TSA'09 - 1st International CIKM Workshop on Topic-Sentiment Analysis for Mass Opinion Measurement (Hong Kong Nov. 6, 2009)
10-15-2009: A free buffet lunch will be available to all TSA'09 attendees on Nov. 6. Lunch ticket will be included in the conference kit. 
        Lunch Time: 12:00 - 13:45
    Lunch Location: IKON restaurant, located on the same  floor as the workshop room

08-25-2009: early registration extended to September 3 (10:59 EDT(GMT-5)) 2009! (deadline passed)
08-11-2009: Notification of acceptance
07-13-2009: last CFP
06-28-2009: 4th CFP
05-28-2009: 3rd CFP
05-18-2009: Submission site is up
04-30-2009: 2nd CFP
03-30-2009: 1st CFP
03-22-2009: Workshop site is up
Scope of the Workshop

This workshop seeks to bring together researchers in both computer science and social sciences who are interested in developing and using topic-sentiment analysis methods to measure mass opinion, and to foster communications between the research community and industry practitioners as well.

The increasing amount of user-generated content on the Internet and social media and the digitization of large number of government and institutional documents provide new opinion-rich data sources for researchers to examine individual and group perceptions on products, organizations, and social issues at a large scale, and thus contribute to the research and practice in the areas of political science, social policy, communications, and business intelligence.

On the other hand, researchers are tackling the problem of processing large amount of opinion-rich data using various approaches. The increasing number of relevant publications in top data mining, information retrieval and natural language processing conferences (KDD, SIGIR, ACL, WWW, etc.) has witnessed the growing interest in automatic opinion analysis. Both TREC and TAC (Text Analysis Conference) have set up individual tracks for opinion retrieval and analysis tasks.

In recent years topic detection and tracking techniques have been well developed to identify the issues discussed in a large text collection. Sentiment analysis is catching up to detect the polarity of opinions expressed in texts. However, many times real-world applications have to take into consideration of both topics and sentiments for precise opinion measurement. Topic and sentiment alignment is crucial for opinion retrieval, extraction, categorization, and aggregation on various issues. Topics and sentiments could also have sophisticated interactions. For example, the choice of topics and the attention distribution among topics might bear hidden opinions as well.

How do we build synergistic topic and sentiment models for text documents? How do we tackle the domain-dependency problem of sentiment analysis? How do we identify users' needs and integrate them into the design of opinion analysis systems? What are the successful applications of topic-sentiment analysis for mass opinion measurement? What lessons have the pioneers learned? How do we evaluate the automatic mass opinion measuring tools with regard to the reliability and validity? This workshop solicits submissions to address these problems and more.

We hope this workshop can advance research in topic-sentiment analysis, make connections between research community and industry practitioners and encourage development of high performance tools and systems that can work at the web scale for real world applications.

Topics of Interest

Suggested topics include, but are not limited to:

  • Opinion retrieval, extraction, categorization, and aggregation
  • Topic and sentiment alignment in opinion analysis
  • Applications of topic-sentiment analysis, e.g. corporate reputation measurement, political orientation categorization, customer preference study, public opinion study
  • Issues in using topic-sentiment analysis as a new research method for mass opinion estimation, such as reliability, validity, sample bias, etc.
  • Sentiment identification and filtering at various text granularity
  • Domain-dependency of sentiment analyzers
  • Evaluation methodologies
  • Performance issues, scalability and efficiency
  • Web-based system demonstration
  • Novel algorithms, tools and systems
  • Construction of benchmark data sets
Important Dates
  • Individual workshop papers due: July 22, 2009 (deadline passed)
  • Notification of Acceptance: August 10, 2009 (deadline passed)
  • Camera ready: August 19, 2009 *(hard deadline for publication in proceedings)* (deadline passed)
  • Early registration deadline: Sep. 3 (10:59 EDT(GMT-5)) 2009 (deadline passed)
  • Workshop: November 6, 2009
TSA'09 will be held in Rm202 at Asia World-Expo, near Hong Kong International Airport, Lantau, Hong Kong. For details, please visit the following websites of CIKM'09.
conference site: http://www.comp.polyu.edu.hk/conference/cikm2009/location/location.htm

accommodation: http://www.comp.polyu.edu.hk/conference/cikm2009/location/local_information.htm

