How Does Time Shape Political Campaign Communication?

This study asks how political parties divide attention across the past, present and future in campaign communication and whether incumbency shapes emotive rhetoric across these temporal dimensions. Using supervised machine learning to label temporal focus, the author analyzes 621 party manifestos from nine countries spanning 1949–2017 and describes the share of manifesto text devoted to each temporal category. The contribution is a systematic, cross-national description of parties' temporal rhetorical emphasis and how statements about past and present relate to differences in sentiment between incumbents and opposition.

Supervised machine learning for temporal labeling 621 party manifestos across nine countries (1949–2017) Comparison of incumbents versus opposition rhetoric

Data and methods

The author applies supervised machine learning to identify temporal focus (past, present, future) in 621 party manifestos collected from nine countries between 1949 and 2017. The abstract reports the approach as automated classification of manifesto statements by temporal category; further dataset specifics and replication materials are linked in the citation but are not summarized beyond the abstract.

Main findings

According to the abstract, parties allocate about half of manifesto text to future promises and the remaining half to descriptions of the past and present. The author also reports that statements about the past and present account for previously observed sentiment differences between incumbents and opposition parties, suggesting incumbency conditions emotive rhetoric across temporal dimensions.

• Parties devote, on average, roughly 50% of manifesto content to future promises, with the remainder focused on past and present.
• Past and present statements help explain incumbent–opposition differences in sentiment, per the author's analysis.