Hey guys,
I'm trying to apply a dictionary based sentiment analysis using an own dictionary.
First, my dataset are Excel Files of newspaper interviews and is structured in the following way: column 1 contains the text (the text is splitted in the first question in row 1, the first answer in row 2, the second question in row 3 and so on), column 2 contains an id (interview identifier as well as if it is a question/answer and which one). I am able to manage it from retrieving excel files, processing the documents including tokenization. Afterwards I am using "Dictionary Based Sentiment" and "Apply dictionary based sentiment" operators but it is not possible to me to match dictionary (excel file with column 1 for word and column 2 for weights (1 positive and -1 negative)) and newspaper interviews.
Can you help me?
<?xml version="1.0" encoding="UTF-8"?><process version="7.6.003">
<context>
<input/>
<output/>
<macros/>
</context>
<operator activated="true" class="process" compatibility="7.6.003" expanded="true" name="Process">
<parameter key="logverbosity" value="init"/>
<parameter key="random_seed" value="2001"/>
<parameter key="send_mail" value="never"/>
<parameter key="notification_email" value=""/>
<parameter key="process_duration_for_mail" value="30"/>
<parameter key="encoding" value="UTF-8"/>
<process expanded="true">
<operator activated="true" class="concurrency:loop_files" compatibility="7.6.003" expanded="true" height="82" name="Loop Files" width="90" x="45" y="34">
<parameter key="directory" value="C:\Users\g21640\Desktop\ojee\bla"/>
<parameter key="filter_type" value="glob"/>
<parameter key="recursive" value="false"/>
<parameter key="enable_macros" value="false"/>
<parameter key="macro_for_file_name" value="file_name"/>
<parameter key="macro_for_file_type" value="file_type"/>
<parameter key="macro_for_folder_name" value="folder_name"/>
<parameter key="reuse_results" value="false"/>
<parameter key="enable_parallel_execution" value="true"/>
<process expanded="true">
<operator activated="true" class="read_excel" compatibility="7.6.003" expanded="true" height="68" name="Read Excel" width="90" x="179" y="34">
<parameter key="excel_file" value="C:\Users\g21640\Desktop\ojee\bla\2000_0101_2003_3112(1).xlsx"/>
<parameter key="sheet_number" value="1"/>
<parameter key="imported_cell_range" value="A1:E43"/>
<parameter key="encoding" value="UTF-8"/>
<parameter key="first_row_as_names" value="false"/>
<list key="annotations">
<parameter key="0" value="Name"/>
</list>
<parameter key="date_format" value=""/>
<parameter key="time_zone" value="SYSTEM"/>
<parameter key="locale" value="English (United States)"/>
<list key="data_set_meta_data_information">
<parameter key="0" value="data.false.file_path.attribute"/>
<parameter key="1" value="id.false.integer.attribute"/>
<parameter key="2" value="item.true.polynominal.attribute"/>
<parameter key="3" value="type.false.polynominal.attribute"/>
<parameter key="4" value="idid.true.polynominal.id"/>
</list>
<parameter key="read_not_matching_values_as_missings" value="true"/>
<parameter key="datamanagement" value="double_array"/>
<parameter key="data_management" value="auto"/>
</operator>
<connect from_port="file object" to_op="Read Excel" to_port="file"/>
<connect from_op="Read Excel" from_port="output" to_port="output 1"/>
<portSpacing port="source_file object" spacing="0"/>
<portSpacing port="source_input 1" spacing="0"/>
<portSpacing port="sink_output 1" spacing="0"/>
<portSpacing port="sink_output 2" spacing="0"/>
</process>
</operator>
<operator activated="true" class="append" compatibility="7.6.003" expanded="true" height="82" name="Append" width="90" x="179" y="34">
<parameter key="datamanagement" value="double_array"/>
<parameter key="data_management" value="auto"/>
<parameter key="merge_type" value="all"/>
</operator>
<operator activated="true" class="nominal_to_text" compatibility="7.6.003" expanded="true" height="82" name="Nominal to Text" width="90" x="313" y="34">
<parameter key="attribute_filter_type" value="single"/>
<parameter key="attribute" value="item"/>
<parameter key="attributes" value=""/>
<parameter key="use_except_expression" value="false"/>
<parameter key="value_type" value="nominal"/>
<parameter key="use_value_type_exception" value="false"/>
<parameter key="except_value_type" value="file_path"/>
<parameter key="block_type" value="single_value"/>
<parameter key="use_block_type_exception" value="false"/>
<parameter key="except_block_type" value="single_value"/>
<parameter key="invert_selection" value="false"/>
<parameter key="include_special_attributes" value="false"/>
</operator>
<operator activated="true" breakpoints="after" class="text:process_document_from_data" compatibility="7.5.000" expanded="true" height="82" name="Process Documents from Data (8)" width="90" x="447" y="34">
<parameter key="create_word_vector" value="true"/>