Hong Kong: http://www.comp.polyu.edu.hk/conference/cikm2009/location/hongkong.htm

travel: http://www.comp.polyu.edu.hk/conference/cikm2009/location/travel.htm

Program (9:00 - 17:30 Nov. 6, 2009)
keynote speech
*Title: What were they thinking?!  The Role of Topics and Opinion Holders for Fine-grained Opinion Analysis
     by Professor Claire Cardie, Cornell University (USA)

Claire Cardie is a Professor in the Computer Science department at Cornell University, where she is also the Charles and Barbara Weiss Director of the university's new Information Science program. She obtained a B.S. in Computer Science from Yale University (1982) and an M.S. and PhD in Computer Science at the University of Massachusetts at Amherst (1994).  Cardie's research is in the areas of natural language processing and machine learning.  In particular, she has focused on the development of machine learning techniques for building robust and portable information extraction systems. She is a recipient of a National Science Foundation CAREER award and has served on the ACL's executive committee, and as secretary of the North American chapter of the Association for Computational Linguistics (NAACL) (2000-2003). She has been Program Chair for the joint ACL/COLING conference in 2006, for CoNLL (Conference on Natural Language Learning) in 2000, and for the EMNLP (Empirical Methods in NLP) conference in 1997.  She is co-founder and Chief Scientist of Jodange.com, a company that specializes in the extraction and aggregation of opinions and sentiment from text.

common coffee break

Session 1: Topic and Sentiment
Chair: Sung-Hyon Myaeng (KAIST, Republic of Korea)

* Patterns in the Stream: Exploring the Interaction of Polarity, Topic, and Discourse in a Large Opinion Corpus (11:00-11:25)
    Julian Brooke (University of Toronto, Canada)
    Matthew Hurst (Microsoft Live Labs, United States)

* Topic-dependent Sentiment Analysis of Financial Blogs (11:25-11:50)
     Neil O'Hare (CLARITY: Centre for Sensor Web Technologies, Dublin City University, Ireland)
    Michael Davy (National Centre for Language Technology, Dublin City University, Ireland)
    Adam Bermingham  (CLARITY: Centre for Sensor Web Technologies, Dublin City University, Ireland)
    Paul Ferguson  (CLARITY: Centre for Sensor Web Technologies, Dublin City University, Ireland)
    Paraic Sheridan (National Centre for Language Technology, Dublin City University, Ireland)
    Cathal Gurrin  (CLARITY: Centre for Sensor Web Technologies, Dublin City University, Ireland)
    Alan Smeaton  (CLARITY: Centre for Sensor Web Technologies, Dublin City University, Ireland)

* Scary Films Good, Scary Flights Bad: Topic driven feature selection for classification of sentiment (11:50-12:15)
    Scott Nowson (Appen Pty Ltd, Australia)

* Evaluating Question Answering Systems on Opinion Queries (12:15-12:30)
    Alexandra Balahur (DLSI, University of Alicante, Spain)
    Ester Boldrini (Universidad de Alicante, DLSI, Spain)
    Andrés Montoyo (University of Alicante, Spain)
    Patricio Martínez-Barco (University of Alicante, Spain)

free buffet lunch (IKON restaurant, the same floor as the workshop room)

Session 2: Challenge: corpus, domain, irony
Chair: Jingbo Zhu (Northeastern University, China)

* Automatic Creation of a Reference Corpus for Political Opinion Mining in User-Generated Content (14:00-14:25) (link to authors' work)
    Luis Sarmento (Universidade do Porto, Portugal)
    Paula Carvalho (University of Lisbon, Faculty of Sciences, LASIGE, Portugal)
    Mário J. Silva (University of Lisbon, Faculty of Sciences, LASIGE, Portugal)
    Eugénio Oliveira (Faculdade de Engenharia Universidade do Porto - LIACC, Portugal)

* Domain-specific Sentiment Analysis using Contextual Feature Generation (14:25-14:50)
    Yoonjung Choi (KAIST, Korea, Republic of)
    Youngho Kim (KAIST, Korea, Republic of)
    Sung-Hyon Myaeng (KAIST, Korea, Republic of)

* Weakly Supervised Techniques for Domain-Independent Sentiment Classification (14:50-15:15)
    Jonathon Read (University of Sussex, United Kingdom)
    John Carroll (University of Sussex, United Kingdom)

