This n8n workflow automates the process of analyzing hotel reviews to determine sentiment. It starts by receiving reviews via a webhook, processes the text to split it into manageable chunks, and generates embeddings using Hugging Face models. These embeddings are stored in a Pinecone vector database for efficient retrieval. When a new review is received, the workflow queries similar past reviews from Pinecone, employs a language model to interpret sentiment, and maintains context with a memory buffer. Finally, the results are logged into a Google Sheet for record-keeping. This setup is ideal for hoteliers or travel platforms seeking to automate review sentiment analysis and improve customer insights.
Hotel Review Sentiment Analysis Workflow
Node Count | 11 – 20 Nodes |
---|---|
Nodes Used | @n8n/n8n-nodes-langchain.agent, @n8n/n8n-nodes-langchain.embeddingsHuggingFace, @n8n/n8n-nodes-langchain.lmChatHf, @n8n/n8n-nodes-langchain.memoryBufferWindow, @n8n/n8n-nodes-langchain.textSplitterCharacterTextSplitter, @n8n/n8n-nodes-langchain.toolVectorStore, @n8n/n8n-nodes-langchain.vectorStorePinecone, googleSheets, stickyNote, webhook |
Reviews
There are no reviews yet.