k-nn clasifier

ArnoG

I am using a K-nn clasifier to perform a sentiment analysis on review texts. I export the results to an excel sheet. For every month (cumlative) I create a bar graph showing the results, Basically the bar graph shows the # of positive and negative reviews.

But till my suprise the results of the sentiment analysis difference per month. For the sentiment analysis I am using exacrly the same model, and exactly the same data & training set. When I run the analyses for january a certain review is labeled positive, when I run the same analyses till february, the same review in january is now labeled as negative.

Is there a way to prefend this?

Best regards,

Arno

RalfKlinkenberg

Hi Arno,

Are you sure that you use exactly the same training data set for both applications of k-NN in January and February?

If you share your RapidMiner process, we could better check for the reason for this process behaviour.

Best regards,
Ralf

ArnoG

Hi Ralf,
Thanks for your response!

I am completely sure that I didn't change the training set.

As an example I used following process:

<?xml version="1.0" encoding="UTF-8" standalone="no"?>
<process version="6.0.003">
  <context>
    <input/>
    <output/>
    <macros/>
  </context>
  <operator activated="true" class="process" compatibility="6.0.003" expanded="true" name="Process">
    <process expanded="true">
      <operator activated="true" class="read_excel" compatibility="6.0.003" expanded="true" height="60" name="Results" width="90" x="45" y="210">
        <parameter key="excel_file" value="C:\Improve Your Business\Qing\Rapidminer\testing knn.xls"/>
        <parameter key="sheet_number" value="2"/>
        <parameter key="imported_cell_range" value="A1:A18"/>
        <parameter key="first_row_as_names" value="false"/>
        <list key="annotations">
          <parameter key="0" value="Name"/>
        </list>
        <list key="data_set_meta_data_information">
          <parameter key="0" value="Test reviews.true.text.attribute"/>
        </list>
      </operator>
      <operator activated="true" class="select_attributes" compatibility="6.0.003" expanded="true" height="76" name="Select Attributes" width="90" x="313" y="210">
        <parameter key="attribute_filter_type" value="subset"/>
        <parameter key="attributes" value="text|sent|Review|Prijs|Test reviews"/>
      </operator>
      <operator activated="true" class="set_role" compatibility="6.0.003" expanded="true" height="76" name="Set Role" width="90" x="514" y="210">
        <parameter key="attribute_name" value="Test reviews"/>
        <list key="set_additional_roles"/>
      </operator>
      <operator activated="true" class="text:process_document_from_data" compatibility="5.3.002" expanded="true" height="76" name="Process Documents from Data (2)" width="90" x="648" y="210">
        <parameter key="keep_text" value="true"/>
        <parameter key="prune_method" value="absolute"/>
        <parameter key="prune_below_absolute" value="2"/>
        <parameter key="prune_above_absolute" value="999"/>
        <list key="specify_weights"/>
        <process expanded="true">
          <operator activated="true" class="text:tokenize" compatibility="5.3.002" expanded="true" height="60" name="Tokenize (2)" width="90" x="112" y="30"/>
          <operator activated="true" class="text:transform_cases" compatibility="5.3.002" expanded="true" height="60" name="Transform Cases (4)" width="90" x="246" y="30"/>
          <operator activated="true" class="text:filter_stopwords_dictionary" compatibility="5.3.002" expanded="true" height="76" name="Filter Stopwords (4)" width="90" x="380" y="30">
            <parameter key="file" value="C:\Improve Your Business\Qing\Rapidminer\nederlandse stopwoordenlijst.txt"/>
          </operator>
          <operator activated="false" class="text:stem_snowball" compatibility="5.3.002" expanded="true" height="60" name="Stem (4)" width="90" x="514" y="120">
            <parameter key="language" value="Dutch"/>
          </operator>
          <operator activated="true" class="text:filter_by_length" compatibility="5.3.002" expanded="true" height="60" name="Filter Tokens (3)" width="90" x="648" y="30">
            <parameter key="min_chars" value="2"/>
          </operator>
          <operator activated="false" class="text:generate_n_grams_terms" compatibility="5.3.002" expanded="true" height="60" name="Generate n-Grams (2)" width="90" x="782" y="120"/>
          <connect from_port="document" to_op="Tokenize (2)" to_port="document"/>
          <connect from_op="Tokenize (2)" from_port="document" to_op="Transform Cases (4)" to_port="document"/>
          <connect from_op="Transform Cases (4)" from_port="document" to_op="Filter Stopwords (4)" to_port="document"/>
          <connect from_op="Filter Stopwords (4)" from_port="document" to_op="Filter Tokens (3)" to_port="document"/>
          <connect from_op="Filter Tokens (3)" from_port="document" to_port="document 1"/>
          <portSpacing port="source_document" spacing="0"/>
          <portSpacing port="sink_document 1" spacing="0"/>
          <portSpacing port="sink_document 2" spacing="0"/>
        </process>
      </operator>
      <operator activated="true" class="read_excel" compatibility="6.0.003" expanded="true" height="60" name="Training set" width="90" x="45" y="30">
        <parameter key="excel_file" value="C:\Improve Your Business\Qing\Rapidminer\testing knn.xls"/>
        <parameter key="imported_cell_range" value="A1:B243"/>
