A Predictive Method to Improve the Effectiveness of Twitter Communication for Museums

What is it about?

Museums are embracing social technologies in an attempt to broaden their audience and engage people. But, are their communication strategies effective? How can they be improved? In this paper, we focus on Twitter and we propose a novel method that exploits interpretable machine learning techniques to (a) predict whether a tweet will likely be appreciated by Twitter users or not; (b) present simple suggestions that will help enhance the message and increase the probability of its success.

Featured Image

Photo by Sergei A on Unsplash

Photo by Sergei A on Unsplash

Why is it important?

Our proposal is the first step towards a communication strategy capable of restoring users’ interest in museums. From a practical point of view, our method allows museum media managers to improve users’ engagement. Indeed, our method is easy to implement (as shown through our developed dashboard) and is democratic (i.e., it can be used by museums with rich communication plan budgets, and by museums with poor or no communication budgets). Using a real-world dataset of around 40,000 tweets written by 23 world-famous museums, we show that our proposed method allows identifying tweet features that are more likely to influence the tweet's success.

Perspectives