Abstract

A story is defined as actors taking actions that culminate in resolutions. In this paper, we extract subject - verb - object relationships from paragraphs and generalize them into semantic conceptual representations. Overlapping generalized concepts and relationships correspond to archetypes/targets and actions that characterize story forms. We present an analytic framework which implements co-clustering based on generalized conceptual relationships to automatically detect such story forms. Co-clustering can help in identifying similarities that exist in low-dimensional sub-spaces of sparse data such as textual paragraphs. Through co-clustering, we detect not only the clusters themselves but also their characteristic features which can be useful in describing and summarizing their contents. We perform co-clustering of stories using two different types of features: standard unigrams/bigrams and generalized concepts. We show that the residual error of factorization with concept-based features is significantly lower than the error with standard keyword-based features. Qualitative evaluations also suggest that concept-based features yield more coherent, distinctive and interesting story forms compared to those produced by using standard keyword-based features.

Original languageEnglish (US)
Title of host publicationProceedings - 2016 IEEE International Conferences on Big Data and Cloud Computing, BDCloud 2016, Social Computing and Networking, SocialCom 2016 and Sustainable Computing and Communications, SustainCom 2016
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages258-265
Number of pages8
ISBN (Electronic)9781509039364
DOIs
StatePublished - Oct 26 2016
Event6th IEEE International Conference on Big Data and Cloud Computing, BDCloud 2016, 9th IEEE International Conference on Social Computing and Networking, SocialCom 2016 and 2016 IEEE International Conference on Sustainable Computing and Communications, SustainCom 2016 - Atlanta, United States
Duration: Oct 8 2016Oct 10 2016

Other

Other6th IEEE International Conference on Big Data and Cloud Computing, BDCloud 2016, 9th IEEE International Conference on Social Computing and Networking, SocialCom 2016 and 2016 IEEE International Conference on Sustainable Computing and Communications, SustainCom 2016
CountryUnited States
CityAtlanta
Period10/8/1610/10/16

Fingerprint

Factorization
Semantics
semantics
Clustering
evaluation
Key words
Archetypes
Overlapping
Evaluation

Keywords

  • Co-clustering
  • Narrative analysis
  • Non-negative matrix factorization
  • Story forms

ASJC Scopus subject areas

  • Information Systems and Management
  • Computer Networks and Communications
  • Information Systems
  • Sociology and Political Science
  • Communication

Cite this

Alzahrani, S., Ceran, B., Alashri, S., Ruston, S. W., Corman, S., & Davulcu, H. (2016). Story forms detection in text through concept-based co-clustering. In Proceedings - 2016 IEEE International Conferences on Big Data and Cloud Computing, BDCloud 2016, Social Computing and Networking, SocialCom 2016 and Sustainable Computing and Communications, SustainCom 2016 (pp. 258-265). [7723702] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/BDCloud-SocialCom-SustainCom.2016.48

Story forms detection in text through concept-based co-clustering. / Alzahrani, Sultan; Ceran, Betul; Alashri, Saud; Ruston, Scott W.; Corman, Steven; Davulcu, Hasan.

Proceedings - 2016 IEEE International Conferences on Big Data and Cloud Computing, BDCloud 2016, Social Computing and Networking, SocialCom 2016 and Sustainable Computing and Communications, SustainCom 2016. Institute of Electrical and Electronics Engineers Inc., 2016. p. 258-265 7723702.