<parameter key="vector_creation" value="Term Occurrences"/>
<parameter key="add_meta_information" value="true"/>
<parameter key="keep_text" value="true"/>
<parameter key="prune_method" value="none"/>
<parameter key="prune_below_percent" value="3.0"/>
<parameter key="prune_above_percent" value="30.0"/>
<parameter key="prune_below_rank" value="0.05"/>
<parameter key="prune_above_rank" value="0.95"/>
<parameter key="datamanagement" value="double_sparse_array"/>
<parameter key="data_management" value="auto"/>
<parameter key="select_attributes_and_weights" value="false"/>
<list key="specify_weights"/>
<process expanded="true">
<operator activated="true" class="text:transform_cases" compatibility="7.5.000" expanded="true" height="68" name="Transform Cases" width="90" x="246" y="34">
<parameter key="transform_to" value="lower case"/>
</operator>
<operator activated="true" class="text:tokenize" compatibility="7.5.000" expanded="true" height="68" name="Tokenize" width="90" x="447" y="34">
<parameter key="mode" value="non letters"/>
<parameter key="characters" value=".:"/>
<parameter key="language" value="English"/>
<parameter key="max_token_length" value="3"/>
</operator>
<connect from_port="document" to_op="Transform Cases" to_port="document"/>
<connect from_op="Transform Cases" from_port="document" to_op="Tokenize" to_port="document"/>
<connect from_op="Tokenize" 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="set_role" compatibility="7.6.003" expanded="true" height="82" name="Set Role" width="90" x="581" y="34">
<parameter key="attribute_name" value="text"/>
<parameter key="target_role" value="text"/>
<list key="set_additional_roles">
<parameter key="idid" value="id"/>
<parameter key="text" value="text"/>
</list>
</operator>
<operator activated="true" breakpoints="after" class="text:data_to_documents" compatibility="7.5.000" expanded="true" height="68" name="Data to Documents" width="90" x="514" y="136">
<parameter key="select_attributes_and_weights" value="true"/>
<list key="specify_weights">
<parameter key="text" value="1.0"/>
</list>
</operator>
<operator activated="true" breakpoints="after" class="read_excel" compatibility="7.6.003" expanded="true" height="68" name="Read Excel (2)" width="90" x="45" y="187">
<parameter key="excel_file" value="C:\Users\g21640\Desktop\Dropbox\Promotion\rapidminer listen\BPW_Wortlisten_test.xlsx"/>
<parameter key="sheet_number" value="1"/>
<parameter key="imported_cell_range" value="A1:B12350"/>
<parameter key="encoding" value="SYSTEM"/>
<parameter key="first_row_as_names" value="true"/>
<list key="annotations"/>
<parameter key="date_format" value=""/>
<parameter key="time_zone" value="SYSTEM"/>
<parameter key="locale" value="English (United States)"/>
<list key="data_set_meta_data_information">
<parameter key="0" value="A.true.polynominal.attribute"/>
<parameter key="1" value="B.true.integer.attribute"/>
</list>
<parameter key="read_not_matching_values_as_missings" value="true"/>
<parameter key="datamanagement" value="double_array"/>
<parameter key="data_management" value="auto"/>
</operator>
<operator activated="true" breakpoints="after" class="operator_toolbox:dictionary_sentiment_learner" compatibility="0.9.000" expanded="true" height="82" name="Dictionary Based Sentiment" width="90" x="313" y="187">
<parameter key="Value Attribute" value="B"/>
<parameter key="Key Attribute" value="A"/>
<parameter key="Negation Attribute" value=""/>
<parameter key="Negation Window Size" value="1"/>
</operator>
<operator activated="true" class="operator_toolbox:apply_dictionary_learner" compatibility="0.9.000" expanded="true" height="103" name="Apply Dictionary Based Sentiment (2)" width="90" x="581" y="238"/>
<connect from_op="Loop Files" from_port="output 1" to_op="Append" to_port="example set 1"/>
<connect from_op="Append" from_port="merged set" to_op="Nominal to Text" to_port="example set input"/>
<connect from_op="Nominal to Text" from_port="example set output" to_op="Process Documents from Data (8)" to_port="example set"/>
<connect from_op="Process Documents from Data (8)" from_port="example set" to_op="Set Role" to_port="example set input"/>
<connect from_op="Set Role" from_port="example set output" to_op="Data to Documents" to_port="example set"/>
<connect from_op="Data to Documents" from_port="documents" to_op="Apply Dictionary Based Sentiment (2)" to_port="doc"/>
<connect from_op="Read Excel (2)" from_port="output" to_op="Dictionary Based Sentiment" to_port="exa"/>
<connect from_op="Dictionary Based Sentiment" from_port="mod" to_op="Apply Dictionary Based Sentiment (2)" to_port="mod"/>
<connect from_op="Apply Dictionary Based Sentiment (2)" from_port="res" 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"/>
<description align="left" color="yellow" colored="true" height="128" resized="true" width="459" x="46" y="27">Step 1<br></description>
</process>
</operator>
</process>
Best regards,
Daniel