In some cases, you may not need to create a category model to score. The Text Link Analysis (TLA)
node adds a pattern-matching technology to text mining's concept extraction. This identifies
relationships between the concepts in the text data based on known patterns. These relationships can
describe how a customer feels about a product, which companies are doing business together, or even
the relationships between genes or pharmaceutical agents.Figure 1. Text Link Analysis node
Add a Text Link Analysis node to your canvas and connect it to the Data Asset node that points
to hotelSatisfaction.csv. Double-click the node to open its properties.
Select id for the ID field and Comments
for the Text field. Note that only the Text field is
required.
For Copy resources from, select the Hotel Satisfaction
(English) template.Figure 2. Text Link Analysis node FIELD properties
Under Expert, select Accommodate spelling for a minimum word
character length of.Figure 3. Text Link Analysis node Expert properties
The resulting output is a table (or the result of an Export node).Figure 4. Raw TLA output
Figure 5. Counting sentiments on a TLA node
Focus sentinel
Focus sentinel
Focus sentinel
Focus sentinel
Generative AI search and answer
These answers are generated by a large language model in watsonx.ai based on content from the product documentation. Learn more
The resulting output is a table (or the result of an Export node).
