Strong correlations between text quality and complex networks features

Abstract

Concepts of complex networks have been used to obtain metrics that were correlated to text quality established by scores assigned by human judges. Texts produced by high-school students in Portuguese were represented as scale-free networks (word adjacency model), from which typical network features such as the in/outdegree, clustering coefficient and shortest path were obtained. Another metric was derived from the dynamics of the network growth, based on the variation of the number of connected components. The scores assigned by the human judges according to three text quality criteria (coherence and cohesion, adherence to standard writing conventions and theme adequacy/development) were correlated with the network measurements. Text quality for all three criteria was found to decrease with increasing average values of outdegrees, clustering coefficient and deviation from the dynamics of network growth. Among the criteria employed, cohesion and coherence showed the strongest correlation, which probably indicates that the network measurements are able to capture how the text is developed in terms of the concepts represented by the nodes in the networks. Though based on a particular set of texts and specific language, the results presented here point to potential applications in other instances of text analysis.

8 pages, 8 figures

References in corpus (15)

• Statistical mechanics of complex networks
• The structure and function of complex networks
• Lethality and centrality in protein networks
• The diameter of the world wide web
• Evolution of networks
• Characterization of complex networks: A survey of measurements
• Community Structure in Jazz
• Detecting communities in large networks
• Topology of the conceptual network of language
• Global Organization of the Lexicon
• Percolation in Directed Scale-Free Networks
• Thesaurus as a complex network
• Using Curvature and Markov Clustering in Graphs for Lexical Acquisition and Word Sense Discrimination
• What's in a name?
• Fractal Power Law in Literary English

Cited by in corpus (19)

• Analyzing and Modeling Real-World Phenomena with Complex Networks: A Survey of Applications
• A complex network approach to stylometry
• Generalized Hurst exponent and multifractal function of original and translated texts mapped into frequency and length time series
• Structure-semantics interplay in complex networks and its effects on the predictability of similarity in texts
• Good practices for a literature survey are not followed by authors while preparing scientific manuscripts
• Authorship recognition via fluctuation analysis of network topology and word intermittency
• Identification of Literary Movements Using Complex Networks to Represent Texts
• Comparing intermittency and network measurements of words and their dependency on authorship
• Chain motifs: The tails and handles of complex networks
• Border trees of complex networks
• Analyzing the relationship between text features and research proposal productivity
• A perspective on the advancement of natural language processing tasks via topological analysis of complex networks
• Inflection system of a language as a complex network
• Average shortest-path length in word-adjacency networks: Chinese versus English
• Harmonic structures of Beethoven quartets: a complex network approach
• Language Networks: a Practical Approach
• A model of language inflection graphs
• Modeling belief systems with scale-free networks
• God ($\equiv Elohim$), the first small world network