Rethinking Summarization and Storytelling for Modern Social Multimedia

Stevan Rudinac, Tat-Seng Chua, Nicolas Diaz-Ferreyra, Gerald Friedland, Tatjana Gornostaja, Benoit Huet, Rianne Kaptein, Krister Linden, Marie-Francine Moens, Jaakko Peltonen, Miriam Redi, Markus Schedl, David A. Shamma, Alan Smeaton, Lexing Xie

Research output: Conference materialsOther conference materialResearch

Abstract

This report documents the program and the outcomes of Dagstuhl Seminar 17301 "User-Generated Content in Social Media". Social media have a profound impact on individuals, businesses, and society. As users post vast amounts of text and multimedia content every minute, the analysis of this user generated content (UGC) can offer insights to individual and societal concerns and could be beneficial to a wide range of applications. In this seminar, we brought together researchers from different subfields of computer science, such as information retrieval, multimedia, natural language processing, machine learning and social media analytics. We discussed the specific properties of UGC, the general research tasks currently operating on this type of content, identifying their limitations, and imagining new types of applications. We formed two working groups, WG1 "Fake News and Credibility", WG2 "Summarizing and Story Telling from UGC". WG1 invented an "Information Nutrition Label" that characterizes a document by different features such as e.g. emotion, opinion, controversy, and topicality; For computing these feature values, available methods and open research issues were identified. WG2 developed a framework for summarizing heterogeneous, multilingual and multimodal data, discussed key challenges and applications of this framework.
Original languageEnglish
Pages141-153
Number of pages13
DOIs
Publication statusPublished - 2018
EventDagstuhl Seminar 17301: July 23 – 28, 2017 - Schloss Dagstuhl, Daghstuhl, Germany
Duration: 23 Jul 201728 Jul 2017
https://www.dagstuhl.de/en/program/calendar/semhp/?semnr=17301

Conference

ConferenceDagstuhl Seminar 17301
CountryGermany
CityDaghstuhl
Period23/07/201728/07/2017
Internet address

Fields of Science

  • 6121 Languages
  • 213 Electronic, automation and communications engineering, electronics
  • social media
  • user-generated content
  • social multimedia
  • summarisation
  • fake-news
  • AI
  • credibility
  • storytelling

Cite this

Rudinac, S., Chua, T-S., Diaz-Ferreyra, N., Friedland, G., Gornostaja, T., Huet, B., ... Xie, L. (2018). Rethinking Summarization and Storytelling for Modern Social Multimedia. 141-153. Dagstuhl Seminar 17301, Daghstuhl, Germany. https://doi.org/10.4230/DagRep.7.7.110
Rudinac, Stevan ; Chua, Tat-Seng ; Diaz-Ferreyra, Nicolas ; Friedland, Gerald ; Gornostaja, Tatjana ; Huet, Benoit ; Kaptein, Rianne ; Linden, Krister ; Moens, Marie-Francine ; Peltonen, Jaakko ; Redi, Miriam ; Schedl, Markus ; Shamma, David A. ; Smeaton, Alan ; Xie, Lexing. / Rethinking Summarization and Storytelling for Modern Social Multimedia. Dagstuhl Seminar 17301, Daghstuhl, Germany.13 p.
@conference{3658782faaf046c681ceb90ce0f31115,
title = "Rethinking Summarization and Storytelling for Modern Social Multimedia",
abstract = "This report documents the program and the outcomes of Dagstuhl Seminar 17301 {"}User-Generated Content in Social Media{"}. Social media have a profound impact on individuals, businesses, and society. As users post vast amounts of text and multimedia content every minute, the analysis of this user generated content (UGC) can offer insights to individual and societal concerns and could be beneficial to a wide range of applications. In this seminar, we brought together researchers from different subfields of computer science, such as information retrieval, multimedia, natural language processing, machine learning and social media analytics. We discussed the specific properties of UGC, the general research tasks currently operating on this type of content, identifying their limitations, and imagining new types of applications. We formed two working groups, WG1 {"}Fake News and Credibility{"}, WG2 {"}Summarizing and Story Telling from UGC{"}. WG1 invented an {"}Information Nutrition Label{"} that characterizes a document by different features such as e.g. emotion, opinion, controversy, and topicality; For computing these feature values, available methods and open research issues were identified. WG2 developed a framework for summarizing heterogeneous, multilingual and multimodal data, discussed key challenges and applications of this framework.",
keywords = "6121 Languages, 213 Electronic, automation and communications engineering, electronics, social media, user-generated content, social multimedia, summarisation, fake-news, AI, credibility, storytelling",
author = "Stevan Rudinac and Tat-Seng Chua and Nicolas Diaz-Ferreyra and Gerald Friedland and Tatjana Gornostaja and Benoit Huet and Rianne Kaptein and Krister Linden and Marie-Francine Moens and Jaakko Peltonen and Miriam Redi and Markus Schedl and Shamma, {David A.} and Alan Smeaton and Lexing Xie",
note = "Working group discussion at the Schloss Dagstuhl seminar ; Dagstuhl Seminar 17301 : July 23 – 28, 2017 ; Conference date: 23-07-2017 Through 28-07-2017",
year = "2018",
doi = "10.4230/DagRep.7.7.110",
language = "English",
pages = "141--153",
url = "https://www.dagstuhl.de/en/program/calendar/semhp/?semnr=17301",

