Topic Signatures in Political Campaign Speeches
نویسندگان
چکیده
Highlighting the recurrence of topics usage in candidates speeches is a key feature to identify the main ideas of each candidate during a political campaign. In this paper, we present a method combining standard topic modeling with signature mining for analyzing topic recurrence in speeches of Clinton and Trump during the 2016 American presidential campaign. The results show that the method extracts automatically the main ideas of each candidate and, in addition, provides information about the evolution of these topics during the campaign.
منابع مشابه
The discrepancy in the perception of the public-political speech in Croatia.
Key place in this paper takes the study of political speech in the Republic of Croatia and their impact on voters, or which keywords are in political speeches and public appearances of politicians in Croatia that their voting body wants to hear. Given listed below we will define the research topic in the form of a question - is there a discrepancy in the perception of the public-political speec...
متن کاملThey Want To Eradicate the Nation: A Cross-Linguistic Study of the Attitudinal Language of Presidential Campaign Speeches in the USA and Iran
Politicians adopt a variety of linguistic strategies in their speeches to connect with their audience. To name one, appraisal, as a system of interpersonal meaning, is concerned with evaluation where resources are used for negotiating social relationships. Despite their significance in shaping texts, there have hardly been any extensive inventories of appraisal tools contrasting electoral speec...
متن کاملMeasuring Ideological Proportions in Political Speeches
We seek to measure political candidates’ ideological positioning from their speeches. To accomplish this, we infer ideological cues from a corpus of political writings annotated with known ideologies. We then represent the speeches of U.S. Presidential candidates as sequences of cues and lags (filler distinguished only by its length in words). We apply a domain-informed Bayesian HMM to infer th...
متن کاملPolitical Speech Generation
In this report we present a system that can generate political speeches for a desired political party. Furthermore, the system allows to specify whether a speech should hold a supportive or opposing opinion. The system relies on a combination of several state-of-the-art NLP methods which are discussed in this report. These include n-grams, Justeson & Katz POS tag filter, recurrent neural networ...
متن کاملAn Analysis of the Influence of Radio Political Campaign Messages on Voters’ Electoral Behavior in Kano, Nigeria
This paper will examine the influence of radio political campaign messages on the electorates’ voting behavior in Kano – Nigeria, with a focus on the 2015 general elections. It seeks to ascertain the extent that the electorates in Kano – Nigeria were exposed to radio political campaign messages, as well as the extent to which such messages influenced their voting decisions. Equally, the study c...
متن کامل