Databases
StackOverflow2013
Postsdbo
PO
 

Note that there are some explanatory texts on larger screens.

plurals
  1. PO
    primarykey
    data
    text
    <p>You don't mention anything about <a href="http://en.wikipedia.org/wiki/Word_stem" rel="nofollow">stemming</a>. In my opinion you could have better results if you were performing word stemming and the WEKA evaluation was based on the <strong>keyword stems</strong>. </p> <p>For example let's suppose that your WEKA model is built given a keyword <em>surfing</em> and a new rss feed contains the word <em>surf</em>. There should be a match between these two words.</p> <p>There are many free available stemmers for several languages. </p> <p>For the English language some available options for stemming are:</p> <ul> <li>The <a href="http://tartarus.org/martin/PorterStemmer/" rel="nofollow">Porter's stemmer</a></li> <li>Stemming based on the <a href="http://wordnet.princeton.edu/" rel="nofollow">WordNet's</a> dictionary</li> </ul> <p>In case you would like to perform stemming using the WordNet's dictionary, there are libraries &amp; frameworks that perform integration with WordNet.</p> <p>Below you can find some of them:</p> <ul> <li>MIT Java WordNet interface (<a href="http://projects.csail.mit.edu/jwi/" rel="nofollow">JWI</a>)</li> <li><a href="http://www.rednoise.org/rita/" rel="nofollow">Rita</a></li> <li>Java WorNet Library (<a href="http://sourceforge.net/projects/jwordnet/" rel="nofollow">JWNL</a>)</li> </ul> <p><strong>EDITED</strong> after more information was provided</p> <p>I believe that the keypoint in the specified case is the selection of the "most popular 64 words". The selected words or phrases should be keywords or keyphrases. So the challenge here is the keywords or keyphrases extraction.</p> <p>There are several books, papers and algorithms written about keywords/keyphrases extraction. The university of Waikato has implemented in JAVA, a famous algorithm called <a href="http://www.nzdl.org/Kea/" rel="nofollow">Keyword Extraction Algorithm (KEA)</a>. KEA extracts keyphrases from text documents and can be either used for free indexing or for indexing with a controlled vocabulary. The implementation is distributed under the GNU General Public License.</p> <p>Another issue that should be taken into consideration is the (Part of Speech)POS tagging. <strong>Nouns contain more information</strong> than the other POS tags. Therefore may you would have better results if you were checking the POS tag and the selected 64 words were mostly nouns.</p> <p>In addition according to the Anette Hulth's published paper <a href="http://acl.ldc.upenn.edu/acl2003/emnlp/pdf/Hulth.pdf" rel="nofollow">Improved Automatic Keyword Extraction Given More Linguistic Knowledge</a>, her experiments showed that the keywords/keyphrases mostly have or are contained in one of the following five patterns:</p> <ul> <li>ADJECTIVE NOUN (singular or mass) </li> <li>NOUN NOUN (both sing. or mass) </li> <li>ADJECTIVE NOUN (plural) </li> <li>NOUN (sing. or mass) NOUN (pl.) </li> <li>NOUN (sing. or mass) </li> </ul> <p>In conclusion a simple action that in my opinion could improve your results is to find the POS tag for each word and select mostly nouns in order to evaluate the new RSS feeds. You can use WordNet in order to find the POS tag for each word and as I mentioned above there are many libraries on the web that perform integration with the WordNet's dictionary. Of course stemming is also essential for the classification process and has to be maintained.</p> <p>I hope this helps.</p>
    singulars
    1. This table or related slice is empty.
    1. POImproving classification results with Weka J48 and Naive Bayes Multinomial classifiers
      singulars
      1. PTQuestion
    1. PTAnswer
    1. USTolis Emmanouilidis
    1. USTolis Emmanouilidis
    plurals
    1. This table or related slice is empty.
    1. This table or related slice is empty.
    1. POImproving classification results with Weka J48 and Naive Bayes Multinomial classifiers
      singulars
      1. PTQuestion
    1. This table or related slice is empty.
    1. VO
      singulars
      1. PO
      1. This table or related slice is empty.
      1. VTAcceptedByOriginator
    2. VO
      singulars
      1. PO
      1. This table or related slice is empty.
      1. VTUpMod
    1. COThanks but unfortunately, the keywords are being stemmed prior to classification by Lucene's implementation of Porter.
      singulars
      1. PO
      1. USMr Morgan
    2. COCould you provide a high level description of the whole procedure? It will help us to have a better understanding of how your system works. The keywords are stemmed using Lucene's stemmer but what happens afterwards? Are the new rss feeds classified using the stems or not? Thanks
      singulars
      1. PO
      1. USTolis Emmanouilidis
    3. COI've added a detailed description of the process and some thoughts of my own as to why the frequencies are low. Maybe I can't see the 'wood for the trees' at the moment.
      singulars
      1. PO
      1. USMr Morgan
 

Querying!

 
Guidance
A row detail

Detail views are divided into sections. All the information in the data section comes from columns in the selected row. The other sections display data from other, related rows.

Related data can be related in a to-one or a to-many fashion. Captions of data related in a to-many fashion link to a list view showing a filtered view of the table.

Try moving around until you find a non-empty to-many entry and click on the label to get to one. You can move back to the root by clicking on the database name in the header.

SQuiL has stopped working due to an internal error.

If you are curious you may find further information in the browser console, which is accessible through the devtools (F12).

Reload