Choice-Aware User Engagement Modeling andOptimization on Social Media

TL;DR

This paper presents a neural network model for predicting and optimizing user engagement on Twitter by modeling choice behavior and leveraging engagement history to maximize interactions like likes and retweets.

Contribution

It introduces a choice-aware neural network architecture for engagement prediction and formulates an optimization framework for maximizing user engagement on social media.

Findings

Effective prediction of user engagement using the proposed model.

Demonstrated improvement in engagement metrics through optimization.

Large-scale Twitter dataset validates the approach.

Abstract

We address the problem of maximizing user engagement with content (in the form of like, reply, retweet, and retweet with comments)on the Twitter platform. We formulate the engagement forecasting task as a multi-label classification problem that captures choice behavior on an unsupervised clustering of tweet-topics. We propose a neural network architecture that incorporates user engagement history and predicts choice conditional on this context. We study the impact of recommend-ing tweets on engagement outcomes by solving an appropriately defined sweet optimization problem based on the proposed model using a large dataset obtained from Twitter.