Detrended fluctuation analysis of sentiment patterns in literary texts
Authors:
- Łukasz Gaża,
- Stanisław Drożdż,
- Paweł Oświęcimka,
- Marek Stanuszek
Abstract
Temporal correlations of the sentiment content in consecutive sentences are studied based on a large corpus of the world-famous literary texts in four major European languages (English, French, German, and Spanish). For quantifying the related characteristics in terms of the Hurst exponents the Detrended Fluctuation Analysis (DFA) is employed. The results obtained provide a clear indication for the existence of persistent correlations as revealed by the Hurst exponents significantly larger than 1/2 in all the four languages studied. An interesting result that requires a deeper study is the identified fact that in many texts the DFA indicates two different regimes of scaling and thus two different Hurst exponents. In those cases - quite universally - the cross-over occurs at the scale corresponding to about 200 sentences and the Hurst exponents at the scales above this value are even larger which indicates the presence of stronger long-range temporal correlations than those at the shorter scales.
- Record ID
- CUT8286eac176c3433faabe9795bf37295b
- Publication categories
- ; ;
- Author
- Pages
- 549-555
- Other elements of collation
- tab.; wykr.; Bibliografia (na s.) - 554; Bibliografia (liczba pozycji) - 15; Oznaczenie streszczenia - Abstr.
- Substantive notes
- Wydaw. wg cop.
- Miejsce wyd. wg siedziby wydaw.
- Punktacja MNiSW/MEiN (rozdział) - 5
- Book
- Vicario Enrico, Enrico Vicario Bandinelli Romeo, Romeo Bandinelli Fani Virginia Virginia Fani [et al.] (eds.): ECMS 2023 : proceedings of the 37th ECMS International Conference on Modelling and Simulation, June 20th – June 23rd, 2023 Florence, Italy, European Conference for Modelling and Simulation, no. Vol. 37, Iss. 1, 2023, Caserta, ECMS, ISBN 978-3-937436-80-7 (Print)
- Keywords in English
- sentiment analysis, simulation, detrended fluctuation analysis, time-series analysis
- URL
- https://www.scs-europe.net/dlib/dl-index.htm Opening in a new tab
- Language
- eng (en) English
- License
- Score (nominal)
- 5
- Score source
- publisherList
- Score
- Additional fields
- Indeksowana w: Scopus, CORE
- Uniform Resource Identifier
- https://cris.pk.edu.pl/info/article/CUT8286eac176c3433faabe9795bf37295b/
- URN
urn:pkr-prod:CUT8286eac176c3433faabe9795bf37295b
* presented citation count is obtained through Internet information analysis, and it is close to the number calculated by the Publish or PerishOpening in a new tab system.