Abstract
Social media sites played an important role in the 2022 Philippine election, capturing and swaying the public’s opinion and shaping the political narrative in the country. This paper explores the public conversations in social media, specifically Twitter, to identify dominant sentiments in election-related social media posts. Focusing on and using keywords related to the top Philippine Presidential and Vice-Presidential candidates, a corpus of 16.3 million Twitter posts made during the election period were analyzed. Results show that the prevailing emotions during the election period were: (1) Hope/Excitement/Optimism; (2) Anger/Hate/Sadness; (3) Anxiety/Fear; and (4)Trust/Pride. While these posts evoked distinct and heightened emotions, the overall tone generated from the posts were neutral (overall: 85.6%; presidentiables: 84.9%; vice-presidentiable: 82.8%). Negative sentiments were associated with the spread of false information and some of the candidates’ avoidance of debate and interviews (overall: 4.8%; presidentiables: 4%; vice-presidentiable: 2.3%). Meanwhile, positive sentiments stemmed from endorsements from prominent personalities and the people’s belief that their candidates will lead the country to a better future (overall: 9.6%; presidentiables: 11.1%; vice-presidentiable: 14.9%). Being able to infer public sentiments in a dynamic platform like Twitter will help us understand how social media platforms perform key roles in enabling or deterring political action.
Presenters
Elena PerniaVice President for Public Affairs, Office of the Vice President for Public Affairs, University of the Philippines, Philippines Rachel Khan
Associate Dean, Journalism, University of the Philippines College of Mass Communication, Philippines Dianne Stephanie Gavan
Research Assistant, University of the Philippines, Philippines Jamie Lyn Loristo
Research Associate, University of the Philippines, Philippines
Details
Presentation Type
Paper Presentation in a Themed Session
Theme
KEYWORDS
Philippine Election, Social Media, Twitter, Sentiment Analysis