Deploying Sentiment Predictor - Lexicon Based

Deploying Sentiment Analysis Predictive Model - Lexicon Based Approach

This worflow applies the lexicon based approach on unlabeled social media posts to predict their sentiment. The last component visualizes (1) the bar chart with the number of negative/positive/neutral posts, (2) the word cloud of all collected posts, and (3) the table with all collected posts.

1. Read unlabeled, compatible social media posts.

2. Data Manipulation/Preparation.

Here the most important node is Strings to Document, which formats sevaral string columns (e.g., author, text, title) into a single document that can be text-mined in KNIME.

6. Visualize data. (1) bar chart of # positive, negative, and neutral posts; (2) word cloud; and (3) table with posts.

3. Use Text Mining to Tag Words with Positive and Negative Meaning based on a Dictionary.

4. Count the Number of Positive and Negative Words per Document.

5. Calculate a Sentiment Score based on the Number of Positive and Negative Words and Classify Documents based on the Score.

The sentiment score is calculated by (number of postive words - number of negative words) divided by (number of postive words + number of negative words).

If the score is negative, the post is classified as negative; if the score is positive, it is classified as positive; and if it is equal to 0, the post is classified as neutral.