skip to main content
10.1145/2501217acmconferencesBook PagePublication PageskddConference Proceedingsconference-collections
MDMKDD '13: Proceedings of the Thirteenth International Workshop on Multimedia Data Mining
ACM2013 Proceeding
Publisher:
  • Association for Computing Machinery
  • New York
  • NY
  • United States
Conference:
KDD' 13: The 19th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining Chicago Illinois 11 August 2013
ISBN:
978-1-4503-2333-8
Published:
11 August 2013
Sponsors:
Recommend ACM DL
ALREADY A SUBSCRIBER?SIGN IN
Next Conference
Reflects downloads up to 16 Feb 2025Bibliometrics
Skip Abstract Section
Abstract

The theme of the MDMKDD'13 workshop is\mining large scale rich content in a networked society." The workshop brought together experts in computational analysis on digital media content and multimedia databases, as well as knowledge engineers and domain experts from different applied disciplines with potential in multimedia data mining. The new theme of this year's workshop highlights the integration of multimedia in people's daily lives. With the rapid growth of mobile devices and personalized data, we wanted the workshop to focus on mining large scale rich content which is abundant in today's networked societies.

Vast amount of multimedia data are produced, shared, and accessed everyday in various social platforms. These multimedia objects (images, videos, texts, tags, etc.) represent rich, multifaceted recordings of human behavior in the networked society, which lead to a range of social applications such as consumer behavior forecasting, social driven advertising / business, local knowledge discovery (e.g., for tourism or shopping), detection of emergent news events and trends, and so on. In addition to techniques for mining single media items, all of these applications require new methods for extracting robust features and discovering stable relationships among different media modalities and the users, in a dynamic, social context rich, and likely noisy environment.

Multimedia is designed to stimulate the human senses beyond text. Using the rich content in multiple media types, we can capture the full experience of an event. Mining the data within media rich platforms and immersive environments (such as online communities, blogs, social networks, and virtual worlds) integrates the digital and physical experiences and information. The aim of the MDMKDD'13 workshop is to explore the role that multimedia data mining can play to enhance virtual society experiences.

Skip Table Of Content Section
research-article
Who is repinning?: predicting a brand's user interactions using social media retrieval
Article No.: 1, Pages 1–9https://doi.org/10.1145/2501217.2501218

Despite the fact that firms spend heavily in marketing their brands across social media platforms, very little is understood about what media content, in a predictive manner, can generate high interaction rates among their prospects and customers. ...

research-article
Robust detection of hyper-local events from geotagged social media data
Article No.: 2, Pages 1–9https://doi.org/10.1145/2501217.2501219

An increasing number of location-annotated content available from social media channels like Twitter, Instagram, Foursquare and others are reflecting users' local activities and their attention like never before. In particular, we now have enough ...

research-article
Towards social imagematics: sentiment analysis in social multimedia
Article No.: 3, Pages 1–8https://doi.org/10.1145/2501217.2501220

Online social networks have attracted attention of people from both the academia and real world. In particular, the rich multimedia information accumulated in recent years provides an easy and convenient way for more active communication between people. ...

Contributors
  • International Business Machines
  • Google LLC
  • Nokia Corporation
  • University of Pittsburgh
  • Ying Wu College of Computing

Index Terms

  1. Proceedings of the Thirteenth International Workshop on Multimedia Data Mining
      Index terms have been assigned to the content through auto-classification.

      Recommendations

      Acceptance Rates

      MDMKDD '13 Paper Acceptance Rate 3 of 5 submissions, 60%;
      Overall Acceptance Rate 3 of 5 submissions, 60%
      YearSubmittedAcceptedRate
      MDMKDD '135360%
      Overall5360%