Sentiment Analysis - Generative AI
<p>Generative AI for Sentiment Analysis: Classifying Customer Reviews</p><p>This workflow uses a Kaggle Dataset (https://www.kaggle.com/crowdflower/twitter-airline-sentiment) including thousands of customer social media posts towards six US airlines. Contributors annotated the valence of the tweets as positive, negative and neutral.</p><p>The generative AI-based approach prompts to an LLM, requesting to classify the airline reviews. Here, prompt engineering plays a key role. The response returned by the <em>LLM Prompter</em> node is then cleaned (post-processing) and then the GenAI-based predictions are evaluated.</p>
Generative AI for Sentiment Analysis: Classifying Customer Reviews
This workflow uses a Kaggle Dataset (https://www.kaggle.com/crowdflower/twitter-airline-sentiment) including thousands of customer social media posts towards six US airlines. Contributors annotated the valence of the tweets as positive, negative and neutral.
The generative AI-based approach prompts to an LLM, requesting to classify the airline reviews. Here, prompt engineering plays a key role. The response returned by the LLM Prompter node is then cleaned (post-processing) and then the GenAI-based predictions are evaluated.
Nodes
- Column Filter3 ×
- Expression3 ×
- Row Filter2 ×
CSV Reader1 ×- Credentials Configuration1 ×
- Joiner1 ×
- Scorer1 ×
- String Cleaner1 ×
- String Format Manager1 ×
- Table View1 ×
Extensions
Links
- No links available