Stand still and watch the patterns, which by pure chance have been generated: Stains on the wall, or the ashes in a fireplace or the clouds in the sky, or the gravel on the beach, or other things. If you look at them carefully you might discover miraculous inventions. (Leonardo da Vinci)
 

Mining Mass Opinions: International Workshop in Hong Kong

March 30th, 2009 General, Innovation, Knowledge|

What is an opinion? Wikipedia says that “an opinion is a belief that may or may not be backed up with evidence, but which cannot be proved with that evidence. An opinion is neither right nor wrong. It is normally a subjective statement and may be the result of an emotion or an interpretation of facts; people may draw opposing opinions from the same facts.”

However. Understanding and analyzing opinions is fine for geeky twitter-blogosphere-analysts, marketing soldiers (who want to know how their products perform in the public) or, somehow more evil, for political governments to check the people’s opinions about public topics. The last approach could should be inverted: Analyze political publications, quotations in the media and parliament protocols to really understand the opinion and intentions of individual politicians or parties. This can be a tool for positive democratic development.

In November 2009 there is an interesing workshop about this field: http://sites.google.com/site/tsa2009workshop/

The suggested topics are:

  • 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

Tags: analysis, Analyze, bias, categorization, Domain-dependency, emotion, Hong Kong, interpretation, Mining, opinion, retrieval, sentiment, Topic, Understanding, workshop

2 Comments on “Mining Mass Opinions: International Workshop in Hong Kong”

  1. 1 Hannes Carl Meyer said at 11:01 am on March 30th, 2009:

    There was an interesting example from the Fraunhofer IAIS at CeBIT 09 doing kind of opinion mining, project called: “Online Emotions-Radar”:

    http://www.iais.fraunhofer.de/4399.html

    They are still searching for cooperations with companies who are interested in opinion mining projects!

  2. 2 Volker said at 2:57 pm on April 3rd, 2009:

    Yup, been there. It seemed to be a really promising technology.


Leave a Reply