Synerise at RecSys 2021: Twitter user engagement prediction with a fast neural model

by   Michał Daniluk, et al.

In this paper we present our 2nd place solution to ACM RecSys 2021 Challenge organized by Twitter. The challenge aims to predict user engagement for a set of tweets, offering an exceptionally large data set of 1 billion data points sampled from over four weeks of real Twitter interactions. Each data point contains multiple sources of information, such as tweet text along with engagement features, user features, and tweet features. The challenge brings the problem close to a real production environment by introducing strict latency constraints in the model evaluation phase: the average inference time for single tweet engagement prediction is limited to 6ms on a single CPU core with 64GB memory. Our proposed model relies on extensive feature engineering performed with methods such as the Efficient Manifold Density Estimator (EMDE) - our previously introduced algorithm based on Locality Sensitive Hashing method, and novel Fourier Feature Encoding, among others. In total, we create numerous features describing a user's Twitter account status and the content of a tweet. In order to adhere to the strict latency constraints, the underlying model is a simple residual feed-forward neural network. The system is a variation of our previous methods which proved successful in KDD Cup 2021, WSDM Challenge 2021, and SIGIR eCom Challenge 2020. We release the source code at:


page 1

page 2

page 3

page 4


Choice-Aware User Engagement Modeling andOptimization on Social Media

We address the problem of maximizing user engagement with content (in th...

Privacy-Preserving Recommender Systems Challenge on Twitter's Home Timeline

Recommender systems constitute the core engine of most social network pl...

Modeling Multi-Destination Trips with Sketch-Based Model

The recently proposed EMDE (Efficient Manifold Density Estimator) model ...

Predicting User Engagement Status for Online Evaluation of Intelligent Assistants

Evaluation of intelligent assistants in large-scale and online settings ...

Predicting Misinformation and Engagement in COVID-19 Twitter Discourse in the First Months of the Outbreak

Disinformation entails the purposeful dissemination of falsehoods toward...

Two Stages Approach for Tweet Engagement Prediction

This paper describes the approach proposed by the D2KLab team for the 20...

Understanding Twitter Engagement with a Click-Through Rate-based Method

This paper presents the POLINKS solution to the RecSys Challenge 2020 th...

Please sign up or login with your details

Forgot password? Click here to reset