P-leader multifractal analysis for text type identification

Roberto Leonarduzzi (1) , Patrice Abry (1) , Stéphane Jaffard (2) , Herwig Wendt (3, 4) , Lucie Gournay (5) , Tita Kyriacopoulou (6) , Claude Martineau (6) , Cristian Martinez (6)

1 Phys-ENS - Laboratoire de Physique de l'ENS Lyon
2 LAMA - Laboratoire d'Analyse et de Mathématiques Appliquées
3 IRIT-SC - Signal et Communications
4 CNRS - Centre National de la Recherche Scientifique
5 IMAGER - Institut des mondes anglophones, germanique et roman
6 LIGM - Laboratoire d'Informatique Gaspard-Monge

Among many research efforts devoted to automated art investigations, the problem of quantification of literary style remains current. Meanwhile, linguists and computer scientists have tried to sort out texts according to their types or authors. We use the recently-introduced p-leader multifractal formalism to analyze a corpus of novels written for adults and young adults, with the goal of assessing if a difference in style can be found. Our results agree with the interpretation that novels written for young adults largely follow conventions of the genre, whereas novels written for adults are less homogeneous.

Mots clés: text analysis; stylometry; Multifractal analysis; p-leaders

Domaines: Mathématiques [math]; Linguistique

Roberto Leonarduzzi, Patrice Abry, Stéphane Jaffard, Herwig Wendt, Lucie Gournay, et al.. P-leader multifractal analysis for text type identification. IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2017), IEEE, Mar 2017, New Orleans, United States. pp.4661-4665, ⟨10.1109/ICASSP.2017.7953040⟩. ⟨hal-01579780⟩