Home > Research > Publications & Outputs > Detection of stance and sentiment modifiers in ...

Electronic data

  • stancemodifiers_review_update (1)

    Rights statement: The final publication is available at Springer via http://dx.doi.org/10.1007/978-3-319-66429-3_29

    Accepted author manuscript, 302 KB, PDF document

Links

Text available via DOI:

View graph of relations

Detection of stance and sentiment modifiers in political blogs

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSNConference contribution/Paperpeer-review

Published

Standard

Detection of stance and sentiment modifiers in political blogs. / Skeppstedt, Maria; Simaki, Vasiliki; Paradis, Carita et al.
SPECOM 2017: Speech and Computer. ed. / A. Karpov; R. Potapova; I. Mporas. Cham: Springer, 2017. p. 302-311 (Lecture Notes in Computer Science; Vol. 10458).

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSNConference contribution/Paperpeer-review

Harvard

Skeppstedt, M, Simaki, V, Paradis, C & Kerren, A 2017, Detection of stance and sentiment modifiers in political blogs. in A Karpov, R Potapova & I Mporas (eds), SPECOM 2017: Speech and Computer. Lecture Notes in Computer Science, vol. 10458, Springer, Cham, pp. 302-311. https://doi.org/10.1007/978-3-319-66429-3_29

APA

Skeppstedt, M., Simaki, V., Paradis, C., & Kerren, A. (2017). Detection of stance and sentiment modifiers in political blogs. In A. Karpov, R. Potapova, & I. Mporas (Eds.), SPECOM 2017: Speech and Computer (pp. 302-311). (Lecture Notes in Computer Science; Vol. 10458). Springer. https://doi.org/10.1007/978-3-319-66429-3_29

Vancouver

Skeppstedt M, Simaki V, Paradis C, Kerren A. Detection of stance and sentiment modifiers in political blogs. In Karpov A, Potapova R, Mporas I, editors, SPECOM 2017: Speech and Computer. Cham: Springer. 2017. p. 302-311. (Lecture Notes in Computer Science). Epub 2017 Aug 13. doi: 10.1007/978-3-319-66429-3_29

Author

Skeppstedt, Maria ; Simaki, Vasiliki ; Paradis, Carita et al. / Detection of stance and sentiment modifiers in political blogs. SPECOM 2017: Speech and Computer. editor / A. Karpov ; R. Potapova ; I. Mporas. Cham : Springer, 2017. pp. 302-311 (Lecture Notes in Computer Science).

Bibtex

@inproceedings{226a2276378a4578a98860d23ad0ca8f,
title = "Detection of stance and sentiment modifiers in political blogs",
abstract = "The automatic detection of seven types of modifiers was studied: Certainty, Uncertainty, Hypotheticality, Prediction, Recommendation, Concession/Contrast and Source. A classifier aimed at detecting local cue words that signal the categories was the most successful method for five of the categories. For Prediction and Hypotheticality, however, better results were obtained with a classifier trained on tokens and bigrams present in the entire sentence. Unsupervised cluster features were shown useful for the categories Source and Uncertainty, when a subset of the training data available was used. However, when all of the 2,095 sentences that had been actively selected and manually annotated were used as training data, the cluster features had a very limited effect. Some of the classification errors made by the models would be possible to avoid by extending the training data set, while other features and feature representations, as well as the incorporation of pragmatic knowledge, would be required for other error types.",
keywords = "Stance modifiers, Sentiment modifiers , Active learning , Unsupervised features , Sesource-aware natural language processing",
author = "Maria Skeppstedt and Vasiliki Simaki and Carita Paradis and Andreas Kerren",
note = "The final publication is available at Springer via http://dx.doi.org/10.1007/978-3-319-66429-3_29",
year = "2017",
doi = "10.1007/978-3-319-66429-3_29",
language = "English",
isbn = "9783319665286",
series = "Lecture Notes in Computer Science",
publisher = "Springer",
pages = "302--311",
editor = "A. Karpov and R. Potapova and I. Mporas",
booktitle = "SPECOM 2017",

}

RIS

TY - GEN

T1 - Detection of stance and sentiment modifiers in political blogs

AU - Skeppstedt, Maria

AU - Simaki, Vasiliki

AU - Paradis, Carita

AU - Kerren, Andreas

N1 - The final publication is available at Springer via http://dx.doi.org/10.1007/978-3-319-66429-3_29

PY - 2017

Y1 - 2017

N2 - The automatic detection of seven types of modifiers was studied: Certainty, Uncertainty, Hypotheticality, Prediction, Recommendation, Concession/Contrast and Source. A classifier aimed at detecting local cue words that signal the categories was the most successful method for five of the categories. For Prediction and Hypotheticality, however, better results were obtained with a classifier trained on tokens and bigrams present in the entire sentence. Unsupervised cluster features were shown useful for the categories Source and Uncertainty, when a subset of the training data available was used. However, when all of the 2,095 sentences that had been actively selected and manually annotated were used as training data, the cluster features had a very limited effect. Some of the classification errors made by the models would be possible to avoid by extending the training data set, while other features and feature representations, as well as the incorporation of pragmatic knowledge, would be required for other error types.

AB - The automatic detection of seven types of modifiers was studied: Certainty, Uncertainty, Hypotheticality, Prediction, Recommendation, Concession/Contrast and Source. A classifier aimed at detecting local cue words that signal the categories was the most successful method for five of the categories. For Prediction and Hypotheticality, however, better results were obtained with a classifier trained on tokens and bigrams present in the entire sentence. Unsupervised cluster features were shown useful for the categories Source and Uncertainty, when a subset of the training data available was used. However, when all of the 2,095 sentences that had been actively selected and manually annotated were used as training data, the cluster features had a very limited effect. Some of the classification errors made by the models would be possible to avoid by extending the training data set, while other features and feature representations, as well as the incorporation of pragmatic knowledge, would be required for other error types.

KW - Stance modifiers

KW - Sentiment modifiers

KW - Active learning

KW - Unsupervised features

KW - Sesource-aware natural language processing

U2 - 10.1007/978-3-319-66429-3_29

DO - 10.1007/978-3-319-66429-3_29

M3 - Conference contribution/Paper

SN - 9783319665286

T3 - Lecture Notes in Computer Science

SP - 302

EP - 311

BT - SPECOM 2017

A2 - Karpov, A.

A2 - Potapova, R.

A2 - Mporas, I.

PB - Springer

CY - Cham

ER -