Probing the topological properties of complex networks modeling short written texts

Abstract

In recent years, graph theory has been widely employed to probe several language properties. More specifically, the so-called word adjacency model has been proven useful for tackling several practical problems, especially those relying on textual stylistic analysis. The most common approach to treat texts as networks has simply considered either large pieces of texts or entire books. This approach has certainly worked well -- many informative discoveries have been made this way -- but it raises an uncomfortable question: could there be important topological patterns in small pieces of texts? To address this problem, the topological properties of subtexts sampled from entire books was probed. Statistical analyzes performed on a dataset comprising 50 novels revealed that most of the traditional topological measurements are stable for short subtexts. When the performance of the authorship recognition task was analyzed, it was found that a proper sampling yields a discriminability similar to the one found with full texts. Surprisingly, the support vector machine classification based on the characterization of short texts outperformed the one performed with entire books. These findings suggest that a local topological analysis of large documents might improve its global characterization. Most importantly, it was verified, as a proof of principle, that short texts can be analyzed with the methods and concepts of complex networks. As a consequence, the techniques described here can be extended in a straightforward fashion to analyze texts as time-varying complex networks.

References in corpus (25)

• Community structure in social and biological networks
• Networks in Cognitive Science
• Time varying networks and the weakness of strong ties
• Word sense disambiguation: a survey
• A systematic comparison of supervised classifiers
• Network properties of written human language
• The Topology of Music Recommendation Networks
• Signatures of small-world and scale-free properties in large computer programs
• Hierarchical characterization of complex networks
• Characterizing the network topology of the energy landscapes of atomic clusters
• A complex network approach to stylometry
• Statistical keyword detection in literary corpora
• Let Your CyberAlter Ego Share Information and Manage Spam
• Probing the statistical properties of unknown texts: application to the Voynich Manuscript
• Wikipedia information flow analysis reveals the scale-free architecture of the Semantic Space
• Structure-semantics interplay in complex networks and its effects on the predictability of similarity in texts
• Word sense disambiguation via high order of learning in complex networks
• Authorship recognition via fluctuation analysis of network topology and word intermittency
• Network analysis of the Íslendinga sögur - the Sagas of Icelanders
• Identification of Literary Movements Using Complex Networks to Represent Texts
• Comparing intermittency and network measurements of words and their dependency on authorship
• Complex networks analysis of language complexity
• Complex network analysis of literary and scientific texts
• A Heavenly Example of Scale Free Networks and Self-Organized Criticality
• Discriminating word senses with tourist walks in complex networks

Cited by in corpus (24)

• Text authorship identified using the dynamics of word co-occurrence networks
• A complex network approach to stylometry
• Word sense disambiguation: a complex network approach
• Comparing the writing style of real and artificial papers
• Text-mining forma mentis networks reconstruct public perception of the STEM gender gap in social media
• Using word embeddings to improve the discriminability of co-occurrence text networks
• Concentric network symmetry grasps authors' styles in word adjacency networks
• Paragraph-based complex networks: application to document classification and authenticity verification
• Word sense induction using word embeddings and community detection in complex networks
• On the role of words in the network structure of texts: application to authorship attribution
• Writing about COVID-19 vaccines: Emotional profiling unravels how mainstream and alternative press framed AstraZeneca, Pfizer and vaccination campaigns
• Connecting Network Science and Information Theory
• The Dynamics of Knowledge Acquisition via Self-Learning in Complex Networks
• Complexity-entropy analysis at different levels of organization in written language
• Labelled network subgraphs reveal stylistic subtleties in written texts
• Analyzing the relationship between text features and research proposal productivity
• Semantic flow in language networks
• A pattern recognition approach for distinguishing between prose and poetry
• An Image Analysis Approach to the Calligraphy of Books
• Cognitive networks identify the content of English and Italian popular posts about COVID-19 vaccines: Anticipation, logistics, conspiracy and loss of trust
• Language Networks: a Practical Approach
• K-method of calculating the mutual influence of nodes in a directed weight complex networks
• #lockdown: network-enhanced emotional profiling at the times of COVID-19
• God ($\equiv Elohim$), the first small world network