What is Neural Sentiment Detection?
Neural Sentiment Detection is an AutoLearn model that was trained on a dataset of 44 million English customer product reviews using a Label-Embedding Attentive Model (LEAM) approach. It was trained to determine sentiment using star ratings from the reviews as its ground truth. The model returns a score field that reflects sentiment scores or polarities scored on a scale of 0 to 1.
As a pre-trained model, sometimes the Neural Sentiment Detection can get lost among your other pre-trained models. However, you can always find it by searching.
When should I use Neural Sentiment Detection?
Because few clients have enough quality data to build out powerful AutoLearn models, Stratifyd provides one that is pre-trained. Since the model is already trained, you need only select a textual field similar to a customer review to use it. You might also use a textual field from survey responses or Glassdoor reviews, as the language used is similar to the language people use when leaving a product review.
The Neural Sentiment Detection model is not optimal for large text fields. This is because longer text contains language (emotional and descriptive terms used to express their concerns) that is fundamentally different in comparison. For example a chat transcript is typically so long that the sentiment averages out to zero, unless people chat in and say "I hate you guys, you are terrible."
If you require more flexibility, and want to specify your own ground truth, you can opt to use the Theme Detection model instead. With that lexicon-based model, in addition to getting sentiment scores, you can also specify a date field for timelines, and location fields for maps.
Additionally, custom models are available (see versions of sentiment predictive below). New custom models can be developed upon request but depends on the scope. If interested, contact your account team for more details.
The model requires one Unstructured Text field, a field that collects free-form user feedback that users type rather than select from a list.
The model returns the following fields for use in widget visualizations.
neural_sentiment_en.keyword: A textual array of the most important words within the data stream. In supervised models, keywords are the terms that the model finds and uses to predict each label.
nerual_sentiment_en.score: The predicted sentiment value between 0 and 1 based on your input data, also known as the Neural Sentiment Score.
Data: A table containing all of the original data from the data stream, plus all of the analyzed data from the model.
Versions of Sentiment Predictive
General English - used amazon as training data
App Store - used app store data for training
Pharma - used pharma medical insight notes for training
Hospitality - used hospitality feedback for training
To use the Neural Sentiment Detection Model
1. You can create a model from within a workspace, or you can add one to the Models page. Here, we create it from within a workspace.
2. To access the Data Settings Panel menu, click the Data settings button, accompanied by the gear icon.
In the data settings panel that appears, you'll see a list of all data connections for that workspace. Make sure you have selected the data stream you want to work with in the Connected column.
3. In the Analyze tab, expand the section labelled How are our customers feeling? to see available models.
4. Choose Neural Sentiment Detection by clicking the + icon.
5. For the model to run successfully, you'll need to select a text dimension that is associated with a star rating value, like review text. Make your selections and click Start Analysis.
6. Depending on the size and complexity of your data, it may take some time for the analysis to finish running. When you return to the Data Settings, you'll see this analysis within the Deployed section at the top of the the Analyze tab.
We're here to help! Don't hesitate to contact us for further assistance via chat or submit a ticket!
Please sign in to leave a comment.