Abstract

The subliminal impact of framing of social, political and environmental issues such as climate change has been studied for long time in political science and communications research. Media framing offers interpretative package for average citizens on how to make sense of climate change and its consequences to their livelihoods, how to deal with its negative impacts, and which mitigation or adaptation policies to support. A line of related work has used bag of words and word-level features to detect frames automatically in text. Such works face limitations since standard keyword based features may not generalize well to accommodate surface variations in text when different keywords are used for similar concepts. In this paper, we develop a new type of textual features that generalize (subject, verb, object) triplets extracted from text, by clustering them into high-level concepts. We utilize these concepts as features to detect frames in text. Our corpus comprises more than 45,000 climate change related sentences. Expert coders annotated those sentences as frame/non-frame and framed sentences were mapped into one of four general frame categories: solution, problem threat, cause, and motivation. Compared to unigram and bigram based models, classification using our generalized concepts yielded better discriminating features and a higher accuracy classifier with a 12% boost (i.e. from 74% to 83% in f-measure) for frame/no frame detection.

Original languageEnglish (US)
Title of host publicationProceedings - 2016 IEEE 10th International Conference on Semantic Computing, ICSC 2016
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages277-284
Number of pages8
ISBN (Print)9781509006618
DOIs
StatePublished - Mar 22 2016
Event10th IEEE International Conference on Semantic Computing, ICSC 2016 - Laguna Hills, United States
Duration: Feb 3 2016Feb 5 2016

Other

Other10th IEEE International Conference on Semantic Computing, ICSC 2016
CountryUnited States
CityLaguna Hills
Period2/3/162/5/16

Fingerprint

Climate change
Classifiers
Communication

Keywords

  • Big Data
  • Climate Change
  • Concepts
  • Frames Detection
  • Natural Language Processing
  • Text mining

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Networks and Communications
  • Information Systems

Cite this

Alashri, S., Tsai, J. Y., Alzahrani, S., Corman, S., & Davulcu, H. (2016). Climate Change Frames Detection and Categorization Based on Generalized Concepts. In Proceedings - 2016 IEEE 10th International Conference on Semantic Computing, ICSC 2016 (pp. 277-284). [7439349] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICSC.2016.14

Climate Change Frames Detection and Categorization Based on Generalized Concepts. / Alashri, Saud; Tsai, Jiun Yi; Alzahrani, Sultan; Corman, Steven; Davulcu, Hasan.

Proceedings - 2016 IEEE 10th International Conference on Semantic Computing, ICSC 2016. Institute of Electrical and Electronics Engineers Inc., 2016. p. 277-284 7439349.

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

Alashri, S, Tsai, JY, Alzahrani, S, Corman, S & Davulcu, H 2016, Climate Change Frames Detection and Categorization Based on Generalized Concepts. in Proceedings - 2016 IEEE 10th International Conference on Semantic Computing, ICSC 2016., 7439349, Institute of Electrical and Electronics Engineers Inc., pp. 277-284, 10th IEEE International Conference on Semantic Computing, ICSC 2016, Laguna Hills, United States, 2/3/16. https://doi.org/10.1109/ICSC.2016.14
Alashri S, Tsai JY, Alzahrani S, Corman S, Davulcu H. Climate Change Frames Detection and Categorization Based on Generalized Concepts. In Proceedings - 2016 IEEE 10th International Conference on Semantic Computing, ICSC 2016. Institute of Electrical and Electronics Engineers Inc. 2016. p. 277-284. 7439349 https://doi.org/10.1109/ICSC.2016.14
Alashri, Saud ; Tsai, Jiun Yi ; Alzahrani, Sultan ; Corman, Steven ; Davulcu, Hasan. / Climate Change Frames Detection and Categorization Based on Generalized Concepts. Proceedings - 2016 IEEE 10th International Conference on Semantic Computing, ICSC 2016. Institute of Electrical and Electronics Engineers Inc., 2016. pp. 277-284
@inproceedings{dc6341d7bb7d4854ab09fa23c009a115,
title = "Climate Change Frames Detection and Categorization Based on Generalized Concepts",
abstract = "The subliminal impact of framing of social, political and environmental issues such as climate change has been studied for long time in political science and communications research. Media framing offers interpretative package for average citizens on how to make sense of climate change and its consequences to their livelihoods, how to deal with its negative impacts, and which mitigation or adaptation policies to support. A line of related work has used bag of words and word-level features to detect frames automatically in text. Such works face limitations since standard keyword based features may not generalize well to accommodate surface variations in text when different keywords are used for similar concepts. In this paper, we develop a new type of textual features that generalize (subject, verb, object) triplets extracted from text, by clustering them into high-level concepts. We utilize these concepts as features to detect frames in text. Our corpus comprises more than 45,000 climate change related sentences. Expert coders annotated those sentences as frame/non-frame and framed sentences were mapped into one of four general frame categories: solution, problem threat, cause, and motivation. Compared to unigram and bigram based models, classification using our generalized concepts yielded better discriminating features and a higher accuracy classifier with a 12{\%} boost (i.e. from 74{\%} to 83{\%} in f-measure) for frame/no frame detection.",
keywords = "Big Data, Climate Change, Concepts, Frames Detection, Natural Language Processing, Text mining",
author = "Saud Alashri and Tsai, {Jiun Yi} and Sultan Alzahrani and Steven Corman and Hasan Davulcu",
year = "2016",
month = "3",
day = "22",
doi = "10.1109/ICSC.2016.14",
language = "English (US)",
isbn = "9781509006618",
pages = "277--284",
booktitle = "Proceedings - 2016 IEEE 10th International Conference on Semantic Computing, ICSC 2016",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Climate Change Frames Detection and Categorization Based on Generalized Concepts