* Clues for Detecting Irony in User-Generated Contents: Oh...!! It's " so easy" ;-) (15:15-15:30) (link to authors' work)
    Paula Carvalho (University of Lisbon, Faculty of Sciences, LASIGE, Portugal)
    Luis Sarmento (Universidade do Porto, Portugal)
    Mário J. Silva (University of Lisbon, Faculty of Sciences, LASIGE, Portugal)
    Eugénio Oliveira (Faculdade de Engenharia Universidade do Porto - LIACC, Portugal)

common coffee break

Session 3: Application
Chair: Mário J. Silva (University of Lisbon, Portugal)

* Beyond the Stars: Exploiting Free-Text User Reviews for Improving the Accuracy of Movie Recommendations (16:00-16:25)
    Niklas Jakob (Technische Universität Darmstadt, Germany)
    Stefan Hagen Weber (Siemens AG, Germany)
    Mark-Christoph Müller (Technische Universität Darmstadt, Germany)
    Iryna Gurevych (Darmstadt University of Technology, Germany)

* Aspect-based Sentence Segmentation for Sentiment Summarization (16:25-16:50)
    Jingbo Zhu (Northeastern University, China)
    Muhua Zhu (Northeastern University, China)
    Huizhen Wang (Northeastern University, China)
    Benjamin Tsou (City University of Hong Kong, Hong Kong)

* Locally Contextualized Smoothing of Language Models for Sentiment Sentence Retrieval (16:50-17:15)
    Takayoshi Okamoto (Kobe University, Japan)
    Tetsuya Honda (Kobe University, Japan)
    Koji Eguchi (Kobe University, Japan)

* Sentiment Analysis of Movie Reviews on Discussion Boards using a Linguistic Approach (17:15-17:30)
    Tun Thura Thet (Nanyang Technological University, Singapore)
    Jin-Cheon Na (Nanyang Technological University, Singapore)
    Christopher S.G. Khoo (Nanyang Technological University, Singapore)
  • All workshop papers will be up to 8 pages, double column in the ACM format. No extra pages can be purchased for all workshop papers.
  • Please ensure that your paper is formatted by using the ACM templates. Papers must be submitted in PDF files.
  • At least one author of each accepted paper must register for the workshop. Registration must be done at the time when the author sends the camera-ready copy of the accepted paper to the workshop chair.
  • Workshop proceedings will be printed along with the CIKM proceedings by ACM. Thus, the timeline to print proceedings must strictly follow with the CIKM proceedings schedule.
  • Submission site is now open for submission via http://www.easychair.org/conferences/?conf=tsa09

Bei Yu, byu@syr.edu, Syracuse University, USA
Maojin Jiang, jianmao@iit.edu, Illinois Institute of Technology, USA

Program Committee
Khurshid Ahmad, Trinity College Dublin (Ireland)
James Allan, University of Massachusetts Amherst (USA)
Shlomo Argamon, Illinois Institute of Technology (USA)
Kenneth Bloom, Illinois Institute of Technology (USA)
Claire Cardie, Cornell University (USA)
Michael Gamon, Microsoft Research (USA)
Natalie Glance, Google (USA)
Xiao Hu, Riverglass (USA)
Matthew Hurst, Microsoft Live Lab (USA)
Panagiotis G. Ipeirotis, New York University (USA)
Stefan Kaufmann, Northwestern University (USA)
Moshe Koppel, Bar-Ilan University (Israel)
Thomas Y. Lee, University of Pennsylvania (USA)
Qiaozhu Mei, University of Illinois at Urbana-Champaign (USA)
Ana-Maria Popescu, Yahoo! Labs (USA)
Long Qiu, Institute for Infocomm Research (Singapore)
Stuart W. Shulman, University of Massachusetts Amherst (USA)
Veselin Stoyanov, Cornell University (USA)
John D. Wilkerson, University of Washington (USA)
Waigen Yee, Illinois Institute of Technology (USA)
Bei Yu, Syracuse University (USA)
Chengxiang Zhai, University of Illinois at Urbana-Champaign (USA)
Xiaojin Zhu, University of Wisconsin-Madison (USA)

Please contact Maojin Jiang to report problems. Thanks! (last updated: 2:05PM, 11/19/2009)