nakov",
year = "2009",
language = "English",
pages = "360--364",
booktitle = "International Conference Recent Advances in Natural Language Processing, RANLP",

}

TY - GEN

T1 - Language-independent sentiment analysis using subjectivity and positional information

AU - Raychev, Veselin

AU - Nakov, Preslav

PY - 2009

Y1 - 2009

N2 - We describe a novel language-independent approach to the task of determining the polarity, positive or negative, of the author's opinion on a specific topic in natural language text. In particular, weights are assigned to attributes, individual words or word bi-grams, based on their position and on their likelihood of being subjective. The subjectivity of each attribute is estimated in a two-step process, where first the probability of being subjective is calculated for each sentence containing the attribute, and then these probabilities are used to alter the attribute's weights for polarity classification. The evaluation results on a standard dataset of movie reviews shows 89.85% classification accuracy, which rivals the best previously published results for this dataset for systems that use no additional linguistic information nor external resources.

AB - We describe a novel language-independent approach to the task of determining the polarity, positive or negative, of the author's opinion on a specific topic in natural language text. In particular, weights are assigned to attributes, individual words or word bi-grams, based on their position and on their likelihood of being subjective. The subjectivity of each attribute is estimated in a two-step process, where first the probability of being subjective is calculated for each sentence containing the attribute, and then these probabilities are used to alter the attribute's weights for polarity classification. The evaluation results on a standard dataset of movie reviews shows 89.85% classification accuracy, which rivals the best previously published results for this dataset for systems that use no additional linguistic information nor external resources.

KW - Polarity classification

KW - Sentiment analysis

KW - Subjectivity identification

KW - Text categorization

UR - http://www.scopus.com/inward/record.url?scp=79955619875&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79955619875&partnerID=8YFLogxK

M3 - Conference contribution

SP - 360

EP - 364

BT - International Conference Recent Advances in Natural Language Processing, RANLP

ER -