Semantic temporality analysis: A computational approach to time in English and German texts

Temporality is an important aspect of political discourse. Politicians and policymakers attempt to construct the past future gain power, legitimize their policies, claim success for themselves blame others. To make computational analysis temporality more accessible, we develop a new methodology using semisupervised machine-learning algorithm called Latent Semantic Scaling. Only with set common verbs in perfect tense as seed words, estimates all other words. We demonstrate that it can identify temporal orientation English German sentences from election manifestos around 60–70% accurately, which comparable results recent study based on supervised algorithms. also apply Twitter posts by parties reveal policy issues.