Topic Signatures in Political Campaign Speeches

Clément Gautrais 1, 2 Peggy Cellier 3, 4 René Quiniou 2 Alexandre Termier 2, 1
2 LACODAM - Large Scale Collaborative Data Mining
Inria Rennes – Bretagne Atlantique , IRISA_D7 - GESTION DES DONNÉES ET DE LA CONNAISSANCE
4 LIS - Logical Information Systems
IRISA-D7 - GESTION DES DONNÉES ET DE LA CONNAISSANCE
Abstract : 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.
Complete list of metadatas

Cited literature [17 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-01640498
Contributor : Alexandre Termier <>
Submitted on : Monday, November 20, 2017 - 5:51:15 PM
Last modification on : Monday, April 1, 2019 - 12:49:55 PM
Long-term archiving on : Wednesday, February 21, 2018 - 4:06:10 PM

File

emnlp2017.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01640498, version 1

Citation

Clément Gautrais, Peggy Cellier, René Quiniou, Alexandre Termier. Topic Signatures in Political Campaign Speeches. EMNLP 2017 - Conference on Empirical Methods in Natural Language Processing, Sep 2017, Copenhagen, Denmark. ⟨hal-01640498⟩

Share

Metrics

Record views

680

Files downloads

743