Towards Successful Social Media Advertising: Predicting the Influence of Commercial Tweets

TL;DR

This paper develops a predictive model for commercial tweets' influence, combining decoration and meta features, and demonstrates how to reword unsuccessful tweets to enhance their impact on social media marketing.

Contribution

It introduces a systematic methodology for analyzing and predicting the influence of commercial tweets, outperforming baseline and embedding models, and shows how to engineer tweets for greater success.

Findings

Model outperforms baseline and embedding models in influence prediction

Combining decoration and meta features improves accuracy

Rewording tweets can increase their likelihood of success

Abstract

Businesses communicate using Twitter for a variety of reasons -- to raise awareness of their brands, to market new products, to respond to community comments, and to connect with their customers and potential customers in a targeted manner. For businesses to do this effectively, they need to understand which content and structural elements about a tweet make it influential, that is, widely liked, followed, and retweeted. This paper presents a systematic methodology for analyzing commercial tweets, and predicting the influence on their readers. Our model, which use a combination of decoration and meta features, outperforms the prediction ability of the baseline model as well as the tweet embedding model. Further, in order to demonstrate a practical use of this work, we show how an unsuccessful tweet may be engineered (for example, reworded) to increase its potential for success.