Using Semantic Similarity and Text Embedding to Measure the Social Media Echo of Strategic Communications
This addresses the challenge for researchers and organizations in measuring message influence in large-scale social media data, though it is incremental as it applies existing methods to a specific domain.
The paper tackles the problem of evaluating the impact of strategic communications in online discourse by introducing a technique that uses semantic similarity to quantify changes in discussion after a message is published, showing a heavy-tailed distribution of responses in climate change debates.
Online discourse covers a wide range of topics and many actors tailor their content to impact online discussions through carefully crafted messages and targeted campaigns. Yet the scale and diversity of online media content make it difficult to evaluate the impact of a particular message. In this paper, we present a new technique that leverages semantic similarity to quantify the change in the discussion after a particular message has been published. We use a set of press releases from environmental organisations and tweets from the climate change debate to show that our novel approach reveals a heavy-tailed distribution of response in online discourse to strategic communications.