Generative Concatenative Nets Jointly Learn to Write and Classify Reviews

TL;DR

This paper introduces a character-level RNN called the Generative Concatenative Network (GCN) that generates personalized reviews, learns author styles, and classifies reviews by author, product category, and sentiment without extra training.

Contribution

The GCN model jointly learns to generate and classify reviews using auxiliary inputs, demonstrating high accuracy in author, category, and sentiment classification from raw text.

Findings

GCN accurately identifies authors, categories, and ratings.

The model captures complex language dynamics like negation and slang.

Generates realistic, personalized product reviews.

Abstract

A recommender system's basic task is to estimate how users will respond to unseen items. This is typically modeled in terms of how a user might rate a product, but here we aim to extend such approaches to model how a user would write about the product. To do so, we design a character-level Recurrent Neural Network (RNN) that generates personalized product reviews. The network convincingly learns styles and opinions of nearly 1000 distinct authors, using a large corpus of reviews from BeerAdvocate.com. It also tailors reviews to describe specific items, categories, and star ratings. Using a simple input replication strategy, the Generative Concatenative Network (GCN) preserves the signal of static auxiliary inputs across wide sequence intervals. Without any additional training, the generative model can classify reviews, identifying the author of the review, the product category, and the sentiment (rating), with remarkable accuracy. Our evaluation shows the GCN captures complex dynamics in text, such as the effect of negation, misspellings, slang, and large vocabularies gracefully absent any machinery explicitly dedicated to the purpose.