}

Rudinac, S, Chua, T-S, Diaz-Ferreyra, N, Friedland, G, Gornostaja, T, Huet, B, Kaptein, R, Linden, K, Moens, M-F, Peltonen, J, Redi, M, Schedl, M, Shamma, DA, Smeaton, A & Xie, L 2018, 'Rethinking Summarization and Storytelling for Modern Social Multimedia' Dagstuhl Seminar 17301, Daghstuhl, Germany, 23/07/2017 - 28/07/2017, pp. 141-153. https://doi.org/10.4230/DagRep.7.7.110

Rethinking Summarization and Storytelling for Modern Social Multimedia. / Rudinac, Stevan; Chua, Tat-Seng; Diaz-Ferreyra, Nicolas; Friedland, Gerald; Gornostaja, Tatjana; Huet, Benoit; Kaptein, Rianne; Linden, Krister; Moens, Marie-Francine; Peltonen, Jaakko; Redi, Miriam; Schedl, Markus; Shamma, David A.; Smeaton, Alan; Xie, Lexing.

2018. 141-153 Dagstuhl Seminar 17301, Daghstuhl, Germany.

Research output: Conference materialsOther conference materialResearch

TY - CONF

T1 - Rethinking Summarization and Storytelling for Modern Social Multimedia

AU - Rudinac, Stevan

AU - Chua, Tat-Seng

AU - Diaz-Ferreyra, Nicolas

AU - Friedland, Gerald

AU - Gornostaja, Tatjana

AU - Huet, Benoit

AU - Kaptein, Rianne

AU - Linden, Krister

AU - Moens, Marie-Francine

AU - Peltonen, Jaakko

AU - Redi, Miriam

AU - Schedl, Markus

AU - Shamma, David A.

AU - Smeaton, Alan

AU - Xie, Lexing

N1 - Working group discussion at the Schloss Dagstuhl seminar

PY - 2018

Y1 - 2018

N2 - This report documents the program and the outcomes of Dagstuhl Seminar 17301 "User-Generated Content in Social Media". Social media have a profound impact on individuals, businesses, and society. As users post vast amounts of text and multimedia content every minute, the analysis of this user generated content (UGC) can offer insights to individual and societal concerns and could be beneficial to a wide range of applications. In this seminar, we brought together researchers from different subfields of computer science, such as information retrieval, multimedia, natural language processing, machine learning and social media analytics. We discussed the specific properties of UGC, the general research tasks currently operating on this type of content, identifying their limitations, and imagining new types of applications. We formed two working groups, WG1 "Fake News and Credibility", WG2 "Summarizing and Story Telling from UGC". WG1 invented an "Information Nutrition Label" that characterizes a document by different features such as e.g. emotion, opinion, controversy, and topicality; For computing these feature values, available methods and open research issues were identified. WG2 developed a framework for summarizing heterogeneous, multilingual and multimodal data, discussed key challenges and applications of this framework.

AB - This report documents the program and the outcomes of Dagstuhl Seminar 17301 "User-Generated Content in Social Media". Social media have a profound impact on individuals, businesses, and society. As users post vast amounts of text and multimedia content every minute, the analysis of this user generated content (UGC) can offer insights to individual and societal concerns and could be beneficial to a wide range of applications. In this seminar, we brought together researchers from different subfields of computer science, such as information retrieval, multimedia, natural language processing, machine learning and social media analytics. We discussed the specific properties of UGC, the general research tasks currently operating on this type of content, identifying their limitations, and imagining new types of applications. We formed two working groups, WG1 "Fake News and Credibility", WG2 "Summarizing and Story Telling from UGC". WG1 invented an "Information Nutrition Label" that characterizes a document by different features such as e.g. emotion, opinion, controversy, and topicality; For computing these feature values, available methods and open research issues were identified. WG2 developed a framework for summarizing heterogeneous, multilingual and multimodal data, discussed key challenges and applications of this framework.

KW - 6121 Languages

KW - 213 Electronic, automation and communications engineering, electronics

KW - social media

KW - user-generated content

KW - social multimedia

KW - summarisation

KW - fake-news

KW - AI

KW - credibility

KW - storytelling

U2 - 10.4230/DagRep.7.7.110

DO - 10.4230/DagRep.7.7.110

M3 - Other conference material

SP - 141

EP - 153

ER -

Rudinac S, Chua T-S, Diaz-Ferreyra N, Friedland G, Gornostaja T, Huet B et al. Rethinking Summarization and Storytelling for Modern Social Multimedia. 2018. Dagstuhl Seminar 17301, Daghstuhl, Germany. https://doi.org/10.4230/DagRep.7.7.110