Opinion Prediction with User Fingerprinting

TL;DR

This paper introduces a dynamic user fingerprinting approach using contextual embeddings and RNNs to improve opinion prediction accuracy, demonstrating significant performance gains and new insights into user behavior modeling.

Contribution

A novel dynamic fingerprinting method leveraging contextual embeddings and RNNs for improved opinion prediction accuracy.

Findings

Up to 13% improvement in micro F1-score.

Better predictions with increased dynamic history length.

Performance varies with the nature of the article.

Abstract

Opinion prediction is an emerging research area with diverse real-world applications, such as market research and situational awareness. We identify two lines of approaches to the problem of opinion prediction. One uses topic-based sentiment analysis with time-series modeling, while the other uses static embedding of text. The latter approaches seek user-specific solutions by generating user fingerprints. Such approaches are useful in predicting user's reactions to unseen content. In this work, we propose a novel dynamic fingerprinting method that leverages contextual embedding of user's comments conditioned on relevant user's reading history. We integrate BERT variants with a recurrent neural network to generate predictions. The results show up to 13\% improvement in micro F1-score compared to previous approaches. Experimental results show novel insights that were previously unknown such as better predictions for an increase in dynamic history length, the impact of the nature of the article on performance, thereby laying the foundation for further research.