Scale and time dependence of serial correlations in word-length time series of written texts

Aguilar-Cornejo, M.; Femat, R.; Alvarez-Ramı́rez, José

doi:10.1016/j.physa.2014.07.063

Cited by 13 publications

(9 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Since our work here is based on the NVG analysis of the integrated word-length series, the corresponding relationship for the increments (i.e., the original word-length values) would be γ = 2 − β , with β = β − 2 [27]. Given our values of γ s ≈ 1.7 and γ l ≈ 1.3, this means that the corresponding exponents of the power spectrum are given by β s ≈ 0.3 and β l ≈ 0.7, in agreement with previous results obtained for small datasets [5,20,21].…”

Section: Resultssupporting

confidence: 90%

“…However, the direct evaluation of these correlations is not feasible, because words can be used in different manners, which can make a quantitative analysis difficult. In past years, diverse methods have been used to explore the presence of temporal correlations in texts [5,20,21], mainly focused on the length or frequency of words. Very recently, it has been reported that there are some differences between European languages when they are compared in terms of the frequency and correlations of the word lengths [11].…”

Section: Introductionmentioning

confidence: 99%

“…As is recognized, written language is the conformation of grammar properties and semantic connotations with the purpose of expressing ideas or information. It has been reported that the temporal organization of word-length sequences from written texts can be characterized by the presence of slightly positive correlations [5,20] and with local variations of the scaling exponents related to the temporal organization of the texts [21].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Word-Length Correlations and Memory in Large Texts: A Visibility Network Analysis

Guzmán‐Vargas

Obregón-Quintana

Aguilar-Velázquez

et al. 2015

Entropy

View full text Add to dashboard Cite

We study the correlation properties of word lengths in large texts from 30 ebooks in the English language from the Gutenberg Project (www.gutenberg.org) using the natural visibility graph method (NVG). NVG converts a time series into a graph and then analyzes its graph properties. First, the original sequence of words is transformed into a sequence of values containing the length of each word, and then, it is integrated. Next, we apply the NVG to the integrated word-length series and construct the network. We show that the degree distribution of that network follows a power law, P (k) ∼ k −γ , with two regimes, which are characterized by the exponents γ s ≈ 1.7 (at short degree scales) and γ l ≈ 1.3 (at large degree scales). This suggests that word lengths are much more strongly correlated at large distances between words than at short distances between words. That finding is also supported by the detrended fluctuation analysis (DFA) and recurrence time distribution. These results provideEntropy 2015, 177799 new information about the universal characteristics of the structure of written texts beyond that given by word frequencies.

show abstract

Section: Resultssupporting

confidence: 90%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Word-Length Correlations and Memory in Large Texts: A Visibility Network Analysis

Guzmán‐Vargas

Obregón-Quintana

Aguilar-Velázquez

et al. 2015

Entropy

View full text Add to dashboard Cite

show abstract

“…Several papers have used similar methods to map texts into token length sequences [24,[56][57][58][59]. The token length sequence mapping method (Eq.…”

Section: Token Length Sequence (Tls)mentioning

confidence: 99%

Enriching feature engineering for short text samples by language time series analysis

2020

View full text Add to dashboard Cite

In this case study, we are extending feature engineering approaches for short text samples by integrating techniques which have been introduced in the context of time series classification and signal processing. The general idea of the presented feature engineering approach is to tokenize the text samples under consideration and map each token to a number, which measures a specific property of the token. Consequently, each text sample becomes a language time series, which is generated from consecutively emitted tokens, and time is represented by the position of the respective token within the text sample. The resulting language time series can be characterised by collections of established time series feature extraction algorithms from time series analysis and signal processing. This approach maps each text sample (irrespective of its original length) to 3970 stylometric features, which can be analysed with standard statistical learning methodologies. The proposed feature engineering technique for short text data is applied to two different corpora: the Federalist Papers data set and the Spooky Books data set. We demonstrate that the extracted language time series features can be successfully combined with standard machine learning approaches for natural language processing and have the potential to improve the classification performance. Furthermore, the suggested feature engineering approach can be used for visualizing differences and commonalities of stylometric features. The presented framework models the systematic feature engineering based on approaches from time series classification and develops a statistical testing methodology for multi-classification problems.

show abstract

“…The key difference between one and othersthem is the use of the forms of a lexeme to build words and sentences. In this context, many methods developed in the study of time-series analysis and network science are potentially suitable to evaluate this kind of structural differences [ 7 , 8 , 9 , 10 , 11 , 12 , 13 , 14 , 15 ].…”

Section: Introductionmentioning

confidence: 99%

Recurrence Networks in Natural Languages

Baeza-Blancas

Obregón-Quintana

Hernández-Gómez³

et al. 2019

Entropy

View full text Add to dashboard Cite

We present a study of natural language using the recurrence network method. In our approach, the repetition of patterns of characters is evaluated without considering the word structure in written texts from different natural languages. Our dataset comprises 85 ebookseBooks written in 17 different European languages. The similarity between patterns of length m is determined by the Hamming distance and a value r is considered to define a matching between two patterns, i.e., a repetition is defined if the Hamming distance is equal or less than the given threshold value r. In this way, we calculate the adjacency matrix, where a connection between two nodes exists when a matching occurs. Next, the recurrence network is constructed for the texts and some representative network metrics are calculated. Our results show that average values of network density, clustering, and assortativity are larger than their corresponding shuffled versions, while for metrics like such as closeness, both original and random sequences exhibit similar values. Moreover, our calculations show similar average values for density among languages which that belong to the same linguistic family. In addition, the application of a linear discriminant analysis leads to well-separated clusters of family languages based on based on the network-density properties. Finally, we discuss our results in the context of the general characteristics of written texts.

show abstract

Scale and time dependence of serial correlations in word-length time series of written texts

Cited by 13 publications

References 13 publications

Word-Length Correlations and Memory in Large Texts: A Visibility Network Analysis

Word-Length Correlations and Memory in Large Texts: A Visibility Network Analysis

Enriching feature engineering for short text samples by language time series analysis

Recurrence Networks in Natural Languages

Contact Info

Product

Resources

About