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

Alzahrani, S, Ceran, B, Alashri, S, Ruston, SW, Corman, S & Davulcu, H 2016, Story forms detection in text through concept-based co-clustering. in Proceedings - 2016 IEEE International Conferences on Big Data and Cloud Computing, BDCloud 2016, Social Computing and Networking, SocialCom 2016 and Sustainable Computing and Communications, SustainCom 2016., 7723702, Institute of Electrical and Electronics Engineers Inc., pp. 258-265, 6th IEEE International Conference on Big Data and Cloud Computing, BDCloud 2016, 9th IEEE International Conference on Social Computing and Networking, SocialCom 2016 and 2016 IEEE International Conference on Sustainable Computing and Communications, SustainCom 2016, Atlanta, United States, 10/8/16. https://doi.org/10.1109/BDCloud-SocialCom-SustainCom.2016.48
Alzahrani S, Ceran B, Alashri S, Ruston SW, Corman S, Davulcu H. Story forms detection in text through concept-based co-clustering. In Proceedings - 2016 IEEE International Conferences on Big Data and Cloud Computing, BDCloud 2016, Social Computing and Networking, SocialCom 2016 and Sustainable Computing and Communications, SustainCom 2016. Institute of Electrical and Electronics Engineers Inc. 2016. p. 258-265. 7723702 https://doi.org/10.1109/BDCloud-SocialCom-SustainCom.2016.48
Alzahrani, Sultan ; Ceran, Betul ; Alashri, Saud ; Ruston, Scott W. ; Corman, Steven ; Davulcu, Hasan. / Story forms detection in text through concept-based co-clustering. Proceedings - 2016 IEEE International Conferences on Big Data and Cloud Computing, BDCloud 2016, Social Computing and Networking, SocialCom 2016 and Sustainable Computing and Communications, SustainCom 2016. Institute of Electrical and Electronics Engineers Inc., 2016. pp. 258-265
@inproceedings{450d8d5e22634aa290c152ef3eab9043,
title = "Story forms detection in text through concept-based co-clustering",
abstract = "A story is defined as actors taking actions that culminate in resolutions. In this paper, we extract subject - verb - object relationships from paragraphs and generalize them into semantic conceptual representations. Overlapping generalized concepts and relationships correspond to archetypes/targets and actions that characterize story forms. We present an analytic framework which implements co-clustering based on generalized conceptual relationships to automatically detect such story forms. Co-clustering can help in identifying similarities that exist in low-dimensional sub-spaces of sparse data such as textual paragraphs. Through co-clustering, we detect not only the clusters themselves but also their characteristic features which can be useful in describing and summarizing their contents. We perform co-clustering of stories using two different types of features: standard unigrams/bigrams and generalized concepts. We show that the residual error of factorization with concept-based features is significantly lower than the error with standard keyword-based features. Qualitative evaluations also suggest that concept-based features yield more coherent, distinctive and interesting story forms compared to those produced by using standard keyword-based features.",
keywords = "Co-clustering, Narrative analysis, Non-negative matrix factorization, Story forms",
author = "Sultan Alzahrani and Betul Ceran and Saud Alashri and Ruston, {Scott W.} and Steven Corman and Hasan Davulcu",
year = "2016",
month = "10",
day = "26",
doi = "10.1109/BDCloud-SocialCom-SustainCom.2016.48",
language = "English (US)",
pages = "258--265",
booktitle = "Proceedings - 2016 IEEE International Conferences on Big Data and Cloud Computing, BDCloud 2016, Social Computing and Networking, SocialCom 2016 and Sustainable Computing and Communications, SustainCom 2016",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
address = "United States",

}

TY - GEN

T1 - Story forms detection in text through concept-based co-clustering

AU - Alzahrani, Sultan

AU - Ceran, Betul

AU - Alashri, Saud

AU - Ruston, Scott W.

AU - Corman, Steven

AU - Davulcu, Hasan

PY - 2016/10/26

Y1 - 2016/10/26

N2 - A story is defined as actors taking actions that culminate in resolutions. In this paper, we extract subject - verb - object relationships from paragraphs and generalize them into semantic conceptual representations. Overlapping generalized concepts and relationships correspond to archetypes/targets and actions that characterize story forms. We present an analytic framework which implements co-clustering based on generalized conceptual relationships to automatically detect such story forms. Co-clustering can help in identifying similarities that exist in low-dimensional sub-spaces of sparse data such as textual paragraphs. Through co-clustering, we detect not only the clusters themselves but also their characteristic features which can be useful in describing and summarizing their contents. We perform co-clustering of stories using two different types of features: standard unigrams/bigrams and generalized concepts. We show that the residual error of factorization with concept-based features is significantly lower than the error with standard keyword-based features. Qualitative evaluations also suggest that concept-based features yield more coherent, distinctive and interesting story forms compared to those produced by using standard keyword-based features.

AB - A story is defined as actors taking actions that culminate in resolutions. In this paper, we extract subject - verb - object relationships from paragraphs and generalize them into semantic conceptual representations. Overlapping generalized concepts and relationships correspond to archetypes/targets and actions that characterize story forms. We present an analytic framework which implements co-clustering based on generalized conceptual relationships to automatically detect such story forms. Co-clustering can help in identifying similarities that exist in low-dimensional sub-spaces of sparse data such as textual paragraphs. Through co-clustering, we detect not only the clusters themselves but also their characteristic features which can be useful in describing and summarizing their contents. We perform co-clustering of stories using two different types of features: standard unigrams/bigrams and generalized concepts. We show that the residual error of factorization with concept-based features is significantly lower than the error with standard keyword-based features. Qualitative evaluations also suggest that concept-based features yield more coherent, distinctive and interesting story forms compared to those produced by using standard keyword-based features.

KW - Co-clustering

KW - Narrative analysis

KW - Non-negative matrix factorization

KW - Story forms

UR - http://www.scopus.com/inward/record.url?scp=85000879003&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85000879003&partnerID=8YFLogxK

U2 - 10.1109/BDCloud-SocialCom-SustainCom.2016.48

DO - 10.1109/BDCloud-SocialCom-SustainCom.2016.48

M3 - Conference contribution

SP - 258

EP - 265

BT - Proceedings - 2016 IEEE International Conferences on Big Data and Cloud Computing, BDCloud 2016, Social Computing and Networking, SocialCom 2016 and Sustainable Computing and Communications, SustainCom 2016

PB - Institute of Electrical and Electronics Engineers Inc.

ER -