Using word embeddings to improve the discriminability of co-occurrence text networks

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 cooccurrence 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.

State of the Art in Authorship Attribution With Impact Analysis of Stylometric Features on Style Breach Prediction

“…There is an interesting conclusion made by few studies mentioning that instead by neglecting stopwords, a modest worldwide thresholding plan to create virtual links Word co-occurrence networks have been active to examined texts both in the real-world and hypothetical situations (Quispe 2013). This can be regarded as the finest application of word embeddings as a tool to create virtual links in co-occurrence networks whitethorn enhance the excellence of classification systems.…”