Using word embeddings to improve the discriminability of co-occurrence text networks
arXiv:2003.06279 · doi:10.1016/j.physa.2020.125344
Abstract
Word co-occurrence networks have been employed to analyze texts both in the practical and theoretical scenarios. Despite the relative success in several applications, traditional co-occurrence networks fail in establishing links between similar words whenever they appear distant in the text. Here we investigate whether the use of word embeddings as a tool to create virtual links in co-occurrence networks may improve the quality of classification systems. Our results revealed that the discriminability in the stylometry task is improved when using Glove, Word2Vec and FastText. In addition, we found that optimized results are obtained when stopwords are not disregarded and a simple global thresholding strategy is used to establish virtual links. Because the proposed approach is able to improve the representation of texts as complex networks, we believe that it could be extended to study other natural language processing tasks. Likewise, theoretical languages studies could benefit from the adopted enriched representation of word co-occurrence networks.
References in corpus (23)
- Efficient Estimation of Word Representations in Vector Space
- XLNet: Generalized Autoregressive Pretraining for Language Understanding
- Extracting the multiscale backbone of complex weighted networks
- Networks in Cognitive Science
- Text authorship identified using the dynamics of word co-occurrence networks
- A complex network approach to stylometry
- Word sense disambiguation: a complex network approach
- Probing the topological properties of complex networks modeling short written texts
- Authorship Attribution through Function Word Adjacency Networks
- Knowledge Acquisition: A Complex Networks Approach
- Probing the statistical properties of unknown texts: application to the Voynich Manuscript
- Classifying informative and imaginative prose using complex networks
- Analyzing complex networks through correlations in centrality measurements
- Modeling the clustering in citation networks
- Concentric network symmetry grasps authors' styles in word adjacency networks
- On the use of topological features and hierarchical characterization for disambiguating names in collaborative networks
- Linguistic data mining with complex networks: a stylometric-oriented approach
- In narrative texts punctuation marks obey the same statistics as words
- Complex networks analysis of language complexity
- Patterns in the English Language: Phonological Networks, Percolation and Assembly Models
- Complexity-entropy analysis at different levels of organization in written language
- Labelled network subgraphs reveal stylistic subtleties in written texts
- Building Networks for Image Segmentation using Particle Competition and Cooperation