Call for Chapters

Edited book:

Mining of User Generated Content and Its Applications


Editors:

Marie-Francine Moens
Katholieke Universiteit Leuven, Belgium
http://people.cs.kuleuven.be/~sien.moens/

Juanzi Li
Tsinghua University, China
http://keg.cs.tsinghua.edu.cn/persons/ljz/

Tat-Seng Chua
National University of Singapore
http://www.comp.nus.edu.sg/~chuats/


The emergence of social networking sites such as Forums, Blogs, Twitter, YouTube, FanFiction, social news, mobile photo and video, check-ins has given rise to a huge amount of user generated content (UGC). Through these social sites, users ask questions, pose comments, provide answers, and tweet about their recent pursuits. These contents accumulated over the years have evolved into a huge unstructured source of timely knowledge. The ability to organize this knowledge will help to unlock the rich user generated contents to better understand the current information needs of users as well as to support trend and sentiment analysis, retrieval and question answering. The knowledge in UGC is also valuable for business intelligence, governmental intelligence, computational advertising, social communication, etc.

We will edit a book published by Tailor & Francis (CRC Press) in the series Social Media and Social Computing (Series editor is Irwin King) on this very current topic and would like to invite you to contribute a chapter to this book. Hereunder we specify the aims of the book, challenges of the domain, and give a tentative table of content.


Important dates:

March 15, 2012: Deadline for submission of title and abstract to be sent to one of the editors.
November December 20, 2012: End of reviewing period.
March 19, 2013: Deadline for submission of camera-ready version.

We foresee that the book will be published the latest in the Spring of 2013. Your chapter will be reviewed by the editors and additional specialists in the field, who will give you valuable comments to improve your chapter.
Templates for formatting the chapters can be found at: http://www.cs.kuleuven.be/groups/liir/UGCBookProject/CRC.zip
We expect chapters to be 20-30 pages long. Ideally a chapter contains 50% state-of-the-art work and 50% own work.

Challenges

User Generated Content is heterogeneous, distributed, informal, and often regards complementary content. Also, the content is not well-formed, containing non-grammatical sentences, spelling errors, and non-professional photos and videos. This gives rise to challenging research questions when processing UGC. These include: how to collect useful information from UGC, how to integrate and fuse them into knowledge, how to model and apply UGC to the benefit of our daily activities and to embody their business or societal value.

Aims

This book aims at introducing the current advanced research techniques relating to the analysis and understanding of UGC, as well as their applications such as prediction, analytics and computational advertising. In this book, we will define the tasks and media involved when processing the user generated content; present the most successful models for extracting and linking structured knowledge from UGC; lay the foundations for semantic annotation of UGC and multimodal processing of UGC sources (video/image/text /fanfiction/check-ins); study the important task of fusion of the many different domains that are involved; and discuss the collective intelligence, social aspects of UGC and latent topic modeling in UGC.

The book is divided into five parts. The first introduces the topic and discusses the emergence and implications of UGC. UGC is increasingly multimodal. The second part introduces the various techniques developed for processing multimodal UGC. The third part deals with knowledge extraction from the different types of UGC making UGC valuable for mining and search. This part also deals with the fusion of multi-source UGC to generate structured knowledge. The fourth part of the book especially focuses on natural language processing applications such as question answering and summarization. The fifth part discusses the applications of structured UGC in the domains of business intelligence, topic prediction and recommendation.

Preliminary Table of Contents

Part I. Introduction
  1. Introduction
    2. Marie-Francine Moens, Katholieke Universiteit Leuven, Belgium
    Juanzi Li, Tsinghua University, China
    Tat-Seng Chua, National University of Singapore, Singapore

  2. The Current State of the Web and Trends
    3. Juanzi Li, Tsinghua University, China
    Tat-Seng Chua, National University of Singapore, Singapore
    Marie-Francine Moens, Katholieke Universiteit Leuven, Belgium
Part II. Mining Different Media
  1. Social Annotation
    2. Jia Chen, Shanghai Jiaotong University, China
    Shenghua Bao, IBM China Research Laboratory, China
    Haofen Wang, Shanghai Jiaotong University, China
    Yong Yu, Shanghai Jiaotong University, China

  2. Sentiment Analysis in UGC
    3. Ning Yu, University of Kentucky, USA

  3. Mining User-Generated Content for Music Information Retrieval
    4. Markus Schedl, Johannes Kepler Universität Linz, Austria
    Mohamed Sordo, Universitat Pompeu Fabra (UPF), Spain
    Noam Koenigstein, Tel Aviv University, Israel
    Udi Weinsberg, Tel Aviv University, Israel

  4. Graph and Network Pattern Mining
    5. Jan Ramon, KU Leuven, Belgium
PART III. Mining and searching different types of UGC
  1. Knowledge Extraction from Wiki/Bbs/Blog/ News Websites
    2. Jun Zhao, NLPR, Institute of Automation Chinese Academy of Science, Chinas
    Kang Liu, NLPR, Institute of Automation Chinese Academy of Sciences, China
    Guangyou Zhou, NLPR, Institute of Automation Chinese Academy of Sciences, China
    Zhenyu Qi, NLPR, Institute of Automation Chinese Academy of Sciences, China
    Yang Liu, NLPR, Institute of Automation Chinese Academy of Sciences, China
    Xianpei Han, Institute of Software Chinese Academy of Sciences, China

  2. User Generated Content Search
    3. Roi Blanco, Yahoo! Labs, Barcelona, Spain
    Manuel Eduardo Ares Brea , Universidade da Coruña, Spain
    Christina Lioma, University of Copenhagen, Denmark

  3. Annotating a Five-Billion-Word Corpus of Japanese Blogs with Syntactic and Affective Information
    4. Michal Ptaszynski, Hokkai-Gakuen University, Japan
    Jacek Maciejewski, Hokkai-Gakuen University, Japan
    Pawel Dybala, Hokkai-Gakuen University, Japan
    Rafal Rzepka, Hokkai-Gakuen University, Japan
    Kenji Araki, Hokkai-Gakuen University, Japan
    Yoshio Momouchi, Hokkai-Gakuen University, Japan

PART IV. NLP applications
  1. Question-Answering of UCC
    2. Chin-Yew Lin, Microsoft Asia

  2. Summarization of UGC
    3. Dominic Rout, Sheffield University, UK
    Kalina Bontcheva, Sheffield University, UK

Part V. Other applications
  1. Recommendation systems
    2. Claudio Lucchese, Istituto di Scienza e Tecnologie dell’Informazione (ISTI), Italy
    Cristina Ioana Munteanu, Babes-Bolyai University, Romania
    Raffaele Perego, Istituto di Scienza e Tecnologie dell’Informazione (ISTI), Italy
    Fabrizio Silvestri, Istituto di Scienza e Tecnologie dell’Informazione (ISTI), Italy
    Hossein Vahabi, Istituto di Scienza e Tecnologie dell’Informazione (ISTI), Italy
    Rossano Venturini, Istituto di Scienza e Tecnologie dell’Informazione (ISTI), Italy

  2. Conclusions and a roadmap for future developments
    3. Marie-Francine Moens, Katholieke Universiteit Leuven, Belgium
    Juanzi Li, Tsinghua University, China
    Tat-Seng Chua, National University of Singapore, Singapore

Submissions and reviews