What is it about?
We transform the review text into feature vectors and use them in combination with the rating scores in a hybrid probabilistic matrix factorization algorithm.
Featured Image
Why is it important?
The proposed methodology outperforms other recommendation approaches, ALS, a pure matrix factorization approach, HFT3, which incorporates the free-text reviews in Matrix Factorization, and DeepCoNN++4, which preserves word order and context but does not take into account the document (review) context, on six datasets, five categories of Amazon product data and Yelp Open Dataset.
Read the Original
This page is a summary of: From Free-text User Reviews to Product Recommendation using Paragraph Vectors and Matrix Factorization, May 2019, ACM (Association for Computing Machinery),
DOI: 10.1145/3308560.3316601.
You can read the full text:
Contributors
The following have contributed to this page