        <parameter key="first_row_as_names" value="false"/>
        <list key="annotations">
          <parameter key="0" value="Name"/>
        </list>
        <list key="data_set_meta_data_information">
          <parameter key="0" value="Prijs.true.text.attribute"/>
          <parameter key="1" value="B.true.polynominal.label"/>
        </list>
      </operator>
      <operator activated="true" class="select_attributes" compatibility="6.0.003" expanded="true" height="76" name="Select Attributes (2)" width="90" x="313" y="30">
        <parameter key="attribute_filter_type" value="subset"/>
        <parameter key="attributes" value="sent|text|training set|sen|Prijs"/>
      </operator>
      <operator activated="true" class="set_role" compatibility="6.0.003" expanded="true" height="76" name="Set Role (2)" width="90" x="514" y="30">
        <parameter key="attribute_name" value="Prijs"/>
        <list key="set_additional_roles"/>
      </operator>
      <operator activated="true" class="text:process_document_from_data" compatibility="5.3.002" expanded="true" height="76" name="Process Documents from Data" width="90" x="648" y="30">
        <parameter key="keep_text" value="true"/>
        <parameter key="prune_method" value="absolute"/>
        <parameter key="prune_below_absolute" value="2"/>
        <parameter key="prune_above_absolute" value="999"/>
        <list key="specify_weights"/>
        <process expanded="true">
          <operator activated="true" class="text:tokenize" compatibility="5.3.002" expanded="true" height="60" name="Tokenize" width="90" x="45" y="30">
            <parameter key="characters" value=".:?!"/>
          </operator>
          <operator activated="true" class="text:transform_cases" compatibility="5.3.002" expanded="true" height="60" name="Transform Cases" width="90" x="179" y="30"/>
          <operator activated="true" class="text:filter_stopwords_dictionary" compatibility="5.3.002" expanded="true" height="76" name="Filter Stopwords (3)" width="90" x="313" y="30">
            <parameter key="file" value="C:\Improve Your Business\Qing\Rapidminer\nederlandse stopwoordenlijst.txt"/>
          </operator>
          <operator activated="true" class="text:filter_by_length" compatibility="5.3.002" expanded="true" height="60" name="Filter Tokens (by Length)" width="90" x="581" y="30">
            <parameter key="min_chars" value="2"/>
          </operator>
          <connect from_port="document" to_op="Tokenize" to_port="document"/>
          <connect from_op="Tokenize" from_port="document" to_op="Transform Cases" to_port="document"/>
          <connect from_op="Transform Cases" from_port="document" to_op="Filter Stopwords (3)" to_port="document"/>
          <connect from_op="Filter Stopwords (3)" from_port="document" to_op="Filter Tokens (by Length)" to_port="document"/>
          <connect from_op="Filter Tokens (by Length)" from_port="document" to_port="document 1"/>
          <portSpacing port="source_document" spacing="0"/>
          <portSpacing port="sink_document 1" spacing="0"/>
          <portSpacing port="sink_document 2" spacing="0"/>
        </process>
      </operator>
      <operator activated="true" class="k_nn" compatibility="6.0.003" expanded="true" height="76" name="k-NN (2)" width="90" x="782" y="30">
        <parameter key="k" value="3"/>
        <parameter key="weighted_vote" value="true"/>
        <parameter key="measure_types" value="NumericalMeasures"/>
        <parameter key="numerical_measure" value="CosineSimilarity"/>
      </operator>
      <operator activated="true" class="apply_model" compatibility="6.0.003" expanded="true" height="76" name="Apply Model (2)" width="90" x="916" y="120">
        <list key="application_parameters"/>
      </operator>
      <connect from_op="Results" from_port="output" to_op="Select Attributes" to_port="example set input"/>
      <connect from_op="Select Attributes" from_port="example set output" to_op="Set Role" to_port="example set input"/>
      <connect from_op="Set Role" from_port="example set output" to_op="Process Documents from Data (2)" to_port="example set"/>
      <connect from_op="Process Documents from Data (2)" from_port="example set" to_op="Apply Model (2)" to_port="unlabelled data"/>
      <connect from_op="Training set" from_port="output" to_op="Select Attributes (2)" to_port="example set input"/>
      <connect from_op="Select Attributes (2)" from_port="example set output" to_op="Set Role (2)" to_port="example set input"/>
      <connect from_op="Set Role (2)" from_port="example set output" to_op="Process Documents from Data" to_port="example set"/>
      <connect from_op="Process Documents from Data" from_port="example set" to_op="k-NN (2)" to_port="training set"/>
      <connect from_op="k-NN (2)" from_port="model" to_op="Apply Model (2)" to_port="model"/>
      <connect from_op="Apply Model (2)" from_port="labelled data" to_port="result 1"/>
      <portSpacing port="source_input 1" spacing="0"/>
      <portSpacing port="sink_result 1" spacing="0"/>
      <portSpacing port="sink_result 2" spacing="0"/>
    </process>
  </operator>
</process>


I run the process for data till april and one till may.

Images below shows the results from running the two datasets

Till April



Till May:


As you can see is the review "goede prijs" in the run till april predicted neg and in the run till may pos.

I used exactly the same RM process and exactly the same training data.

How can I get different results?

Best Regards,

Arno