Abstract
This paper examines the social media strategies of candidates seeking their party’s nomination for the 2016 U.S. presidential election. We use textual analysis to understand what candidates focused on. We assess eight themes covered in Twitter posts. For example, Clinton focused on GUN CONTROL, while Sanders focused on climate change. Using Facebook data, we introduce a topic modeling approach, latent Dirichlet allocation, to the political marketing literature. This allows us to uncover what topics the candidates focus on without researcher intervention and, using a dynamic model, show how this changes over time. We note that Clinton’s focus on Trump increases toward the end of the primary campaign.
| Original language | English |
|---|---|
| Pages (from-to) | 244-266 |
| Journal | Journal of Political Marketing |
| Volume | 16 |
| Issue number | 3-4 |
| DOIs | |
| Publication status | Published - 29 Jul 2017 |
| Externally published | Yes |
Bibliographical note
Publication details (e.g. title, author(s), publication statuses and dates) are captured on an “AS IS” and “AS AVAILABLE” basis at the time of record harvesting from the data source. Suggestions for further amendments or supplementary information can be sent to [email protected].Research Keywords
- Political campaigns
- Primaries
- Social media
- Topic modeling
