.. _auto_dataset_run_sentiment_analysis:

*RUN SENTIMENT ANALYSIS ON A DATASET COLUMN*
============================================

Runs sentiment analysis on a specified text column in a dataset, classifying each row's text as positive or negative based on a configurable score threshold and optional custom word lists. The result is appended as a new column in the output dataset. Use this worker to enrich tabular data with sentiment labels derived from free-text fields.

When to use
-----------

Classification: **process**.

Tagged: ``custom_words``, ``dataset``, ``nlp``, ``positive_threshold``, ``sentiment_analysis``, ``text_classification``.

Inputs
------

.. list-table::
   :header-rows: 1
   :widths: 20 20 20 20 20 20

   * - Label
     - ID
     - Type
     - Default
     - Required
     - Description
   * - Dataset
     - dataset_1
     - dataset
     - —
     - 
     - Input dataset containing the text column to be analyzed; must be a tabular dataset with at least one free-text column.
   * - Choose Column
     - target_column
     - text
     - —
     - 
     - Name of the column in dataset_1 whose text values will be scored for sentiment; must match an existing column header exactly.
   * - New Column Name
     - new_col_name
     - text
     - —
     - 
     - Name to assign to the newly created sentiment-label column appended to the output dataset; choose a unique name to avoid overwriting existing columns.
   * - Positive Threshold Value
     - positive_threshold
     - text
     - 0.9
     - 
     - Floating-point score threshold (0.0–1.0) above which a text entry is classified as positive; defaults to 0.9 — lower this value to broaden the positive class.
   * - Additional Positive Words
     - positive_words
     - textarea
     - —
     - 
     - Newline- or comma-separated list of additional words to bias the model toward a positive classification; leave blank to rely solely on the built-in vocabulary.
   * - Additional Negative Words
     - negative_words
     - textarea
     - —
     - 
     - Newline- or comma-separated list of additional words to bias the model toward a negative classification; leave blank to rely solely on the built-in vocabulary.

Outputs
-------

.. list-table::
   :header-rows: 1
   :widths: 20 20 20 20

   * - Label
     - ID
     - Type
     - Description
   * - dataset_run_sentiment_analysis_output_1
     - dataset_run_sentiment_analysis_output_1
     - dataset
     - Copy of the input dataset with an appended column (named by new_col_name) containing the sentiment label or score for each row.

Disciplines
-----------

- ai_ml.llm
- ai_ml.supervised.classification
- data.dataset.transform

Runnable example
----------------

A runnable example is registered for this worker. Open the example workflow on the d3VIEW canvas: `/api/workflow/example?id=dataset_run_sentiment_analysis <https://www.d3view.com/api/workflow/example?id=dataset_run_sentiment_analysis>`_

.. raw:: html

   <hr style="margin-top:2em">
   <p style="font-size:11px;color:#888">
   Auto-generated from <code>transformation</code> schema. Worker id: <code>dataset_run_sentiment_analysis</code>. Schema hash: <code>5d6c8fa55c64</code>. Hand-curated docs in <code>workerexamples/</code> override this page when present.
   </p>