Opinion Mining

sudheendra
sudheendra New Altair Community Member
edited November 5 in Community Q&A
Hai,

My Objective is to extract the opinion about a particular subject/fact(For Example- Scope of Data Mining) from social medias like twitter, facebook. How can I proceed with the same using RM. Any one can provide the operator names whch is suitable for my objective

Thanks,
Sudheendra
Tagged:

Answers

  • land
    land New Altair Community Member
    Hi,
    this is possible with the operators of the Text Plugin of RapidMiner 4.x or with the combination of the Text Processing Extension and the still unpublished Web Extension of RapidMiner 5. The latter will give you easy access to all these pages, but we still working on it.

    Greetings,
      Sebastian
  • sudheendra
    sudheendra New Altair Community Member
    Hai Sebastain,

    I have tried with crawler operator with RM 4.6 version. I would like to get the opinion about global warming from facebook.whenever I am trying for that I am getting an error message "ArrayIndexOutOfBoundsException". I am attaching the process below.Can you suggest how to proceed further

    <operator name="Root" class="Process" expanded="yes">
        <operator name="Crawler" class="Crawler">
            <parameter key="url" value="http://www.facebook.com"/>
            <list key="crawling_rules">
              <parameter key="visit_url" value="http://www.facebook.com/search/?q=global+warming&amp;init=quick#/topic.php?uid=20009925629&amp;topic=13945"/>
              <parameter key="visit_content" value="global warming"/>
            </list>
            <parameter key="output_dir" value="C:\Documents and Settings\ADMIN\Desktop\qq"/>
            <parameter key="extension" value="html"/>
        </operator>
    </operator>


    Thanks,
    Sudheendra
  • land
    land New Altair Community Member
    Hi,
    the old crawler had many problems, these error messages where one, the intraceability the second. So I can't really say why this hapens. I would guess it's because you don't have a single website crawled, because your rules don't apply correct. It's a little bit tricky how to do this.
    The visit_url is no regular expression and applies only to the starting site. This should be put to URL parameter instead.

    Greetings,
      Sebastian
  • Jepse
    Jepse New Altair Community Member
    Hi!!

    @Sebastian: when will be the Web Extension released? Is there any beta available?

    Brgds Jepse
  • land
    land New Altair Community Member
    Hi,
    unfortunately not, but it will be published soon.

    Greetings,
      Sebastian

Categories