# Simultaneous Inference of User Representations and Trust

## TL;DR

This paper introduces a novel representation learning approach for trust prediction among social media users, effectively leveraging limited trust data to learn user embeddings and predict trust relations, outperforming existing methods.

## Contribution

It is the first to explore representation learning specifically for trust prediction, combining small trust datasets with embedding techniques for improved accuracy.

## Key findings

- Achieved an F-score of 92.65% on a large dataset.
- Outperformed classifier-based approaches using DeepWalk and LINE.
- Further improved performance with pre-trained embeddings.

## Abstract

Inferring trust relations between social media users is critical for a number of applications wherein users seek credible information. The fact that available trust relations are scarce and skewed makes trust prediction a challenging task. To the best of our knowledge, this is the first work on exploring representation learning for trust prediction. We propose an approach that uses only a small amount of binary user-user trust relations to simultaneously learn user embeddings and a model to predict trust between user pairs. We empirically demonstrate that for trust prediction, our approach outperforms classifier-based approaches which use state-of-the-art representation learning methods like DeepWalk and LINE as features. We also conduct experiments which use embeddings pre-trained with DeepWalk and LINE each as an input to our model, resulting in further performance improvement. Experiments with a dataset of $\sim$356K user pairs show that the proposed method can obtain an high F-score of 92.65%.