From Amateurs to Connoisseurs: Modeling the Evolution of User Expertise through Online Reviews

Abstract

Recommending products to consumers means not only understanding their tastes, but also understanding their level of experience. For example, it would be a mistake to recommend the iconic film Seven Samurai simply because a user enjoys other action movies; rather, we might conclude that they will eventually enjoy it -- once they are ready. The same is true for beers, wines, gourmet foods -- or any products where users have acquired tastes: the `best' products may not be the most `accessible'. Thus our goal in this paper is to recommend products that a user will enjoy now, while acknowledging that their tastes may have changed over time, and may change again in the future. We model how tastes change due to the very act of consuming more products -- in other words, as users become more experienced. We develop a latent factor recommendation system that explicitly accounts for each user's level of experience. We find that such a model not only leads to better recommendations, but also allows us to study the role of user experience and expertise on a novel dataset of fifteen million beer, wine, food, and movie reviews.

arXiv comment11 pages, 7 figures

References in corpus (1)

• Learning Attitudes and Attributes from Multi-Aspect Reviews

Cited by in corpus (30)

• Enhancing Graph Neural Network-based Fraud Detectors against Camouflaged Fraudsters
• Winning Arguments: Interaction Dynamics and Persuasion Strategies in Good-faith Online Discussions
• Online Popularity and Topical Interests through the Lens of Instagram
• Semi-supervised Credit Card Fraud Detection via Attribute-Driven Graph Representation
• People on Media: Jointly Identifying Credible News and Trustworthy Citizen Journalists in Online Communities
• Alleviating Structural Distribution Shift in Graph Anomaly Detection
• DP-GAN: Diversity-Promoting Generative Adversarial Network for Generating Informative and Diversified Text
• Wisdom of the Crowd or Wisdom of a Few? An Analysis of Users' Content Generation
• Item Recommendation with Evolving User Preferences and Experience
• Action Sequence Augmentation for Early Graph-based Anomaly Detection
• FairJudge: Trustworthy User Prediction in Rating Platforms
• Modeling User Behavior With Interaction Networks for Spam Detection
• Community Identity and User Engagement in a Multi-Community Landscape
• Autoencoder as Assistant Supervisor: Improving Text Representation for Chinese Social Media Text Summarization
• Detecting Changes in User Preferences using Hidden Markov Models for Sequential Recommendation Tasks
• GCN-Based User Representation Learning for Unifying Robust Recommendation and Fraudster Detection
• Item Recommendation with Continuous Experience Evolution of Users using Brownian Motion
• HoloScope: Topology-and-Spike Aware Fraud Detection
• Regularizing Output Distribution of Abstractive Chinese Social Media Text Summarization for Improved Semantic Consistency
• Coupled Compound Poisson Factorization
• A Field Test of Bandit Algorithms for Recommendations: Understanding the Validity of Assumptions on Human Preferences in Multi-armed Bandits
• Modeling, comprehending and summarizing textual content by graphs
• Packaging and Sharing Machine Learning Models via the Acumos AI Open Platform
• Autoencoding Word Representations through Time for Semantic Change Detection
• The Graph-Based Behavior-Aware Recommendation for Interactive News
• Who is Really Affected by Fraudulent Reviews? An analysis of shilling attacks on recommender systems in real-world scenarios
• A Surrogate-based Generic Classifier for Chinese TV Series Reviews
• User Bias Removal in Review Score Prediction
• Efficient Time-Evolving Stream Processing at Scale
• Preference Modeling by Exploiting Latent Components of Ratings