AU - Alashri, Saud

AU - Tsai, Jiun Yi

AU - Alzahrani, Sultan

AU - Corman, Steven

AU - Davulcu, Hasan

PY - 2016/3/22

Y1 - 2016/3/22

N2 - The subliminal impact of framing of social, political and environmental issues such as climate change has been studied for long time in political science and communications research. Media framing offers interpretative package for average citizens on how to make sense of climate change and its consequences to their livelihoods, how to deal with its negative impacts, and which mitigation or adaptation policies to support. A line of related work has used bag of words and word-level features to detect frames automatically in text. Such works face limitations since standard keyword based features may not generalize well to accommodate surface variations in text when different keywords are used for similar concepts. In this paper, we develop a new type of textual features that generalize (subject, verb, object) triplets extracted from text, by clustering them into high-level concepts. We utilize these concepts as features to detect frames in text. Our corpus comprises more than 45,000 climate change related sentences. Expert coders annotated those sentences as frame/non-frame and framed sentences were mapped into one of four general frame categories: solution, problem threat, cause, and motivation. Compared to unigram and bigram based models, classification using our generalized concepts yielded better discriminating features and a higher accuracy classifier with a 12% boost (i.e. from 74% to 83% in f-measure) for frame/no frame detection.

AB - The subliminal impact of framing of social, political and environmental issues such as climate change has been studied for long time in political science and communications research. Media framing offers interpretative package for average citizens on how to make sense of climate change and its consequences to their livelihoods, how to deal with its negative impacts, and which mitigation or adaptation policies to support. A line of related work has used bag of words and word-level features to detect frames automatically in text. Such works face limitations since standard keyword based features may not generalize well to accommodate surface variations in text when different keywords are used for similar concepts. In this paper, we develop a new type of textual features that generalize (subject, verb, object) triplets extracted from text, by clustering them into high-level concepts. We utilize these concepts as features to detect frames in text. Our corpus comprises more than 45,000 climate change related sentences. Expert coders annotated those sentences as frame/non-frame and framed sentences were mapped into one of four general frame categories: solution, problem threat, cause, and motivation. Compared to unigram and bigram based models, classification using our generalized concepts yielded better discriminating features and a higher accuracy classifier with a 12% boost (i.e. from 74% to 83% in f-measure) for frame/no frame detection.

KW - Big Data

KW - Climate Change

KW - Concepts

KW - Frames Detection

KW - Natural Language Processing

KW - Text mining

UR - http://www.scopus.com/inward/record.url?scp=84968735319&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84968735319&partnerID=8YFLogxK

U2 - 10.1109/ICSC.2016.14

DO - 10.1109/ICSC.2016.14

M3 - Conference contribution

SN - 9781509006618

SP - 277

EP - 284

BT - Proceedings - 2016 IEEE 10th International Conference on Semantic Computing, ICSC 2016

PB - Institute of Electrical and Electronics Engineers Inc.

ER -