Context-Based Tweet Engagement Prediction

TL;DR

This study investigates the effectiveness of using only contextual features to predict tweet engagement, employing scalable data processing and feature engineering, and compares results with content-based models and challenge winners.

Contribution

It introduces a scalable pipeline for context-based tweet engagement prediction and provides insights into the most informative features and factors affecting model performance.

Findings

User engagement history and hashtag/link popularity are highly informative features.

Context-only models underperform compared to content-based models and challenge winners.

Factors like algorithm choice and dataset sampling significantly influence results.

Abstract

Twitter is currently one of the biggest social media platforms. Its users may share, read, and engage with short posts called tweets. For the ACM Recommender Systems Conference 2020, Twitter published a dataset around 70 GB in size for the annual RecSys Challenge. In 2020, the RecSys Challenge invited participating teams to create models that would predict engagement likelihoods for given user-tweet combinations. The submitted models predicting like, reply, retweet, and quote engagements were evaluated based on two metrics: area under the precision-recall curve (PRAUC) and relative cross-entropy (RCE). In this diploma thesis, we used the RecSys 2020 Challenge dataset and evaluation procedure to investigate how well context alone may be used to predict tweet engagement likelihood. In doing so, we employed the Spark engine on TU Wien's Little Big Data Cluster to create scalable data preprocessing, feature engineering, feature selection, and machine learning pipelines. We manually created just under 200 additional features to describe tweet context. The results indicate that features describing users' prior engagement history and the popularity of hashtags and links in the tweet were the most informative. We also found that factors such as the prediction algorithm, training dataset size, training dataset sampling method, and feature selection significantly affect the results. After comparing the best results of our context-only prediction models with content-only models and with models developed by the Challenge winners, we identified that the context-based models underperformed in terms of the RCE score. This work thus concludes by situating this discrepancy and proposing potential improvements to our implementation, which is shared in a public git repository.